google-api-client 0.28.4 → 0.29.2

data/generated/google/apis/videointelligence_v1/classes.rb

@@ -277,6 +277,16 @@ module Google
       class GoogleCloudVideointelligenceV1LabelDetectionConfig
         include Google::Apis::Core::Hashable
       
+        # The confidence threshold we perform filtering on the labels from
+        # frame-level detection. If not set, it is set to 0.4 by default. The valid
+        # range for this threshold is [0.1, 0.9]. Any value set outside of this
+        # range will be clipped.
+        # Note: for best results please follow the default threshold. We will update
+        # the default threshold everytime when we release a new model.
+        # Corresponds to the JSON property `frameConfidenceThreshold`
+        # @return [Float]
+        attr_accessor :frame_confidence_threshold
+      
         # What labels should be detected with LABEL_DETECTION, in addition to
         # video-level labels or segment-level labels.
         # If unspecified, defaults to `SHOT_MODE`.
@@ -299,15 +309,27 @@ module Google
         attr_accessor :stationary_camera
         alias_method :stationary_camera?, :stationary_camera
       
+        # The confidence threshold we perform filtering on the labels from
+        # video-level and shot-level detections. If not set, it is set to 0.3 by
+        # default. The valid range for this threshold is [0.1, 0.9]. Any value set
+        # outside of this range will be clipped.
+        # Note: for best results please follow the default threshold. We will update
+        # the default threshold everytime when we release a new model.
+        # Corresponds to the JSON property `videoConfidenceThreshold`
+        # @return [Float]
+        attr_accessor :video_confidence_threshold
+      
         def initialize(**args)
            update!(**args)
         end
       
         # Update properties of this object
         def update!(**args)
+          @frame_confidence_threshold = args[:frame_confidence_threshold] if args.key?(:frame_confidence_threshold)
           @label_detection_mode = args[:label_detection_mode] if args.key?(:label_detection_mode)
           @model = args[:model] if args.key?(:model)
           @stationary_camera = args[:stationary_camera] if args.key?(:stationary_camera)
+          @video_confidence_threshold = args[:video_confidence_threshold] if args.key?(:video_confidence_threshold)
         end
       end
       
@@ -362,6 +384,184 @@ module Google
         end
       end
       
+      # Normalized bounding box.
+      # The normalized vertex coordinates are relative to the original image.
+      # Range: [0, 1].
+      class GoogleCloudVideointelligenceV1NormalizedBoundingBox
+        include Google::Apis::Core::Hashable
+      
+        # Bottom Y coordinate.
+        # Corresponds to the JSON property `bottom`
+        # @return [Float]
+        attr_accessor :bottom
+      
+        # Left X coordinate.
+        # Corresponds to the JSON property `left`
+        # @return [Float]
+        attr_accessor :left
+      
+        # Right X coordinate.
+        # Corresponds to the JSON property `right`
+        # @return [Float]
+        attr_accessor :right
+      
+        # Top Y coordinate.
+        # Corresponds to the JSON property `top`
+        # @return [Float]
+        attr_accessor :top
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @bottom = args[:bottom] if args.key?(:bottom)
+          @left = args[:left] if args.key?(:left)
+          @right = args[:right] if args.key?(:right)
+          @top = args[:top] if args.key?(:top)
+        end
+      end
+      
+      # Normalized bounding polygon for text (that might not be aligned with axis).
+      # Contains list of the corner points in clockwise order starting from
+      # top-left corner. For example, for a rectangular bounding box:
+      # When the text is horizontal it might look like:
+      # 0----1
+      # |    |
+      # 3----2
+      # When it's clockwise rotated 180 degrees around the top-left corner it
+      # becomes:
+      # 2----3
+      # |    |
+      # 1----0
+      # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+      # than 0, or greater than 1 due to trignometric calculations for location of
+      # the box.
+      class GoogleCloudVideointelligenceV1NormalizedBoundingPoly
+        include Google::Apis::Core::Hashable
+      
+        # Normalized vertices of the bounding polygon.
+        # Corresponds to the JSON property `vertices`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1NormalizedVertex>]
+        attr_accessor :vertices
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @vertices = args[:vertices] if args.key?(:vertices)
+        end
+      end
+      
+      # A vertex represents a 2D point in the image.
+      # NOTE: the normalized vertex coordinates are relative to the original image
+      # and range from 0 to 1.
+      class GoogleCloudVideointelligenceV1NormalizedVertex
+        include Google::Apis::Core::Hashable
+      
+        # X coordinate.
+        # Corresponds to the JSON property `x`
+        # @return [Float]
+        attr_accessor :x
+      
+        # Y coordinate.
+        # Corresponds to the JSON property `y`
+        # @return [Float]
+        attr_accessor :y
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @x = args[:x] if args.key?(:x)
+          @y = args[:y] if args.key?(:y)
+        end
+      end
+      
+      # Annotations corresponding to one tracked object.
+      class GoogleCloudVideointelligenceV1ObjectTrackingAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # Object category's labeling confidence of this track.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1Entity]
+        attr_accessor :entity
+      
+        # Information corresponding to all frames where this object track appears.
+        # Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame
+        # messages in frames.
+        # Streaming mode: it can only be one ObjectTrackingFrame message in frames.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1ObjectTrackingFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1VideoSegment]
+        attr_accessor :segment
+      
+        # Streaming mode ONLY.
+        # In streaming mode, we do not know the end time of a tracked object
+        # before it is completed. Hence, there is no VideoSegment info returned.
+        # Instead, we provide a unique identifiable integer track_id so that
+        # the customers can correlate the results of the ongoing
+        # ObjectTrackAnnotation of the same track_id over time.
+        # Corresponds to the JSON property `trackId`
+        # @return [Fixnum]
+        attr_accessor :track_id
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @entity = args[:entity] if args.key?(:entity)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+          @track_id = args[:track_id] if args.key?(:track_id)
+        end
+      end
+      
+      # Video frame level annotations for object detection and tracking. This field
+      # stores per frame location, time offset, and confidence.
+      class GoogleCloudVideointelligenceV1ObjectTrackingFrame
+        include Google::Apis::Core::Hashable
+      
+        # Normalized bounding box.
+        # The normalized vertex coordinates are relative to the original image.
+        # Range: [0, 1].
+        # Corresponds to the JSON property `normalizedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1NormalizedBoundingBox]
+        attr_accessor :normalized_bounding_box
+      
+        # The timestamp of the frame in microseconds.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @normalized_bounding_box = args[:normalized_bounding_box] if args.key?(:normalized_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
       # Config for SHOT_CHANGE_DETECTION.
       class GoogleCloudVideointelligenceV1ShotChangeDetectionConfig
         include Google::Apis::Core::Hashable
@@ -574,31 +774,44 @@ module Google
         end
       end
       
-      # Annotation progress for a single video.
-      class GoogleCloudVideointelligenceV1VideoAnnotationProgress
+      # Annotations related to one detected OCR text snippet. This will contain the
+      # corresponding text, confidence value, and frame level information for each
+      # detection.
+      class GoogleCloudVideointelligenceV1TextAnnotation
         include Google::Apis::Core::Hashable
       
-        # Video file location in
-        # [Google Cloud Storage](https://cloud.google.com/storage/).
-        # Corresponds to the JSON property `inputUri`
+        # All video segments where OCR detected text appears.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1TextSegment>]
+        attr_accessor :segments
+      
+        # The detected text.
+        # Corresponds to the JSON property `text`
         # @return [String]
-        attr_accessor :input_uri
+        attr_accessor :text
       
-        # Approximate percentage processed thus far. Guaranteed to be
-        # 100 when fully processed.
-        # Corresponds to the JSON property `progressPercent`
-        # @return [Fixnum]
-        attr_accessor :progress_percent
+        def initialize(**args)
+           update!(**args)
+        end
       
-        # Time when the request was received.
-        # Corresponds to the JSON property `startTime`
-        # @return [String]
-        attr_accessor :start_time
+        # Update properties of this object
+        def update!(**args)
+          @segments = args[:segments] if args.key?(:segments)
+          @text = args[:text] if args.key?(:text)
+        end
+      end
       
-        # Time of the most recent update.
-        # Corresponds to the JSON property `updateTime`
-        # @return [String]
-        attr_accessor :update_time
+      # Config for TEXT_DETECTION.
+      class GoogleCloudVideointelligenceV1TextDetectionConfig
+        include Google::Apis::Core::Hashable
+      
+        # Language hint can be specified if the language to be detected is known a
+        # priori. It can increase the accuracy of the detection. Language hint must
+        # be language code in BCP-47 format.
+        # Automatic language detection is performed if no hint is provided.
+        # Corresponds to the JSON property `languageHints`
+        # @return [Array<String>]
+        attr_accessor :language_hints
       
         def initialize(**args)
            update!(**args)
@@ -606,54 +819,163 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @input_uri = args[:input_uri] if args.key?(:input_uri)
-          @progress_percent = args[:progress_percent] if args.key?(:progress_percent)
-          @start_time = args[:start_time] if args.key?(:start_time)
-          @update_time = args[:update_time] if args.key?(:update_time)
+          @language_hints = args[:language_hints] if args.key?(:language_hints)
         end
       end
       
-      # Annotation results for a single video.
-      class GoogleCloudVideointelligenceV1VideoAnnotationResults
+      # Video frame level annotation results for text annotation (OCR).
+      # Contains information regarding timestamp and bounding box locations for the
+      # frames containing detected OCR text snippets.
+      class GoogleCloudVideointelligenceV1TextFrame
         include Google::Apis::Core::Hashable
       
