AWS bedrock documentation change
Summary
Updated video analysis documentation: changed 'Scene Summaries' to 'Chapter Summaries', added 'Logo Detection' section, updated content moderation description, and added note about audio stream processing
Security assessment
The changes are feature updates and terminology changes without any indication of addressing security vulnerabilities or adding security features
Diff
diff --git a/bedrock/latest/userguide/bda-ouput-video.md index a10e84421..4f39d73d2 100644 --- a/bedrock/latest/userguide/bda-ouput-video.md +++ b/bedrock/latest/userguide/bda-ouput-video.md @@ -5 +5 @@ -Full Video SummaryScene SummariesIAB TaxonomyFull Audio TranscriptText in VideoContent ModerationVideo Standard Output +Full Video SummaryChapter SummariesIAB TaxonomyFull Audio TranscriptText in VideoLogo DetectionContent ModerationVideo Standard Output @@ -15 +15 @@ Full video summary generates an overall summary of the entire video. It distills -## Scene Summaries +## Chapter Summaries @@ -17 +17 @@ Full video summary generates an overall summary of the entire video. It distills -Video scene summarization provides descriptive summaries for individual scenes within a video. A video scene is a sequence of shots that form a coherent unit of action or narrative within the video. This feature breaks down the video into meaningful segments based on visual and audible cues, provides timestamps for those segments, and summarizes each. BDA will attempt to provide a name for each unique speaker based on audio signals (e.g., the speaker introduces themself) or visual signals (e.g., a presentation slide shows a speaker’s name) in the full video summaries and the scene summaries. +Video chapter summarization provides descriptive summaries for individual scenes within a video. A video chapter is a sequence of shots that form a coherent unit of action or narrative within the video. This feature breaks down the video into meaningful segments based on visual and audible cues, provides timestamps for those segments, and summarizes each. @@ -30,0 +31,4 @@ This feature detects and extracts text that appears visually in the video. It ca +## Logo Detection + +This feature identifies logos in a video and provides bounding box information, indicating the coordinates of each detected logos within the video frame, and confidence scores. This feature is not enabled by default. + @@ -33 +37 @@ This feature detects and extracts text that appears visually in the video. It ca -Content moderation detects inappropriate, unwanted, or offensive content in a video. For Preview, BDA will support 7 moderation categories: Explicit, Non-Explicit Nudity of Intimate parts and Kissing, Swimwear or Underwear, Violence, Drugs & Tobacco, Alcohol, Hate symbols. Explicit text in videos is not flagged. +Content moderation detects inappropriate, unwanted, or offensive content in a video. BDA supports 7 moderation categories: Explicit, Non-Explicit Nudity of Intimate parts and Kissing, Swimwear or Underwear, Violence, Drugs & Tobacco, Alcohol, Hate symbols. Explicit text in videos is not flagged. @@ -67 +71 @@ The following is an example of a standard output for a video processed through B - "scenes": [ + "chapter": [ @@ -69 +73 @@ The following is an example of a standard output for a video processed through B - "scene_index": 0, + "chapter_index": 0, @@ -203 +207 @@ The following is an example of a standard output for a video processed through B - "scene_count": 2, + "chapter_count": 2, @@ -213 +217 @@ These examples illustrate the comprehensive nature of the BDA output, providing -BDA supports videos in the file formats MP4, MOV with H.264, VP8, and VP9. Video files have a maximum length of 120 minutes and a maximum size of 10240 MB. Videos must have a width and height greater than 224 and less than 7680. +BDA supports videos in the file formats MP4, MOV with H.264, VP8, and VP9. Video files have a maximum length of 120 minutes and a maximum size of 10240 MB. Videos must have a width and height greater than 224 and less than 7680. If an audio file has mutiple audio streams, it will only process the first stream.