-        # The `Status` type defines a logical error model that is suitable for different
-        # programming environments, including REST APIs and RPC APIs. It is used by
-        # [gRPC](https://github.com/grpc). The error model is designed to be:
-        # - Simple to use and understand for most users
-        # - Flexible enough to meet unexpected needs
-        # # Overview
-        # The `Status` message contains three pieces of data: error code, error message,
-        # and error details. The error code should be an enum value of
-        # google.rpc.Code, but it may accept additional error codes if needed.  The
-        # error message should be a developer-facing English message that helps
-        # developers *understand* and *resolve* the error. If a localized user-facing
-        # error message is needed, put the localized message in the error details or
-        # localize it in the client. The optional error details may contain arbitrary
-        # information about the error. There is a predefined set of error detail types
-        # in the package `google.rpc` that can be used for common error conditions.
-        # # Language mapping
-        # The `Status` message is the logical representation of the error model, but it
-        # is not necessarily the actual wire format. When the `Status` message is
-        # exposed in different client libraries and different wire protocols, it can be
-        # mapped differently. For example, it will likely be mapped to some exceptions
-        # in Java, but more likely mapped to some error codes in C.
-        # # Other uses
-        # The error model and the `Status` message can be used in a variety of
-        # environments, either with or without APIs, to provide a
-        # consistent developer experience across different environments.
-        # Example uses of this error model include:
-        # - Partial errors. If a service needs to return partial errors to the client,
-        # it may embed the `Status` in the normal response to indicate the partial
-        # errors.
-        # - Workflow errors. A typical workflow has multiple steps. Each step may
-        # have a `Status` message for error reporting.
-        # - Batch operations. If a client uses batch request and batch response, the
-        # `Status` message should be used directly inside batch response, one for
-        # each error sub-response.
-        # - Asynchronous operations. If an API call embeds asynchronous operation
-        # results in its response, the status of those operations should be
-        # represented directly using the `Status` message.
+        # Normalized bounding polygon for text (that might not be aligned with axis).
+        # Contains list of the corner points in clockwise order starting from
+        # top-left corner. For example, for a rectangular bounding box:
+        # When the text is horizontal it might look like:
+        # 0----1
+        # |    |
+        # 3----2
+        # When it's clockwise rotated 180 degrees around the top-left corner it
+        # becomes:
+        # 2----3
+        # |    |
+        # 1----0
+        # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+        # than 0, or greater than 1 due to trignometric calculations for location of
+        # the box.
+        # Corresponds to the JSON property `rotatedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1NormalizedBoundingPoly]
+        attr_accessor :rotated_bounding_box
+      
+        # Timestamp of this frame.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @rotated_bounding_box = args[:rotated_bounding_box] if args.key?(:rotated_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Video segment level annotation results for text detection.
+      class GoogleCloudVideointelligenceV1TextSegment
+        include Google::Apis::Core::Hashable
+      
+        # Confidence for the track of detected text. It is calculated as the highest
+        # over all frames where OCR detected text appears.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Information related to the frames where OCR detected text appears.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1TextFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1VideoSegment]
+        attr_accessor :segment
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+        end
+      end
+      
+      # Annotation progress for a single video.
+      class GoogleCloudVideointelligenceV1VideoAnnotationProgress
+        include Google::Apis::Core::Hashable
+      
+        # Video file location in
+        # [Google Cloud Storage](https://cloud.google.com/storage/).
+        # Corresponds to the JSON property `inputUri`
+        # @return [String]
+        attr_accessor :input_uri
+      
+        # Approximate percentage processed thus far. Guaranteed to be
+        # 100 when fully processed.
+        # Corresponds to the JSON property `progressPercent`
+        # @return [Fixnum]
+        attr_accessor :progress_percent
+      
+        # Time when the request was received.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # Time of the most recent update.
+        # Corresponds to the JSON property `updateTime`
+        # @return [String]
+        attr_accessor :update_time
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @progress_percent = args[:progress_percent] if args.key?(:progress_percent)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @update_time = args[:update_time] if args.key?(:update_time)
+        end
+      end
+      
+      # Annotation results for a single video.
+      class GoogleCloudVideointelligenceV1VideoAnnotationResults
+        include Google::Apis::Core::Hashable
+      
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
+        # - Simple to use and understand for most users
+        # - Flexible enough to meet unexpected needs
+        # # Overview
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
+        # google.rpc.Code, but it may accept additional error codes if needed.  The
+        # error message should be a developer-facing English message that helps
+        # developers *understand* and *resolve* the error. If a localized user-facing
+        # error message is needed, put the localized message in the error details or
+        # localize it in the client. The optional error details may contain arbitrary
+        # information about the error. There is a predefined set of error detail types
+        # in the package `google.rpc` that can be used for common error conditions.
+        # # Language mapping
+        # The `Status` message is the logical representation of the error model, but it
+        # is not necessarily the actual wire format. When the `Status` message is
+        # exposed in different client libraries and different wire protocols, it can be
+        # mapped differently. For example, it will likely be mapped to some exceptions
+        # in Java, but more likely mapped to some error codes in C.
+        # # Other uses
+        # The error model and the `Status` message can be used in a variety of
+        # environments, either with or without APIs, to provide a
+        # consistent developer experience across different environments.
+        # Example uses of this error model include:
+        # - Partial errors. If a service needs to return partial errors to the client,
+        # it may embed the `Status` in the normal response to indicate the partial
+        # errors.
+        # - Workflow errors. A typical workflow has multiple steps. Each step may
+        # have a `Status` message for error reporting.
+        # - Batch operations. If a client uses batch request and batch response, the
+        # `Status` message should be used directly inside batch response, one for
+        # each error sub-response.
+        # - Asynchronous operations. If an API call embeds asynchronous operation
+        # results in its response, the status of those operations should be
+        # represented directly using the `Status` message.
         # - Logging. If some API errors are stored in logs, the message `Status` could
         # be used directly after any stripping needed for security/privacy reasons.
         # Corresponds to the JSON property `error`
@@ -679,6 +1001,11 @@ module Google
         # @return [String]
         attr_accessor :input_uri
       
+        # Annotations for list of objects detected and tracked in video.
+        # Corresponds to the JSON property `objectAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1ObjectTrackingAnnotation>]
+        attr_accessor :object_annotations
+      
         # Label annotations on video level or user specified segment level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `segmentLabelAnnotations`
@@ -701,6 +1028,13 @@ module Google
         # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1SpeechTranscription>]
         attr_accessor :speech_transcriptions
       
+        # OCR text detection and tracking.
+        # Annotations for list of detected text snippets. Each will have list of
+        # frame information associated with it.
+        # Corresponds to the JSON property `textAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1TextAnnotation>]
+        attr_accessor :text_annotations
+      
         def initialize(**args)
            update!(**args)
         end
@@ -711,10 +1045,12 @@ module Google
           @explicit_annotation = args[:explicit_annotation] if args.key?(:explicit_annotation)
           @frame_label_annotations = args[:frame_label_annotations] if args.key?(:frame_label_annotations)
           @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @object_annotations = args[:object_annotations] if args.key?(:object_annotations)
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
           @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
+          @text_annotations = args[:text_annotations] if args.key?(:text_annotations)
         end
       end
       
@@ -749,6 +1085,11 @@ module Google
         # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1SpeechTranscriptionConfig]
         attr_accessor :speech_transcription_config
       
+        # Config for TEXT_DETECTION.
+        # Corresponds to the JSON property `textDetectionConfig`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1TextDetectionConfig]
+        attr_accessor :text_detection_config
+      
         def initialize(**args)
            update!(**args)
         end
@@ -760,6 +1101,7 @@ module Google
           @segments = args[:segments] if args.key?(:segments)
           @shot_change_detection_config = args[:shot_change_detection_config] if args.key?(:shot_change_detection_config)
           @speech_transcription_config = args[:speech_transcription_config] if args.key?(:speech_transcription_config)
+          @text_detection_config = args[:text_detection_config] if args.key?(:text_detection_config)
         end
       end
       
@@ -1062,29 +1404,31 @@ module Google
         end
       end
       
-      # Alternative hypotheses (a.k.a. n-best list).
-      class GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative
+      # Normalized bounding box.
+      # The normalized vertex coordinates are relative to the original image.
+      # Range: [0, 1].
+      class GoogleCloudVideointelligenceV1beta2NormalizedBoundingBox
         include Google::Apis::Core::Hashable
       
-        # The confidence estimate between 0.0 and 1.0. A higher number
-        # indicates an estimated greater likelihood that the recognized words are
-        # correct. This field is typically provided only for the top hypothesis, and
-        # only for `is_final=true` results. Clients should not rely on the
-        # `confidence` field as it is not guaranteed to be accurate or consistent.
-        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
-        # Corresponds to the JSON property `confidence`
+        # Bottom Y coordinate.
+        # Corresponds to the JSON property `bottom`
         # @return [Float]
-        attr_accessor :confidence
+        attr_accessor :bottom
       
-        # Transcript text representing the words that the user spoke.
-        # Corresponds to the JSON property `transcript`
-        # @return [String]
-        attr_accessor :transcript
+        # Left X coordinate.
+        # Corresponds to the JSON property `left`
+        # @return [Float]
+        attr_accessor :left
       
-        # A list of word-specific information for each recognized word.
-        # Corresponds to the JSON property `words`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2WordInfo>]
-        attr_accessor :words
+        # Right X coordinate.
+        # Corresponds to the JSON property `right`
+        # @return [Float]
+        attr_accessor :right
+      
+        # Top Y coordinate.
+        # Corresponds to the JSON property `top`
+        # @return [Float]
+        attr_accessor :top
       
         def initialize(**args)
            update!(**args)
@@ -1092,31 +1436,35 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @confidence = args[:confidence] if args.key?(:confidence)
-          @transcript = args[:transcript] if args.key?(:transcript)
-          @words = args[:words] if args.key?(:words)
+          @bottom = args[:bottom] if args.key?(:bottom)
+          @left = args[:left] if args.key?(:left)
+          @right = args[:right] if args.key?(:right)
+          @top = args[:top] if args.key?(:top)
         end
       end
       
-      # A speech recognition result corresponding to a portion of the audio.
-      class GoogleCloudVideointelligenceV1beta2SpeechTranscription
+      # Normalized bounding polygon for text (that might not be aligned with axis).
+      # Contains list of the corner points in clockwise order starting from
+      # top-left corner. For example, for a rectangular bounding box:
+      # When the text is horizontal it might look like:
+      # 0----1
+      # |    |
+      # 3----2
+      # When it's clockwise rotated 180 degrees around the top-left corner it
+      # becomes:
+      # 2----3
+      # |    |
+      # 1----0
+      # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+      # than 0, or greater than 1 due to trignometric calculations for location of
+      # the box.
+      class GoogleCloudVideointelligenceV1beta2NormalizedBoundingPoly
         include Google::Apis::Core::Hashable
       
-        # May contain one or more recognition hypotheses (up to the maximum specified
-        # in `max_alternatives`).  These alternatives are ordered in terms of
-        # accuracy, with the top (first) alternative being the most probable, as
-        # ranked by the recognizer.
-        # Corresponds to the JSON property `alternatives`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative>]
-        attr_accessor :alternatives
-      
-        # Output only. The
-        # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
-        # language in this result. This language code was detected to have the most
-        # likelihood of being spoken in the audio.
-        # Corresponds to the JSON property `languageCode`
-        # @return [String]
-        attr_accessor :language_code
+        # Normalized vertices of the bounding polygon.
+        # Corresponds to the JSON property `vertices`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2NormalizedVertex>]
+        attr_accessor :vertices
       
         def initialize(**args)
            update!(**args)
@@ -1124,29 +1472,1103 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @alternatives = args[:alternatives] if args.key?(:alternatives)
-          @language_code = args[:language_code] if args.key?(:language_code)
+          @vertices = args[:vertices] if args.key?(:vertices)
         end
       end
       
-      # Annotation progress for a single video.
-      class GoogleCloudVideointelligenceV1beta2VideoAnnotationProgress
+      # A vertex represents a 2D point in the image.
+      # NOTE: the normalized vertex coordinates are relative to the original image
+      # and range from 0 to 1.
+      class GoogleCloudVideointelligenceV1beta2NormalizedVertex
         include Google::Apis::Core::Hashable
       
-        # Video file location in
-        # [Google Cloud Storage](https://cloud.google.com/storage/).
-        # Corresponds to the JSON property `inputUri`
-        # @return [String]
-        attr_accessor :input_uri
-      
-        # Approximate percentage processed thus far. Guaranteed to be
-        # 100 when fully processed.
-        # Corresponds to the JSON property `progressPercent`
-        # @return [Fixnum]
-        attr_accessor :progress_percent
+        # X coordinate.
+        # Corresponds to the JSON property `x`
+        # @return [Float]
+        attr_accessor :x
       
-        # Time when the request was received.
-        # Corresponds to the JSON property `startTime`
+        # Y coordinate.
+        # Corresponds to the JSON property `y`
+        # @return [Float]
+        attr_accessor :y
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @x = args[:x] if args.key?(:x)
+          @y = args[:y] if args.key?(:y)
+        end
+      end
+      
+      # Annotations corresponding to one tracked object.
+      class GoogleCloudVideointelligenceV1beta2ObjectTrackingAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # Object category's labeling confidence of this track.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2Entity]
+        attr_accessor :entity
+      
+        # Information corresponding to all frames where this object track appears.
+        # Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame
+        # messages in frames.
+        # Streaming mode: it can only be one ObjectTrackingFrame message in frames.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2ObjectTrackingFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2VideoSegment]
+        attr_accessor :segment
+      
+        # Streaming mode ONLY.
+        # In streaming mode, we do not know the end time of a tracked object
+        # before it is completed. Hence, there is no VideoSegment info returned.
+        # Instead, we provide a unique identifiable integer track_id so that
+        # the customers can correlate the results of the ongoing
+        # ObjectTrackAnnotation of the same track_id over time.
+        # Corresponds to the JSON property `trackId`
+        # @return [Fixnum]
+        attr_accessor :track_id
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @entity = args[:entity] if args.key?(:entity)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+          @track_id = args[:track_id] if args.key?(:track_id)
+        end
+      end
+      
+      # Video frame level annotations for object detection and tracking. This field
+      # stores per frame location, time offset, and confidence.
+      class GoogleCloudVideointelligenceV1beta2ObjectTrackingFrame
+        include Google::Apis::Core::Hashable
+      
+        # Normalized bounding box.
+        # The normalized vertex coordinates are relative to the original image.
+        # Range: [0, 1].
+        # Corresponds to the JSON property `normalizedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2NormalizedBoundingBox]
+        attr_accessor :normalized_bounding_box
+      
+        # The timestamp of the frame in microseconds.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @normalized_bounding_box = args[:normalized_bounding_box] if args.key?(:normalized_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative
+        include Google::Apis::Core::Hashable
+      
+        # The confidence estimate between 0.0 and 1.0. A higher number
+        # indicates an estimated greater likelihood that the recognized words are
+        # correct. This field is typically provided only for the top hypothesis, and
+        # only for `is_final=true` results. Clients should not rely on the
+        # `confidence` field as it is not guaranteed to be accurate or consistent.
+        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
+      
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2WordInfo>]
+        attr_accessor :words
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
+        end
+      end
+      
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1beta2SpeechTranscription
+        include Google::Apis::Core::Hashable
+      
+        # May contain one or more recognition hypotheses (up to the maximum specified
+        # in `max_alternatives`).  These alternatives are ordered in terms of
+        # accuracy, with the top (first) alternative being the most probable, as
+        # ranked by the recognizer.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
+      
+        # Output only. The
+        # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
+        # language in this result. This language code was detected to have the most
+        # likelihood of being spoken in the audio.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
+      # Annotations related to one detected OCR text snippet. This will contain the
+      # corresponding text, confidence value, and frame level information for each
+      # detection.
+      class GoogleCloudVideointelligenceV1beta2TextAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # All video segments where OCR detected text appears.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2TextSegment>]
+        attr_accessor :segments
+      
+        # The detected text.
+        # Corresponds to the JSON property `text`
+        # @return [String]
+        attr_accessor :text
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @segments = args[:segments] if args.key?(:segments)
+          @text = args[:text] if args.key?(:text)
+        end
+      end
+      
+      # Video frame level annotation results for text annotation (OCR).
+      # Contains information regarding timestamp and bounding box locations for the
+      # frames containing detected OCR text snippets.
+      class GoogleCloudVideointelligenceV1beta2TextFrame
+        include Google::Apis::Core::Hashable
+      
+        # Normalized bounding polygon for text (that might not be aligned with axis).
+        # Contains list of the corner points in clockwise order starting from
+        # top-left corner. For example, for a rectangular bounding box:
+        # When the text is horizontal it might look like:
+        # 0----1
+        # |    |
+        # 3----2
+        # When it's clockwise rotated 180 degrees around the top-left corner it
+        # becomes:
+        # 2----3
+        # |    |
+        # 1----0
+        # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+        # than 0, or greater than 1 due to trignometric calculations for location of
+        # the box.
+        # Corresponds to the JSON property `rotatedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2NormalizedBoundingPoly]
+        attr_accessor :rotated_bounding_box
+      
+        # Timestamp of this frame.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @rotated_bounding_box = args[:rotated_bounding_box] if args.key?(:rotated_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Video segment level annotation results for text detection.
+      class GoogleCloudVideointelligenceV1beta2TextSegment
+        include Google::Apis::Core::Hashable
+      
+        # Confidence for the track of detected text. It is calculated as the highest
+        # over all frames where OCR detected text appears.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Information related to the frames where OCR detected text appears.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2TextFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2VideoSegment]
+        attr_accessor :segment
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+        end
+      end
+      
+      # Annotation progress for a single video.
+      class GoogleCloudVideointelligenceV1beta2VideoAnnotationProgress
+        include Google::Apis::Core::Hashable
+      
+        # Video file location in
+        # [Google Cloud Storage](https://cloud.google.com/storage/).
+        # Corresponds to the JSON property `inputUri`
+        # @return [String]
+        attr_accessor :input_uri
+      
+        # Approximate percentage processed thus far. Guaranteed to be
+        # 100 when fully processed.
+        # Corresponds to the JSON property `progressPercent`
+        # @return [Fixnum]
+        attr_accessor :progress_percent
+      
+        # Time when the request was received.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # Time of the most recent update.
+        # Corresponds to the JSON property `updateTime`
+        # @return [String]
+        attr_accessor :update_time
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @progress_percent = args[:progress_percent] if args.key?(:progress_percent)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @update_time = args[:update_time] if args.key?(:update_time)
+        end
+      end
+      
+      # Annotation results for a single video.
+      class GoogleCloudVideointelligenceV1beta2VideoAnnotationResults
+        include Google::Apis::Core::Hashable
+      
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
+        # - Simple to use and understand for most users
+        # - Flexible enough to meet unexpected needs
+        # # Overview
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
+        # google.rpc.Code, but it may accept additional error codes if needed.  The
+        # error message should be a developer-facing English message that helps
+        # developers *understand* and *resolve* the error. If a localized user-facing
+        # error message is needed, put the localized message in the error details or
+        # localize it in the client. The optional error details may contain arbitrary
+        # information about the error. There is a predefined set of error detail types
+        # in the package `google.rpc` that can be used for common error conditions.
+        # # Language mapping
+        # The `Status` message is the logical representation of the error model, but it
+        # is not necessarily the actual wire format. When the `Status` message is
+        # exposed in different client libraries and different wire protocols, it can be
+        # mapped differently. For example, it will likely be mapped to some exceptions
+        # in Java, but more likely mapped to some error codes in C.
+        # # Other uses
+        # The error model and the `Status` message can be used in a variety of
+        # environments, either with or without APIs, to provide a
+        # consistent developer experience across different environments.
+        # Example uses of this error model include:
+        # - Partial errors. If a service needs to return partial errors to the client,
+        # it may embed the `Status` in the normal response to indicate the partial
+        # errors.
+        # - Workflow errors. A typical workflow has multiple steps. Each step may
+        # have a `Status` message for error reporting.
+        # - Batch operations. If a client uses batch request and batch response, the
+        # `Status` message should be used directly inside batch response, one for
+        # each error sub-response.
+        # - Asynchronous operations. If an API call embeds asynchronous operation
+        # results in its response, the status of those operations should be
+        # represented directly using the `Status` message.
+        # - Logging. If some API errors are stored in logs, the message `Status` could
+        # be used directly after any stripping needed for security/privacy reasons.
+        # Corresponds to the JSON property `error`
+        # @return [Google::Apis::VideointelligenceV1::GoogleRpcStatus]
+        attr_accessor :error
+      
+        # Explicit content annotation (based on per-frame visual signals only).
+        # If no explicit content has been detected in a frame, no annotations are
+        # present for that frame.
+        # Corresponds to the JSON property `explicitAnnotation`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2ExplicitContentAnnotation]
+        attr_accessor :explicit_annotation
+      
+        # Label annotations on frame level.
+        # There is exactly one element for each unique label.
+        # Corresponds to the JSON property `frameLabelAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        attr_accessor :frame_label_annotations
+      
+        # Video file location in
+        # [Google Cloud Storage](https://cloud.google.com/storage/).
+        # Corresponds to the JSON property `inputUri`
+        # @return [String]
+        attr_accessor :input_uri
+      
+        # Annotations for list of objects detected and tracked in video.
+        # Corresponds to the JSON property `objectAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2ObjectTrackingAnnotation>]
+        attr_accessor :object_annotations
+      
+        # Label annotations on video level or user specified segment level.
+        # There is exactly one element for each unique label.
+        # Corresponds to the JSON property `segmentLabelAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        attr_accessor :segment_label_annotations
+      
+        # Shot annotations. Each shot is represented as a video segment.
+        # Corresponds to the JSON property `shotAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2VideoSegment>]
+        attr_accessor :shot_annotations
+      
+        # Label annotations on shot level.
+        # There is exactly one element for each unique label.
+        # Corresponds to the JSON property `shotLabelAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        attr_accessor :shot_label_annotations
+      
+        # Speech transcription.
+        # Corresponds to the JSON property `speechTranscriptions`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2SpeechTranscription>]
+        attr_accessor :speech_transcriptions
+      
+        # OCR text detection and tracking.
+        # Annotations for list of detected text snippets. Each will have list of
+        # frame information associated with it.
+        # Corresponds to the JSON property `textAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2TextAnnotation>]
+        attr_accessor :text_annotations
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @error = args[:error] if args.key?(:error)
+          @explicit_annotation = args[:explicit_annotation] if args.key?(:explicit_annotation)
+          @frame_label_annotations = args[:frame_label_annotations] if args.key?(:frame_label_annotations)
+          @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @object_annotations = args[:object_annotations] if args.key?(:object_annotations)
+          @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
+          @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
+          @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
+          @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
+          @text_annotations = args[:text_annotations] if args.key?(:text_annotations)
+        end
+      end
+      
+      # Video segment.
+      class GoogleCloudVideointelligenceV1beta2VideoSegment
+        include Google::Apis::Core::Hashable
+      
+        # Time-offset, relative to the beginning of the video,
+        # corresponding to the end of the segment (inclusive).
+        # Corresponds to the JSON property `endTimeOffset`
+        # @return [String]
+        attr_accessor :end_time_offset
+      
+        # Time-offset, relative to the beginning of the video,
+        # corresponding to the start of the segment (inclusive).
+        # Corresponds to the JSON property `startTimeOffset`
+        # @return [String]
+        attr_accessor :start_time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @end_time_offset = args[:end_time_offset] if args.key?(:end_time_offset)
+          @start_time_offset = args[:start_time_offset] if args.key?(:start_time_offset)
+        end
+      end
+      
+      # Word-specific information for recognized words. Word information is only
+      # included in the response when certain request parameters are set, such
+      # as `enable_word_time_offsets`.
+      class GoogleCloudVideointelligenceV1beta2WordInfo
+        include Google::Apis::Core::Hashable
+      
+        # Output only. The confidence estimate between 0.0 and 1.0. A higher number
+        # indicates an estimated greater likelihood that the recognized words are
+        # correct. This field is set only for the top alternative.
+        # This field is not guaranteed to be accurate and users should not rely on it
+        # to be always provided.
+        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Time offset relative to the beginning of the audio, and
+        # corresponding to the end of the spoken word. This field is only set if
+        # `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+        # experimental feature and the accuracy of the time offset can vary.
+        # Corresponds to the JSON property `endTime`
+        # @return [String]
+        attr_accessor :end_time
+      
+        # Output only. A distinct integer value is assigned for every speaker within
+        # the audio. This field specifies which one of those speakers was detected to
+        # have spoken this word. Value ranges from 1 up to diarization_speaker_count,
+        # and is only set if speaker diarization is enabled.
+        # Corresponds to the JSON property `speakerTag`
+        # @return [Fixnum]
+        attr_accessor :speaker_tag
+      
+        # Time offset relative to the beginning of the audio, and
+        # corresponding to the start of the spoken word. This field is only set if
+        # `enable_word_time_offsets=true` and only in the top hypothesis. This is an
+        # experimental feature and the accuracy of the time offset can vary.
+        # Corresponds to the JSON property `startTime`
+        # @return [String]
+        attr_accessor :start_time
+      
+        # The word corresponding to this set of information.
+        # Corresponds to the JSON property `word`
+        # @return [String]
+        attr_accessor :word
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @end_time = args[:end_time] if args.key?(:end_time)
+          @speaker_tag = args[:speaker_tag] if args.key?(:speaker_tag)
+          @start_time = args[:start_time] if args.key?(:start_time)
+          @word = args[:word] if args.key?(:word)
+        end
+      end
+      
+      # Video annotation progress. Included in the `metadata`
+      # field of the `Operation` returned by the `GetOperation`
+      # call of the `google::longrunning::Operations` service.
+      class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoProgress
+        include Google::Apis::Core::Hashable
+      
+        # Progress metadata for all videos specified in `AnnotateVideoRequest`.
+        # Corresponds to the JSON property `annotationProgress`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoAnnotationProgress>]
+        attr_accessor :annotation_progress
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @annotation_progress = args[:annotation_progress] if args.key?(:annotation_progress)
+        end
+      end
+      
+      # Video annotation response. Included in the `response`
+      # field of the `Operation` returned by the `GetOperation`
+      # call of the `google::longrunning::Operations` service.
+      class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoResponse
+        include Google::Apis::Core::Hashable
+      
+        # Annotation results for all videos specified in `AnnotateVideoRequest`.
+        # Corresponds to the JSON property `annotationResults`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoAnnotationResults>]
+        attr_accessor :annotation_results
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @annotation_results = args[:annotation_results] if args.key?(:annotation_results)
+        end
+      end
+      
+      # Detected entity from video analysis.
+      class GoogleCloudVideointelligenceV1p1beta1Entity
+        include Google::Apis::Core::Hashable
+      
+        # Textual description, e.g. `Fixed-gear bicycle`.
+        # Corresponds to the JSON property `description`
+        # @return [String]
+        attr_accessor :description
+      
+        # Opaque entity ID. Some IDs may be available in
+        # [Google Knowledge Graph Search
+        # API](https://developers.google.com/knowledge-graph/).
+        # Corresponds to the JSON property `entityId`
+        # @return [String]
+        attr_accessor :entity_id
+      
+        # Language code for `description` in BCP-47 format.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @description = args[:description] if args.key?(:description)
+          @entity_id = args[:entity_id] if args.key?(:entity_id)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
+      # Explicit content annotation (based on per-frame visual signals only).
+      # If no explicit content has been detected in a frame, no annotations are
+      # present for that frame.
+      class GoogleCloudVideointelligenceV1p1beta1ExplicitContentAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # All video frames where explicit content was detected.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ExplicitContentFrame>]
+        attr_accessor :frames
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @frames = args[:frames] if args.key?(:frames)
+        end
+      end
+      
+      # Video frame level annotation results for explicit content.
+      class GoogleCloudVideointelligenceV1p1beta1ExplicitContentFrame
+        include Google::Apis::Core::Hashable
+      
+        # Likelihood of the pornography content..
+        # Corresponds to the JSON property `pornographyLikelihood`
+        # @return [String]
+        attr_accessor :pornography_likelihood
+      
+        # Time-offset, relative to the beginning of the video, corresponding to the
+        # video frame for this location.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @pornography_likelihood = args[:pornography_likelihood] if args.key?(:pornography_likelihood)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Label annotation.
+      class GoogleCloudVideointelligenceV1p1beta1LabelAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # Common categories for the detected entity.
+        # E.g. when the label is `Terrier` the category is likely `dog`. And in some
+        # cases there might be more than one categories e.g. `Terrier` could also be
+        # a `pet`.
+        # Corresponds to the JSON property `categoryEntities`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1Entity>]
+        attr_accessor :category_entities
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1Entity]
+        attr_accessor :entity
+      
+        # All video frames where a label was detected.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelFrame>]
+        attr_accessor :frames
+      
+        # All video segments where a label was detected.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelSegment>]
+        attr_accessor :segments
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @category_entities = args[:category_entities] if args.key?(:category_entities)
+          @entity = args[:entity] if args.key?(:entity)
+          @frames = args[:frames] if args.key?(:frames)
+          @segments = args[:segments] if args.key?(:segments)
+        end
+      end
+      
+      # Video frame level annotation results for label detection.
+      class GoogleCloudVideointelligenceV1p1beta1LabelFrame
+        include Google::Apis::Core::Hashable
+      
+        # Confidence that the label is accurate. Range: [0, 1].
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Time-offset, relative to the beginning of the video, corresponding to the
+        # video frame for this location.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Video segment level annotation results for label detection.
+      class GoogleCloudVideointelligenceV1p1beta1LabelSegment
+        include Google::Apis::Core::Hashable
+      
+        # Confidence that the label is accurate. Range: [0, 1].
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment]
+        attr_accessor :segment
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @segment = args[:segment] if args.key?(:segment)
+        end
+      end
+      
+      # Normalized bounding box.
+      # The normalized vertex coordinates are relative to the original image.
+      # Range: [0, 1].
+      class GoogleCloudVideointelligenceV1p1beta1NormalizedBoundingBox
+        include Google::Apis::Core::Hashable
+      
+        # Bottom Y coordinate.
+        # Corresponds to the JSON property `bottom`
+        # @return [Float]
+        attr_accessor :bottom
+      
+        # Left X coordinate.
+        # Corresponds to the JSON property `left`
+        # @return [Float]
+        attr_accessor :left
+      
+        # Right X coordinate.
+        # Corresponds to the JSON property `right`
+        # @return [Float]
+        attr_accessor :right
+      
+        # Top Y coordinate.
+        # Corresponds to the JSON property `top`
+        # @return [Float]
+        attr_accessor :top
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @bottom = args[:bottom] if args.key?(:bottom)
+          @left = args[:left] if args.key?(:left)
+          @right = args[:right] if args.key?(:right)
+          @top = args[:top] if args.key?(:top)
+        end
+      end
+      
+      # Normalized bounding polygon for text (that might not be aligned with axis).
+      # Contains list of the corner points in clockwise order starting from
+      # top-left corner. For example, for a rectangular bounding box:
+      # When the text is horizontal it might look like:
+      # 0----1
+      # |    |
+      # 3----2
+      # When it's clockwise rotated 180 degrees around the top-left corner it
+      # becomes:
+      # 2----3
+      # |    |
+      # 1----0
+      # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+      # than 0, or greater than 1 due to trignometric calculations for location of
+      # the box.
+      class GoogleCloudVideointelligenceV1p1beta1NormalizedBoundingPoly
+        include Google::Apis::Core::Hashable
+      
+        # Normalized vertices of the bounding polygon.
+        # Corresponds to the JSON property `vertices`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1NormalizedVertex>]
+        attr_accessor :vertices
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @vertices = args[:vertices] if args.key?(:vertices)
+        end
+      end
+      
+      # A vertex represents a 2D point in the image.
+      # NOTE: the normalized vertex coordinates are relative to the original image
+      # and range from 0 to 1.
+      class GoogleCloudVideointelligenceV1p1beta1NormalizedVertex
+        include Google::Apis::Core::Hashable
+      
+        # X coordinate.
+        # Corresponds to the JSON property `x`
+        # @return [Float]
+        attr_accessor :x
+      
+        # Y coordinate.
+        # Corresponds to the JSON property `y`
+        # @return [Float]
+        attr_accessor :y
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @x = args[:x] if args.key?(:x)
+          @y = args[:y] if args.key?(:y)
+        end
+      end
+      
+      # Annotations corresponding to one tracked object.
+      class GoogleCloudVideointelligenceV1p1beta1ObjectTrackingAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # Object category's labeling confidence of this track.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1Entity]
+        attr_accessor :entity
+      
+        # Information corresponding to all frames where this object track appears.
+        # Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame
+        # messages in frames.
+        # Streaming mode: it can only be one ObjectTrackingFrame message in frames.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ObjectTrackingFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment]
+        attr_accessor :segment
+      
+        # Streaming mode ONLY.
+        # In streaming mode, we do not know the end time of a tracked object
+        # before it is completed. Hence, there is no VideoSegment info returned.
+        # Instead, we provide a unique identifiable integer track_id so that
+        # the customers can correlate the results of the ongoing
+        # ObjectTrackAnnotation of the same track_id over time.
+        # Corresponds to the JSON property `trackId`
+        # @return [Fixnum]
+        attr_accessor :track_id
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @entity = args[:entity] if args.key?(:entity)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+          @track_id = args[:track_id] if args.key?(:track_id)
+        end
+      end
+      
+      # Video frame level annotations for object detection and tracking. This field
+      # stores per frame location, time offset, and confidence.
+      class GoogleCloudVideointelligenceV1p1beta1ObjectTrackingFrame
+        include Google::Apis::Core::Hashable
+      
+        # Normalized bounding box.
+        # The normalized vertex coordinates are relative to the original image.
+        # Range: [0, 1].
+        # Corresponds to the JSON property `normalizedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1NormalizedBoundingBox]
+        attr_accessor :normalized_bounding_box
+      
+        # The timestamp of the frame in microseconds.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @normalized_bounding_box = args[:normalized_bounding_box] if args.key?(:normalized_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative
+        include Google::Apis::Core::Hashable
+      
+        # The confidence estimate between 0.0 and 1.0. A higher number
+        # indicates an estimated greater likelihood that the recognized words are
+        # correct. This field is typically provided only for the top hypothesis, and
+        # only for `is_final=true` results. Clients should not rely on the
+        # `confidence` field as it is not guaranteed to be accurate or consistent.
+        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
+      
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1WordInfo>]
+        attr_accessor :words
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
+        end
+      end
+      
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1p1beta1SpeechTranscription
+        include Google::Apis::Core::Hashable
+      
+        # May contain one or more recognition hypotheses (up to the maximum specified
+        # in `max_alternatives`).  These alternatives are ordered in terms of
+        # accuracy, with the top (first) alternative being the most probable, as
+        # ranked by the recognizer.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
+      
+        # Output only. The
+        # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
+        # language in this result. This language code was detected to have the most
+        # likelihood of being spoken in the audio.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
+      # Annotations related to one detected OCR text snippet. This will contain the
+      # corresponding text, confidence value, and frame level information for each
+      # detection.
+      class GoogleCloudVideointelligenceV1p1beta1TextAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # All video segments where OCR detected text appears.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1TextSegment>]
+        attr_accessor :segments
+      
+        # The detected text.
+        # Corresponds to the JSON property `text`
+        # @return [String]
+        attr_accessor :text
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @segments = args[:segments] if args.key?(:segments)
+          @text = args[:text] if args.key?(:text)
+        end
+      end
+      
+      # Video frame level annotation results for text annotation (OCR).
+      # Contains information regarding timestamp and bounding box locations for the
+      # frames containing detected OCR text snippets.
+      class GoogleCloudVideointelligenceV1p1beta1TextFrame
+        include Google::Apis::Core::Hashable
+      
+        # Normalized bounding polygon for text (that might not be aligned with axis).
+        # Contains list of the corner points in clockwise order starting from
+        # top-left corner. For example, for a rectangular bounding box:
+        # When the text is horizontal it might look like:
+        # 0----1
+        # |    |
+        # 3----2
+        # When it's clockwise rotated 180 degrees around the top-left corner it
+        # becomes:
+        # 2----3
+        # |    |
+        # 1----0
+        # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+        # than 0, or greater than 1 due to trignometric calculations for location of
+        # the box.
+        # Corresponds to the JSON property `rotatedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1NormalizedBoundingPoly]
+        attr_accessor :rotated_bounding_box
+      
+        # Timestamp of this frame.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @rotated_bounding_box = args[:rotated_bounding_box] if args.key?(:rotated_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Video segment level annotation results for text detection.
+      class GoogleCloudVideointelligenceV1p1beta1TextSegment
+        include Google::Apis::Core::Hashable
+      
+        # Confidence for the track of detected text. It is calculated as the highest
+        # over all frames where OCR detected text appears.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Information related to the frames where OCR detected text appears.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1TextFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment]
+        attr_accessor :segment
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+        end
+      end
+      
+      # Annotation progress for a single video.
+      class GoogleCloudVideointelligenceV1p1beta1VideoAnnotationProgress
+        include Google::Apis::Core::Hashable
+      
+        # Video file location in
+        # [Google Cloud Storage](https://cloud.google.com/storage/).
+        # Corresponds to the JSON property `inputUri`
+        # @return [String]
+        attr_accessor :input_uri
+      
+        # Approximate percentage processed thus far. Guaranteed to be
+        # 100 when fully processed.
+        # Corresponds to the JSON property `progressPercent`
+        # @return [Fixnum]
+        attr_accessor :progress_percent
+      
+        # Time when the request was received.
+        # Corresponds to the JSON property `startTime`
         # @return [String]
         attr_accessor :start_time
       
@@ -1169,17 +2591,17 @@ module Google
       end
       
       # Annotation results for a single video.
-      class GoogleCloudVideointelligenceV1beta2VideoAnnotationResults
+      class GoogleCloudVideointelligenceV1p1beta1VideoAnnotationResults
         include Google::Apis::Core::Hashable
       
-        # The `Status` type defines a logical error model that is suitable for different
-        # programming environments, including REST APIs and RPC APIs. It is used by
-        # [gRPC](https://github.com/grpc). The error model is designed to be:
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
         # - Simple to use and understand for most users
         # - Flexible enough to meet unexpected needs
         # # Overview
-        # The `Status` message contains three pieces of data: error code, error message,
-        # and error details. The error code should be an enum value of
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
         # google.rpc.Code, but it may accept additional error codes if needed.  The
         # error message should be a developer-facing English message that helps
         # developers *understand* and *resolve* the error. If a localized user-facing
@@ -1219,13 +2641,13 @@ module Google
         # If no explicit content has been detected in a frame, no annotations are
         # present for that frame.
         # Corresponds to the JSON property `explicitAnnotation`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2ExplicitContentAnnotation]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ExplicitContentAnnotation]
         attr_accessor :explicit_annotation
       
         # Label annotations on frame level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `frameLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
         attr_accessor :frame_label_annotations
       
         # Video file location in
@@ -1234,28 +2656,40 @@ module Google
         # @return [String]
         attr_accessor :input_uri
       
+        # Annotations for list of objects detected and tracked in video.
+        # Corresponds to the JSON property `objectAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ObjectTrackingAnnotation>]
+        attr_accessor :object_annotations
+      
         # Label annotations on video level or user specified segment level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `segmentLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
         attr_accessor :segment_label_annotations
       
         # Shot annotations. Each shot is represented as a video segment.
         # Corresponds to the JSON property `shotAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2VideoSegment>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment>]
         attr_accessor :shot_annotations
       
         # Label annotations on shot level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `shotLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
         # Speech transcription.
         # Corresponds to the JSON property `speechTranscriptions`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1beta2SpeechTranscription>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1SpeechTranscription>]
         attr_accessor :speech_transcriptions
       
+        # OCR text detection and tracking.
+        # Annotations for list of detected text snippets. Each will have list of
+        # frame information associated with it.
+        # Corresponds to the JSON property `textAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1TextAnnotation>]
+        attr_accessor :text_annotations
+      
         def initialize(**args)
            update!(**args)
         end
@@ -1266,15 +2700,17 @@ module Google
           @explicit_annotation = args[:explicit_annotation] if args.key?(:explicit_annotation)
           @frame_label_annotations = args[:frame_label_annotations] if args.key?(:frame_label_annotations)
           @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @object_annotations = args[:object_annotations] if args.key?(:object_annotations)
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
           @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
+          @text_annotations = args[:text_annotations] if args.key?(:text_annotations)
         end
       end
       
       # Video segment.
-      class GoogleCloudVideointelligenceV1beta2VideoSegment
+      class GoogleCloudVideointelligenceV1p1beta1VideoSegment
         include Google::Apis::Core::Hashable
       
         # Time-offset, relative to the beginning of the video,
@@ -1303,7 +2739,7 @@ module Google
       # Word-specific information for recognized words. Word information is only
       # included in the response when certain request parameters are set, such
       # as `enable_word_time_offsets`.
-      class GoogleCloudVideointelligenceV1beta2WordInfo
+      class GoogleCloudVideointelligenceV1p1beta1WordInfo
         include Google::Apis::Core::Hashable
       
         # Output only. The confidence estimate between 0.0 and 1.0. A higher number
@@ -1362,13 +2798,241 @@ module Google
       # Video annotation progress. Included in the `metadata`
       # field of the `Operation` returned by the `GetOperation`
       # call of the `google::longrunning::Operations` service.
-      class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoProgress
+      class GoogleCloudVideointelligenceV1p2beta1AnnotateVideoProgress
+        include Google::Apis::Core::Hashable
+      
+        # Progress metadata for all videos specified in `AnnotateVideoRequest`.
+        # Corresponds to the JSON property `annotationProgress`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoAnnotationProgress>]
+        attr_accessor :annotation_progress
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @annotation_progress = args[:annotation_progress] if args.key?(:annotation_progress)
+        end
+      end
+      
+      # Video annotation response. Included in the `response`
+      # field of the `Operation` returned by the `GetOperation`
+      # call of the `google::longrunning::Operations` service.
+      class GoogleCloudVideointelligenceV1p2beta1AnnotateVideoResponse
+        include Google::Apis::Core::Hashable
+      
+        # Annotation results for all videos specified in `AnnotateVideoRequest`.
+        # Corresponds to the JSON property `annotationResults`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoAnnotationResults>]
+        attr_accessor :annotation_results
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @annotation_results = args[:annotation_results] if args.key?(:annotation_results)
+        end
+      end
+      
+      # Detected entity from video analysis.
+      class GoogleCloudVideointelligenceV1p2beta1Entity
+        include Google::Apis::Core::Hashable
+      
+        # Textual description, e.g. `Fixed-gear bicycle`.
+        # Corresponds to the JSON property `description`
+        # @return [String]
+        attr_accessor :description
+      
+        # Opaque entity ID. Some IDs may be available in
+        # [Google Knowledge Graph Search
+        # API](https://developers.google.com/knowledge-graph/).
+        # Corresponds to the JSON property `entityId`
+        # @return [String]
+        attr_accessor :entity_id
+      
+        # Language code for `description` in BCP-47 format.
+        # Corresponds to the JSON property `languageCode`
+        # @return [String]
+        attr_accessor :language_code
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @description = args[:description] if args.key?(:description)
+          @entity_id = args[:entity_id] if args.key?(:entity_id)
+          @language_code = args[:language_code] if args.key?(:language_code)
+        end
+      end
+      
+      # Explicit content annotation (based on per-frame visual signals only).
+      # If no explicit content has been detected in a frame, no annotations are
+      # present for that frame.
+      class GoogleCloudVideointelligenceV1p2beta1ExplicitContentAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # All video frames where explicit content was detected.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ExplicitContentFrame>]
+        attr_accessor :frames
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @frames = args[:frames] if args.key?(:frames)
+        end
+      end
+      
+      # Video frame level annotation results for explicit content.
+      class GoogleCloudVideointelligenceV1p2beta1ExplicitContentFrame
+        include Google::Apis::Core::Hashable
+      
+        # Likelihood of the pornography content..
+        # Corresponds to the JSON property `pornographyLikelihood`
+        # @return [String]
+        attr_accessor :pornography_likelihood
+      
+        # Time-offset, relative to the beginning of the video, corresponding to the
+        # video frame for this location.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @pornography_likelihood = args[:pornography_likelihood] if args.key?(:pornography_likelihood)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Label annotation.
+      class GoogleCloudVideointelligenceV1p2beta1LabelAnnotation
+        include Google::Apis::Core::Hashable
+      
+        # Common categories for the detected entity.
+        # E.g. when the label is `Terrier` the category is likely `dog`. And in some
+        # cases there might be more than one categories e.g. `Terrier` could also be
+        # a `pet`.
+        # Corresponds to the JSON property `categoryEntities`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity>]
+        attr_accessor :category_entities
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity]
+        attr_accessor :entity
+      
+        # All video frames where a label was detected.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelFrame>]
+        attr_accessor :frames
+      
+        # All video segments where a label was detected.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelSegment>]
+        attr_accessor :segments
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @category_entities = args[:category_entities] if args.key?(:category_entities)
+          @entity = args[:entity] if args.key?(:entity)
+          @frames = args[:frames] if args.key?(:frames)
+          @segments = args[:segments] if args.key?(:segments)
+        end
+      end
+      
+      # Video frame level annotation results for label detection.
+      class GoogleCloudVideointelligenceV1p2beta1LabelFrame
+        include Google::Apis::Core::Hashable
+      
+        # Confidence that the label is accurate. Range: [0, 1].
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Time-offset, relative to the beginning of the video, corresponding to the
+        # video frame for this location.
+        # Corresponds to the JSON property `timeOffset`
+        # @return [String]
+        attr_accessor :time_offset
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
+        end
+      end
+      
+      # Video segment level annotation results for label detection.
+      class GoogleCloudVideointelligenceV1p2beta1LabelSegment
+        include Google::Apis::Core::Hashable
+      
+        # Confidence that the label is accurate. Range: [0, 1].
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        attr_accessor :segment
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @segment = args[:segment] if args.key?(:segment)
+        end
+      end
+      
+      # Normalized bounding box.
+      # The normalized vertex coordinates are relative to the original image.
+      # Range: [0, 1].
+      class GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingBox
         include Google::Apis::Core::Hashable
       
-        # Progress metadata for all videos specified in `AnnotateVideoRequest`.
-        # Corresponds to the JSON property `annotationProgress`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoAnnotationProgress>]
-        attr_accessor :annotation_progress
+        # Bottom Y coordinate.
+        # Corresponds to the JSON property `bottom`
+        # @return [Float]
+        attr_accessor :bottom
+      
+        # Left X coordinate.
+        # Corresponds to the JSON property `left`
+        # @return [Float]
+        attr_accessor :left
+      
+        # Right X coordinate.
+        # Corresponds to the JSON property `right`
+        # @return [Float]
+        attr_accessor :right
+      
+        # Top Y coordinate.
+        # Corresponds to the JSON property `top`
+        # @return [Float]
+        attr_accessor :top
       
         def initialize(**args)
            update!(**args)
@@ -1376,20 +3040,35 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @annotation_progress = args[:annotation_progress] if args.key?(:annotation_progress)
+          @bottom = args[:bottom] if args.key?(:bottom)
+          @left = args[:left] if args.key?(:left)
+          @right = args[:right] if args.key?(:right)
+          @top = args[:top] if args.key?(:top)
         end
       end
       
-      # Video annotation response. Included in the `response`
-      # field of the `Operation` returned by the `GetOperation`
-      # call of the `google::longrunning::Operations` service.
-      class GoogleCloudVideointelligenceV1p1beta1AnnotateVideoResponse
+      # Normalized bounding polygon for text (that might not be aligned with axis).
+      # Contains list of the corner points in clockwise order starting from
+      # top-left corner. For example, for a rectangular bounding box:
+      # When the text is horizontal it might look like:
+      # 0----1
+      # |    |
+      # 3----2
+      # When it's clockwise rotated 180 degrees around the top-left corner it
+      # becomes:
+      # 2----3
+      # |    |
+      # 1----0
+      # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+      # than 0, or greater than 1 due to trignometric calculations for location of
+      # the box.
+      class GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingPoly
         include Google::Apis::Core::Hashable
       
-        # Annotation results for all videos specified in `AnnotateVideoRequest`.
-        # Corresponds to the JSON property `annotationResults`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoAnnotationResults>]
-        attr_accessor :annotation_results
+        # Normalized vertices of the bounding polygon.
+        # Corresponds to the JSON property `vertices`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedVertex>]
+        attr_accessor :vertices
       
         def initialize(**args)
            update!(**args)
@@ -1397,30 +3076,25 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @annotation_results = args[:annotation_results] if args.key?(:annotation_results)
+          @vertices = args[:vertices] if args.key?(:vertices)
         end
       end
       
-      # Detected entity from video analysis.
-      class GoogleCloudVideointelligenceV1p1beta1Entity
+      # A vertex represents a 2D point in the image.
+      # NOTE: the normalized vertex coordinates are relative to the original image
+      # and range from 0 to 1.
+      class GoogleCloudVideointelligenceV1p2beta1NormalizedVertex
         include Google::Apis::Core::Hashable
       
-        # Textual description, e.g. `Fixed-gear bicycle`.
-        # Corresponds to the JSON property `description`
-        # @return [String]
-        attr_accessor :description
-      
-        # Opaque entity ID. Some IDs may be available in
-        # [Google Knowledge Graph Search
-        # API](https://developers.google.com/knowledge-graph/).
-        # Corresponds to the JSON property `entityId`
-        # @return [String]
-        attr_accessor :entity_id
+        # X coordinate.
+        # Corresponds to the JSON property `x`
+        # @return [Float]
+        attr_accessor :x
       
-        # Language code for `description` in BCP-47 format.
-        # Corresponds to the JSON property `languageCode`
-        # @return [String]
-        attr_accessor :language_code
+        # Y coordinate.
+        # Corresponds to the JSON property `y`
+        # @return [Float]
+        attr_accessor :y
       
         def initialize(**args)
            update!(**args)
@@ -1428,44 +3102,75 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @description = args[:description] if args.key?(:description)
-          @entity_id = args[:entity_id] if args.key?(:entity_id)
-          @language_code = args[:language_code] if args.key?(:language_code)
+          @x = args[:x] if args.key?(:x)
+          @y = args[:y] if args.key?(:y)
         end
       end
       
-      # Explicit content annotation (based on per-frame visual signals only).
-      # If no explicit content has been detected in a frame, no annotations are
-      # present for that frame.
-      class GoogleCloudVideointelligenceV1p1beta1ExplicitContentAnnotation
+      # Annotations corresponding to one tracked object.
+      class GoogleCloudVideointelligenceV1p2beta1ObjectTrackingAnnotation
         include Google::Apis::Core::Hashable
       
-        # All video frames where explicit content was detected.
+        # Object category's labeling confidence of this track.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
+      
+        # Detected entity from video analysis.
+        # Corresponds to the JSON property `entity`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity]
+        attr_accessor :entity
+      
+        # Information corresponding to all frames where this object track appears.
+        # Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame
+        # messages in frames.
+        # Streaming mode: it can only be one ObjectTrackingFrame message in frames.
         # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ExplicitContentFrame>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ObjectTrackingFrame>]
         attr_accessor :frames
       
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        attr_accessor :segment
+      
+        # Streaming mode ONLY.
+        # In streaming mode, we do not know the end time of a tracked object
+        # before it is completed. Hence, there is no VideoSegment info returned.
+        # Instead, we provide a unique identifiable integer track_id so that
+        # the customers can correlate the results of the ongoing
+        # ObjectTrackAnnotation of the same track_id over time.
+        # Corresponds to the JSON property `trackId`
+        # @return [Fixnum]
+        attr_accessor :track_id
+      
         def initialize(**args)
            update!(**args)
         end
       
         # Update properties of this object
         def update!(**args)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @entity = args[:entity] if args.key?(:entity)
           @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
+          @track_id = args[:track_id] if args.key?(:track_id)
         end
       end
       
-      # Video frame level annotation results for explicit content.
-      class GoogleCloudVideointelligenceV1p1beta1ExplicitContentFrame
+      # Video frame level annotations for object detection and tracking. This field
+      # stores per frame location, time offset, and confidence.
+      class GoogleCloudVideointelligenceV1p2beta1ObjectTrackingFrame
         include Google::Apis::Core::Hashable
       
-        # Likelihood of the pornography content..
-        # Corresponds to the JSON property `pornographyLikelihood`
-        # @return [String]
-        attr_accessor :pornography_likelihood
+        # Normalized bounding box.
+        # The normalized vertex coordinates are relative to the original image.
+        # Range: [0, 1].
+        # Corresponds to the JSON property `normalizedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingBox]
+        attr_accessor :normalized_bounding_box
       
-        # Time-offset, relative to the beginning of the video, corresponding to the
-        # video frame for this location.
+        # The timestamp of the frame in microseconds.
         # Corresponds to the JSON property `timeOffset`
         # @return [String]
         attr_accessor :time_offset
@@ -1476,37 +3181,34 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @pornography_likelihood = args[:pornography_likelihood] if args.key?(:pornography_likelihood)
+          @normalized_bounding_box = args[:normalized_bounding_box] if args.key?(:normalized_bounding_box)
           @time_offset = args[:time_offset] if args.key?(:time_offset)
         end
       end
       
-      # Label annotation.
-      class GoogleCloudVideointelligenceV1p1beta1LabelAnnotation
+      # Alternative hypotheses (a.k.a. n-best list).
+      class GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative
         include Google::Apis::Core::Hashable
       
-        # Common categories for the detected entity.
-        # E.g. when the label is `Terrier` the category is likely `dog`. And in some
-        # cases there might be more than one categories e.g. `Terrier` could also be
-        # a `pet`.
-        # Corresponds to the JSON property `categoryEntities`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1Entity>]
-        attr_accessor :category_entities
-      
-        # Detected entity from video analysis.
-        # Corresponds to the JSON property `entity`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1Entity]
-        attr_accessor :entity
+        # The confidence estimate between 0.0 and 1.0. A higher number
+        # indicates an estimated greater likelihood that the recognized words are
+        # correct. This field is typically provided only for the top hypothesis, and
+        # only for `is_final=true` results. Clients should not rely on the
+        # `confidence` field as it is not guaranteed to be accurate or consistent.
+        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
       
-        # All video frames where a label was detected.
-        # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelFrame>]
-        attr_accessor :frames
+        # Transcript text representing the words that the user spoke.
+        # Corresponds to the JSON property `transcript`
+        # @return [String]
+        attr_accessor :transcript
       
-        # All video segments where a label was detected.
-        # Corresponds to the JSON property `segments`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelSegment>]
-        attr_accessor :segments
+        # A list of word-specific information for each recognized word.
+        # Corresponds to the JSON property `words`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1WordInfo>]
+        attr_accessor :words
       
         def initialize(**args)
            update!(**args)
@@ -1514,27 +3216,31 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @category_entities = args[:category_entities] if args.key?(:category_entities)
-          @entity = args[:entity] if args.key?(:entity)
-          @frames = args[:frames] if args.key?(:frames)
-          @segments = args[:segments] if args.key?(:segments)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @transcript = args[:transcript] if args.key?(:transcript)
+          @words = args[:words] if args.key?(:words)
         end
       end
       
-      # Video frame level annotation results for label detection.
-      class GoogleCloudVideointelligenceV1p1beta1LabelFrame
+      # A speech recognition result corresponding to a portion of the audio.
+      class GoogleCloudVideointelligenceV1p2beta1SpeechTranscription
         include Google::Apis::Core::Hashable
       
-        # Confidence that the label is accurate. Range: [0, 1].
-        # Corresponds to the JSON property `confidence`
-        # @return [Float]
-        attr_accessor :confidence
+        # May contain one or more recognition hypotheses (up to the maximum specified
+        # in `max_alternatives`).  These alternatives are ordered in terms of
+        # accuracy, with the top (first) alternative being the most probable, as
+        # ranked by the recognizer.
+        # Corresponds to the JSON property `alternatives`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative>]
+        attr_accessor :alternatives
       
-        # Time-offset, relative to the beginning of the video, corresponding to the
-        # video frame for this location.
-        # Corresponds to the JSON property `timeOffset`
+        # Output only. The
+        # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
+        # language in this result. This language code was detected to have the most
+        # likelihood of being spoken in the audio.
+        # Corresponds to the JSON property `languageCode`
         # @return [String]
-        attr_accessor :time_offset
+        attr_accessor :language_code
       
         def initialize(**args)
            update!(**args)
@@ -1542,24 +3248,26 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @confidence = args[:confidence] if args.key?(:confidence)
-          @time_offset = args[:time_offset] if args.key?(:time_offset)
+          @alternatives = args[:alternatives] if args.key?(:alternatives)
+          @language_code = args[:language_code] if args.key?(:language_code)
         end
       end
       
-      # Video segment level annotation results for label detection.
-      class GoogleCloudVideointelligenceV1p1beta1LabelSegment
+      # Annotations related to one detected OCR text snippet. This will contain the
+      # corresponding text, confidence value, and frame level information for each
+      # detection.
+      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
         include Google::Apis::Core::Hashable
       
-        # Confidence that the label is accurate. Range: [0, 1].
-        # Corresponds to the JSON property `confidence`
-        # @return [Float]
-        attr_accessor :confidence
+        # All video segments where OCR detected text appears.
+        # Corresponds to the JSON property `segments`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextSegment>]
+        attr_accessor :segments
       
-        # Video segment.
-        # Corresponds to the JSON property `segment`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment]
-        attr_accessor :segment
+        # The detected text.
+        # Corresponds to the JSON property `text`
+        # @return [String]
+        attr_accessor :text
       
         def initialize(**args)
            update!(**args)
@@ -1567,34 +3275,40 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @confidence = args[:confidence] if args.key?(:confidence)
-          @segment = args[:segment] if args.key?(:segment)
+          @segments = args[:segments] if args.key?(:segments)
+          @text = args[:text] if args.key?(:text)
         end
       end
       
-      # Alternative hypotheses (a.k.a. n-best list).
-      class GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative
+      # Video frame level annotation results for text annotation (OCR).
+      # Contains information regarding timestamp and bounding box locations for the
+      # frames containing detected OCR text snippets.
+      class GoogleCloudVideointelligenceV1p2beta1TextFrame
         include Google::Apis::Core::Hashable
       
-        # The confidence estimate between 0.0 and 1.0. A higher number
-        # indicates an estimated greater likelihood that the recognized words are
-        # correct. This field is typically provided only for the top hypothesis, and
-        # only for `is_final=true` results. Clients should not rely on the
-        # `confidence` field as it is not guaranteed to be accurate or consistent.
-        # The default of 0.0 is a sentinel value indicating `confidence` was not set.
-        # Corresponds to the JSON property `confidence`
-        # @return [Float]
-        attr_accessor :confidence
+        # Normalized bounding polygon for text (that might not be aligned with axis).
+        # Contains list of the corner points in clockwise order starting from
+        # top-left corner. For example, for a rectangular bounding box:
+        # When the text is horizontal it might look like:
+        # 0----1
+        # |    |
+        # 3----2
+        # When it's clockwise rotated 180 degrees around the top-left corner it
+        # becomes:
+        # 2----3
+        # |    |
+        # 1----0
+        # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
+        # than 0, or greater than 1 due to trignometric calculations for location of
+        # the box.
+        # Corresponds to the JSON property `rotatedBoundingBox`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingPoly]
+        attr_accessor :rotated_bounding_box
       
-        # Transcript text representing the words that the user spoke.
-        # Corresponds to the JSON property `transcript`
+        # Timestamp of this frame.
+        # Corresponds to the JSON property `timeOffset`
         # @return [String]
-        attr_accessor :transcript
-      
-        # A list of word-specific information for each recognized word.
-        # Corresponds to the JSON property `words`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1WordInfo>]
-        attr_accessor :words
+        attr_accessor :time_offset
       
         def initialize(**args)
            update!(**args)
@@ -1602,31 +3316,30 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @confidence = args[:confidence] if args.key?(:confidence)
-          @transcript = args[:transcript] if args.key?(:transcript)
-          @words = args[:words] if args.key?(:words)
+          @rotated_bounding_box = args[:rotated_bounding_box] if args.key?(:rotated_bounding_box)
+          @time_offset = args[:time_offset] if args.key?(:time_offset)
         end
       end
       
-      # A speech recognition result corresponding to a portion of the audio.
-      class GoogleCloudVideointelligenceV1p1beta1SpeechTranscription
+      # Video segment level annotation results for text detection.
+      class GoogleCloudVideointelligenceV1p2beta1TextSegment
         include Google::Apis::Core::Hashable
       
-        # May contain one or more recognition hypotheses (up to the maximum specified
-        # in `max_alternatives`).  These alternatives are ordered in terms of
-        # accuracy, with the top (first) alternative being the most probable, as
-        # ranked by the recognizer.
-        # Corresponds to the JSON property `alternatives`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1SpeechRecognitionAlternative>]
-        attr_accessor :alternatives
+        # Confidence for the track of detected text. It is calculated as the highest
+        # over all frames where OCR detected text appears.
+        # Corresponds to the JSON property `confidence`
+        # @return [Float]
+        attr_accessor :confidence
       
-        # Output only. The
-        # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the
-        # language in this result. This language code was detected to have the most
-        # likelihood of being spoken in the audio.
-        # Corresponds to the JSON property `languageCode`
-        # @return [String]
-        attr_accessor :language_code
+        # Information related to the frames where OCR detected text appears.
+        # Corresponds to the JSON property `frames`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextFrame>]
+        attr_accessor :frames
+      
+        # Video segment.
+        # Corresponds to the JSON property `segment`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        attr_accessor :segment
       
         def initialize(**args)
            update!(**args)
@@ -1634,13 +3347,14 @@ module Google
       
         # Update properties of this object
         def update!(**args)
-          @alternatives = args[:alternatives] if args.key?(:alternatives)
-          @language_code = args[:language_code] if args.key?(:language_code)
+          @confidence = args[:confidence] if args.key?(:confidence)
+          @frames = args[:frames] if args.key?(:frames)
+          @segment = args[:segment] if args.key?(:segment)
         end
       end
       
       # Annotation progress for a single video.
-      class GoogleCloudVideointelligenceV1p1beta1VideoAnnotationProgress
+      class GoogleCloudVideointelligenceV1p2beta1VideoAnnotationProgress
         include Google::Apis::Core::Hashable
       
         # Video file location in
@@ -1679,17 +3393,17 @@ module Google
       end
       
       # Annotation results for a single video.
-      class GoogleCloudVideointelligenceV1p1beta1VideoAnnotationResults
+      class GoogleCloudVideointelligenceV1p2beta1VideoAnnotationResults
         include Google::Apis::Core::Hashable
       
-        # The `Status` type defines a logical error model that is suitable for different
-        # programming environments, including REST APIs and RPC APIs. It is used by
-        # [gRPC](https://github.com/grpc). The error model is designed to be:
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
         # - Simple to use and understand for most users
         # - Flexible enough to meet unexpected needs
         # # Overview
-        # The `Status` message contains three pieces of data: error code, error message,
-        # and error details. The error code should be an enum value of
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
         # google.rpc.Code, but it may accept additional error codes if needed.  The
         # error message should be a developer-facing English message that helps
         # developers *understand* and *resolve* the error. If a localized user-facing
@@ -1729,13 +3443,13 @@ module Google
         # If no explicit content has been detected in a frame, no annotations are
         # present for that frame.
         # Corresponds to the JSON property `explicitAnnotation`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1ExplicitContentAnnotation]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ExplicitContentAnnotation]
         attr_accessor :explicit_annotation
       
         # Label annotations on frame level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `frameLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
         attr_accessor :frame_label_annotations
       
         # Video file location in
@@ -1744,28 +3458,40 @@ module Google
         # @return [String]
         attr_accessor :input_uri
       
+        # Annotations for list of objects detected and tracked in video.
+        # Corresponds to the JSON property `objectAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ObjectTrackingAnnotation>]
+        attr_accessor :object_annotations
+      
         # Label annotations on video level or user specified segment level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `segmentLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
         attr_accessor :segment_label_annotations
       
         # Shot annotations. Each shot is represented as a video segment.
         # Corresponds to the JSON property `shotAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1VideoSegment>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment>]
         attr_accessor :shot_annotations
       
         # Label annotations on shot level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `shotLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
         # Speech transcription.
         # Corresponds to the JSON property `speechTranscriptions`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p1beta1SpeechTranscription>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1SpeechTranscription>]
         attr_accessor :speech_transcriptions
       
+        # OCR text detection and tracking.
+        # Annotations for list of detected text snippets. Each will have list of
+        # frame information associated with it.
+        # Corresponds to the JSON property `textAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextAnnotation>]
+        attr_accessor :text_annotations
+      
         def initialize(**args)
            update!(**args)
         end
@@ -1776,15 +3502,17 @@ module Google
           @explicit_annotation = args[:explicit_annotation] if args.key?(:explicit_annotation)
           @frame_label_annotations = args[:frame_label_annotations] if args.key?(:frame_label_annotations)
           @input_uri = args[:input_uri] if args.key?(:input_uri)
+          @object_annotations = args[:object_annotations] if args.key?(:object_annotations)
           @segment_label_annotations = args[:segment_label_annotations] if args.key?(:segment_label_annotations)
           @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
           @shot_label_annotations = args[:shot_label_annotations] if args.key?(:shot_label_annotations)
           @speech_transcriptions = args[:speech_transcriptions] if args.key?(:speech_transcriptions)
+          @text_annotations = args[:text_annotations] if args.key?(:text_annotations)
         end
       end
       
       # Video segment.
-      class GoogleCloudVideointelligenceV1p1beta1VideoSegment
+      class GoogleCloudVideointelligenceV1p2beta1VideoSegment
         include Google::Apis::Core::Hashable
       
         # Time-offset, relative to the beginning of the video,
@@ -1813,7 +3541,7 @@ module Google
       # Word-specific information for recognized words. Word information is only
       # included in the response when certain request parameters are set, such
       # as `enable_word_time_offsets`.
-      class GoogleCloudVideointelligenceV1p1beta1WordInfo
+      class GoogleCloudVideointelligenceV1p2beta1WordInfo
         include Google::Apis::Core::Hashable
       
         # Output only. The confidence estimate between 0.0 and 1.0. A higher number
@@ -1872,12 +3600,12 @@ module Google
       # Video annotation progress. Included in the `metadata`
       # field of the `Operation` returned by the `GetOperation`
       # call of the `google::longrunning::Operations` service.
-      class GoogleCloudVideointelligenceV1p2beta1AnnotateVideoProgress
+      class GoogleCloudVideointelligenceV1p3beta1AnnotateVideoProgress
         include Google::Apis::Core::Hashable
       
         # Progress metadata for all videos specified in `AnnotateVideoRequest`.
         # Corresponds to the JSON property `annotationProgress`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoAnnotationProgress>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoAnnotationProgress>]
         attr_accessor :annotation_progress
       
         def initialize(**args)
@@ -1893,12 +3621,12 @@ module Google
       # Video annotation response. Included in the `response`
       # field of the `Operation` returned by the `GetOperation`
       # call of the `google::longrunning::Operations` service.
-      class GoogleCloudVideointelligenceV1p2beta1AnnotateVideoResponse
+      class GoogleCloudVideointelligenceV1p3beta1AnnotateVideoResponse
         include Google::Apis::Core::Hashable
       
         # Annotation results for all videos specified in `AnnotateVideoRequest`.
         # Corresponds to the JSON property `annotationResults`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoAnnotationResults>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoAnnotationResults>]
         attr_accessor :annotation_results
       
         def initialize(**args)
@@ -1912,7 +3640,7 @@ module Google
       end
       
       # Detected entity from video analysis.
-      class GoogleCloudVideointelligenceV1p2beta1Entity
+      class GoogleCloudVideointelligenceV1p3beta1Entity
         include Google::Apis::Core::Hashable
       
         # Textual description, e.g. `Fixed-gear bicycle`.
@@ -1947,12 +3675,12 @@ module Google
       # Explicit content annotation (based on per-frame visual signals only).
       # If no explicit content has been detected in a frame, no annotations are
       # present for that frame.
-      class GoogleCloudVideointelligenceV1p2beta1ExplicitContentAnnotation
+      class GoogleCloudVideointelligenceV1p3beta1ExplicitContentAnnotation
         include Google::Apis::Core::Hashable
       
         # All video frames where explicit content was detected.
         # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ExplicitContentFrame>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ExplicitContentFrame>]
         attr_accessor :frames
       
         def initialize(**args)
@@ -1966,7 +3694,7 @@ module Google
       end
       
       # Video frame level annotation results for explicit content.
-      class GoogleCloudVideointelligenceV1p2beta1ExplicitContentFrame
+      class GoogleCloudVideointelligenceV1p3beta1ExplicitContentFrame
         include Google::Apis::Core::Hashable
       
         # Likelihood of the pornography content..
@@ -1992,7 +3720,7 @@ module Google
       end
       
       # Label annotation.
-      class GoogleCloudVideointelligenceV1p2beta1LabelAnnotation
+      class GoogleCloudVideointelligenceV1p3beta1LabelAnnotation
         include Google::Apis::Core::Hashable
       
         # Common categories for the detected entity.
@@ -2000,22 +3728,22 @@ module Google
         # cases there might be more than one categories e.g. `Terrier` could also be
         # a `pet`.
         # Corresponds to the JSON property `categoryEntities`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1Entity>]
         attr_accessor :category_entities
       
         # Detected entity from video analysis.
         # Corresponds to the JSON property `entity`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1Entity]
         attr_accessor :entity
       
         # All video frames where a label was detected.
         # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelFrame>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelFrame>]
         attr_accessor :frames
       
         # All video segments where a label was detected.
         # Corresponds to the JSON property `segments`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelSegment>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelSegment>]
         attr_accessor :segments
       
         def initialize(**args)
@@ -2032,7 +3760,7 @@ module Google
       end
       
       # Video frame level annotation results for label detection.
-      class GoogleCloudVideointelligenceV1p2beta1LabelFrame
+      class GoogleCloudVideointelligenceV1p3beta1LabelFrame
         include Google::Apis::Core::Hashable
       
         # Confidence that the label is accurate. Range: [0, 1].
@@ -2058,7 +3786,7 @@ module Google
       end
       
       # Video segment level annotation results for label detection.
-      class GoogleCloudVideointelligenceV1p2beta1LabelSegment
+      class GoogleCloudVideointelligenceV1p3beta1LabelSegment
         include Google::Apis::Core::Hashable
       
         # Confidence that the label is accurate. Range: [0, 1].
@@ -2068,7 +3796,7 @@ module Google
       
         # Video segment.
         # Corresponds to the JSON property `segment`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoSegment]
         attr_accessor :segment
       
         def initialize(**args)
@@ -2085,7 +3813,7 @@ module Google
       # Normalized bounding box.
       # The normalized vertex coordinates are relative to the original image.
       # Range: [0, 1].
-      class GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingBox
+      class GoogleCloudVideointelligenceV1p3beta1NormalizedBoundingBox
         include Google::Apis::Core::Hashable
       
         # Bottom Y coordinate.
@@ -2136,12 +3864,12 @@ module Google
       # and the vertex order will still be (0, 1, 2, 3). Note that values can be less
       # than 0, or greater than 1 due to trignometric calculations for location of
       # the box.
-      class GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingPoly
+      class GoogleCloudVideointelligenceV1p3beta1NormalizedBoundingPoly
         include Google::Apis::Core::Hashable
       
         # Normalized vertices of the bounding polygon.
         # Corresponds to the JSON property `vertices`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedVertex>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1NormalizedVertex>]
         attr_accessor :vertices
       
         def initialize(**args)
@@ -2157,7 +3885,7 @@ module Google
       # A vertex represents a 2D point in the image.
       # NOTE: the normalized vertex coordinates are relative to the original image
       # and range from 0 to 1.
-      class GoogleCloudVideointelligenceV1p2beta1NormalizedVertex
+      class GoogleCloudVideointelligenceV1p3beta1NormalizedVertex
         include Google::Apis::Core::Hashable
       
         # X coordinate.
@@ -2182,7 +3910,7 @@ module Google
       end
       
       # Annotations corresponding to one tracked object.
-      class GoogleCloudVideointelligenceV1p2beta1ObjectTrackingAnnotation
+      class GoogleCloudVideointelligenceV1p3beta1ObjectTrackingAnnotation
         include Google::Apis::Core::Hashable
       
         # Object category's labeling confidence of this track.
@@ -2192,7 +3920,7 @@ module Google
       
         # Detected entity from video analysis.
         # Corresponds to the JSON property `entity`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1Entity]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1Entity]
         attr_accessor :entity
       
         # Information corresponding to all frames where this object track appears.
@@ -2200,12 +3928,12 @@ module Google
         # messages in frames.
         # Streaming mode: it can only be one ObjectTrackingFrame message in frames.
         # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ObjectTrackingFrame>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ObjectTrackingFrame>]
         attr_accessor :frames
       
         # Video segment.
         # Corresponds to the JSON property `segment`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoSegment]
         attr_accessor :segment
       
         # Streaming mode ONLY.
@@ -2234,14 +3962,14 @@ module Google
       
       # Video frame level annotations for object detection and tracking. This field
       # stores per frame location, time offset, and confidence.
-      class GoogleCloudVideointelligenceV1p2beta1ObjectTrackingFrame
+      class GoogleCloudVideointelligenceV1p3beta1ObjectTrackingFrame
         include Google::Apis::Core::Hashable
       
         # Normalized bounding box.
         # The normalized vertex coordinates are relative to the original image.
         # Range: [0, 1].
         # Corresponds to the JSON property `normalizedBoundingBox`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingBox]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1NormalizedBoundingBox]
         attr_accessor :normalized_bounding_box
       
         # The timestamp of the frame in microseconds.
@@ -2261,7 +3989,7 @@ module Google
       end
       
       # Alternative hypotheses (a.k.a. n-best list).
-      class GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative
+      class GoogleCloudVideointelligenceV1p3beta1SpeechRecognitionAlternative
         include Google::Apis::Core::Hashable
       
         # The confidence estimate between 0.0 and 1.0. A higher number
@@ -2281,7 +4009,7 @@ module Google
       
         # A list of word-specific information for each recognized word.
         # Corresponds to the JSON property `words`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1WordInfo>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1WordInfo>]
         attr_accessor :words
       
         def initialize(**args)
@@ -2297,7 +4025,7 @@ module Google
       end
       
       # A speech recognition result corresponding to a portion of the audio.
-      class GoogleCloudVideointelligenceV1p2beta1SpeechTranscription
+      class GoogleCloudVideointelligenceV1p3beta1SpeechTranscription
         include Google::Apis::Core::Hashable
       
         # May contain one or more recognition hypotheses (up to the maximum specified
@@ -2305,7 +4033,7 @@ module Google
         # accuracy, with the top (first) alternative being the most probable, as
         # ranked by the recognizer.
         # Corresponds to the JSON property `alternatives`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1SpeechRecognitionAlternative>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1SpeechRecognitionAlternative>]
         attr_accessor :alternatives
       
         # Output only. The
@@ -2327,15 +4055,130 @@ module Google
         end
       end
       
+      # `StreamingAnnotateVideoResponse` is the only message returned to the client
+      # by `StreamingAnnotateVideo`. A series of zero or more
+      # `StreamingAnnotateVideoResponse` messages are streamed back to the client.
+      class GoogleCloudVideointelligenceV1p3beta1StreamingAnnotateVideoResponse
+        include Google::Apis::Core::Hashable
+      
+        # Streaming annotation results corresponding to a portion of the video
+        # that is currently being processed.
+        # Corresponds to the JSON property `annotationResults`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1StreamingVideoAnnotationResults]
+        attr_accessor :annotation_results
+      
+        # GCS URI that stores annotation results of one streaming session.
+        # It is a directory that can hold multiple files in JSON format.
+        # Example uri format:
+        # gs://bucket_id/object_id/cloud_project_name-session_id
+        # Corresponds to the JSON property `annotationResultsUri`
+        # @return [String]
+        attr_accessor :annotation_results_uri
+      
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
+        # - Simple to use and understand for most users
+        # - Flexible enough to meet unexpected needs
+        # # Overview
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
+        # google.rpc.Code, but it may accept additional error codes if needed.  The
+        # error message should be a developer-facing English message that helps
+        # developers *understand* and *resolve* the error. If a localized user-facing
+        # error message is needed, put the localized message in the error details or
+        # localize it in the client. The optional error details may contain arbitrary
+        # information about the error. There is a predefined set of error detail types
+        # in the package `google.rpc` that can be used for common error conditions.
+        # # Language mapping
+        # The `Status` message is the logical representation of the error model, but it
+        # is not necessarily the actual wire format. When the `Status` message is
+        # exposed in different client libraries and different wire protocols, it can be
+        # mapped differently. For example, it will likely be mapped to some exceptions
+        # in Java, but more likely mapped to some error codes in C.
+        # # Other uses
+        # The error model and the `Status` message can be used in a variety of
+        # environments, either with or without APIs, to provide a
+        # consistent developer experience across different environments.
+        # Example uses of this error model include:
+        # - Partial errors. If a service needs to return partial errors to the client,
+        # it may embed the `Status` in the normal response to indicate the partial
+        # errors.
+        # - Workflow errors. A typical workflow has multiple steps. Each step may
+        # have a `Status` message for error reporting.
+        # - Batch operations. If a client uses batch request and batch response, the
+        # `Status` message should be used directly inside batch response, one for
+        # each error sub-response.
+        # - Asynchronous operations. If an API call embeds asynchronous operation
+        # results in its response, the status of those operations should be
+        # represented directly using the `Status` message.
+        # - Logging. If some API errors are stored in logs, the message `Status` could
+        # be used directly after any stripping needed for security/privacy reasons.
+        # Corresponds to the JSON property `error`
+        # @return [Google::Apis::VideointelligenceV1::GoogleRpcStatus]
+        attr_accessor :error
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @annotation_results = args[:annotation_results] if args.key?(:annotation_results)
+          @annotation_results_uri = args[:annotation_results_uri] if args.key?(:annotation_results_uri)
+          @error = args[:error] if args.key?(:error)
+        end
+      end
+      
+      # Streaming annotation results corresponding to a portion of the video
+      # that is currently being processed.
+      class GoogleCloudVideointelligenceV1p3beta1StreamingVideoAnnotationResults
+        include Google::Apis::Core::Hashable
+      
+        # Explicit content annotation (based on per-frame visual signals only).
+        # If no explicit content has been detected in a frame, no annotations are
+        # present for that frame.
+        # Corresponds to the JSON property `explicitAnnotation`
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ExplicitContentAnnotation]
+        attr_accessor :explicit_annotation
+      
+        # Label annotation results.
+        # Corresponds to the JSON property `labelAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelAnnotation>]
+        attr_accessor :label_annotations
+      
+        # Object tracking results.
+        # Corresponds to the JSON property `objectAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ObjectTrackingAnnotation>]
+        attr_accessor :object_annotations
+      
+        # Shot annotation results. Each shot is represented as a video segment.
+        # Corresponds to the JSON property `shotAnnotations`
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoSegment>]
+        attr_accessor :shot_annotations
+      
+        def initialize(**args)
+           update!(**args)
+        end
+      
+        # Update properties of this object
+        def update!(**args)
+          @explicit_annotation = args[:explicit_annotation] if args.key?(:explicit_annotation)
+          @label_annotations = args[:label_annotations] if args.key?(:label_annotations)
+          @object_annotations = args[:object_annotations] if args.key?(:object_annotations)
+          @shot_annotations = args[:shot_annotations] if args.key?(:shot_annotations)
+        end
+      end
+      
       # Annotations related to one detected OCR text snippet. This will contain the
       # corresponding text, confidence value, and frame level information for each
       # detection.
-      class GoogleCloudVideointelligenceV1p2beta1TextAnnotation
+      class GoogleCloudVideointelligenceV1p3beta1TextAnnotation
         include Google::Apis::Core::Hashable
       
         # All video segments where OCR detected text appears.
         # Corresponds to the JSON property `segments`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextSegment>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1TextSegment>]
         attr_accessor :segments
       
         # The detected text.
@@ -2357,7 +4200,7 @@ module Google
       # Video frame level annotation results for text annotation (OCR).
       # Contains information regarding timestamp and bounding box locations for the
       # frames containing detected OCR text snippets.
-      class GoogleCloudVideointelligenceV1p2beta1TextFrame
+      class GoogleCloudVideointelligenceV1p3beta1TextFrame
         include Google::Apis::Core::Hashable
       
         # Normalized bounding polygon for text (that might not be aligned with axis).
@@ -2376,7 +4219,7 @@ module Google
         # than 0, or greater than 1 due to trignometric calculations for location of
         # the box.
         # Corresponds to the JSON property `rotatedBoundingBox`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1NormalizedBoundingPoly]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1NormalizedBoundingPoly]
         attr_accessor :rotated_bounding_box
       
         # Timestamp of this frame.
@@ -2396,7 +4239,7 @@ module Google
       end
       
       # Video segment level annotation results for text detection.
-      class GoogleCloudVideointelligenceV1p2beta1TextSegment
+      class GoogleCloudVideointelligenceV1p3beta1TextSegment
         include Google::Apis::Core::Hashable
       
         # Confidence for the track of detected text. It is calculated as the highest
@@ -2407,12 +4250,12 @@ module Google
       
         # Information related to the frames where OCR detected text appears.
         # Corresponds to the JSON property `frames`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextFrame>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1TextFrame>]
         attr_accessor :frames
       
         # Video segment.
         # Corresponds to the JSON property `segment`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoSegment]
         attr_accessor :segment
       
         def initialize(**args)
@@ -2428,7 +4271,7 @@ module Google
       end
       
       # Annotation progress for a single video.
-      class GoogleCloudVideointelligenceV1p2beta1VideoAnnotationProgress
+      class GoogleCloudVideointelligenceV1p3beta1VideoAnnotationProgress
         include Google::Apis::Core::Hashable
       
         # Video file location in
@@ -2467,17 +4310,17 @@ module Google
       end
       
       # Annotation results for a single video.
-      class GoogleCloudVideointelligenceV1p2beta1VideoAnnotationResults
+      class GoogleCloudVideointelligenceV1p3beta1VideoAnnotationResults
         include Google::Apis::Core::Hashable
       
-        # The `Status` type defines a logical error model that is suitable for different
-        # programming environments, including REST APIs and RPC APIs. It is used by
-        # [gRPC](https://github.com/grpc). The error model is designed to be:
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
         # - Simple to use and understand for most users
         # - Flexible enough to meet unexpected needs
         # # Overview
-        # The `Status` message contains three pieces of data: error code, error message,
-        # and error details. The error code should be an enum value of
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
         # google.rpc.Code, but it may accept additional error codes if needed.  The
         # error message should be a developer-facing English message that helps
         # developers *understand* and *resolve* the error. If a localized user-facing
@@ -2517,13 +4360,13 @@ module Google
         # If no explicit content has been detected in a frame, no annotations are
         # present for that frame.
         # Corresponds to the JSON property `explicitAnnotation`
-        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ExplicitContentAnnotation]
+        # @return [Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ExplicitContentAnnotation]
         attr_accessor :explicit_annotation
       
         # Label annotations on frame level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `frameLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelAnnotation>]
         attr_accessor :frame_label_annotations
       
         # Video file location in
@@ -2534,36 +4377,36 @@ module Google
       
         # Annotations for list of objects detected and tracked in video.
         # Corresponds to the JSON property `objectAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1ObjectTrackingAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1ObjectTrackingAnnotation>]
         attr_accessor :object_annotations
       
         # Label annotations on video level or user specified segment level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `segmentLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelAnnotation>]
         attr_accessor :segment_label_annotations
       
         # Shot annotations. Each shot is represented as a video segment.
         # Corresponds to the JSON property `shotAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1VideoSegment>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1VideoSegment>]
         attr_accessor :shot_annotations
       
         # Label annotations on shot level.
         # There is exactly one element for each unique label.
         # Corresponds to the JSON property `shotLabelAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1LabelAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1LabelAnnotation>]
         attr_accessor :shot_label_annotations
       
         # Speech transcription.
         # Corresponds to the JSON property `speechTranscriptions`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1SpeechTranscription>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1SpeechTranscription>]
         attr_accessor :speech_transcriptions
       
         # OCR text detection and tracking.
         # Annotations for list of detected text snippets. Each will have list of
         # frame information associated with it.
         # Corresponds to the JSON property `textAnnotations`
-        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p2beta1TextAnnotation>]
+        # @return [Array<Google::Apis::VideointelligenceV1::GoogleCloudVideointelligenceV1p3beta1TextAnnotation>]
         attr_accessor :text_annotations
       
         def initialize(**args)
@@ -2586,7 +4429,7 @@ module Google
       end
       
       # Video segment.
-      class GoogleCloudVideointelligenceV1p2beta1VideoSegment
+      class GoogleCloudVideointelligenceV1p3beta1VideoSegment
         include Google::Apis::Core::Hashable
       
         # Time-offset, relative to the beginning of the video,
@@ -2615,7 +4458,7 @@ module Google
       # Word-specific information for recognized words. Word information is only
       # included in the response when certain request parameters are set, such
       # as `enable_word_time_offsets`.
-      class GoogleCloudVideointelligenceV1p2beta1WordInfo
+      class GoogleCloudVideointelligenceV1p3beta1WordInfo
         include Google::Apis::Core::Hashable
       
         # Output only. The confidence estimate between 0.0 and 1.0. A higher number
@@ -2722,14 +4565,14 @@ module Google
         attr_accessor :done
         alias_method :done?, :done
       
-        # The `Status` type defines a logical error model that is suitable for different
-        # programming environments, including REST APIs and RPC APIs. It is used by
-        # [gRPC](https://github.com/grpc). The error model is designed to be:
+        # The `Status` type defines a logical error model that is suitable for
+        # different programming environments, including REST APIs and RPC APIs. It is
+        # used by [gRPC](https://github.com/grpc). The error model is designed to be:
         # - Simple to use and understand for most users
         # - Flexible enough to meet unexpected needs
         # # Overview
-        # The `Status` message contains three pieces of data: error code, error message,
-        # and error details. The error code should be an enum value of
+        # The `Status` message contains three pieces of data: error code, error
+        # message, and error details. The error code should be an enum value of
         # google.rpc.Code, but it may accept additional error codes if needed.  The
         # error message should be a developer-facing English message that helps
         # developers *understand* and *resolve* the error. If a localized user-facing
@@ -2825,14 +4668,14 @@ module Google
         end
       end
       
-      # The `Status` type defines a logical error model that is suitable for different
-      # programming environments, including REST APIs and RPC APIs. It is used by
-      # [gRPC](https://github.com/grpc). The error model is designed to be:
+      # The `Status` type defines a logical error model that is suitable for
+      # different programming environments, including REST APIs and RPC APIs. It is
+      # used by [gRPC](https://github.com/grpc). The error model is designed to be:
       # - Simple to use and understand for most users
       # - Flexible enough to meet unexpected needs
       # # Overview
-      # The `Status` message contains three pieces of data: error code, error message,
-      # and error details. The error code should be an enum value of
+      # The `Status` message contains three pieces of data: error code, error
+      # message, and error details. The error code should be an enum value of
       # google.rpc.Code, but it may accept additional error codes if needed.  The
       # error message should be a developer-facing English message that helps
       # developers *understand* and *resolve* the error. If a localized user-facing