2 datasets found

Groups: Natural Language Video Grounding Organizations: No Organization Formats: JSON

Filter Results
  • TACoS

    A dataset of videos with multiple sentence descriptions, used for activity recognition and video description tasks.
  • ActivityNet Captions

    The ActivityNet Captions is a benchmark dataset proposed for dense video captioning. There are 20K untrimmed videos in total, and each video has several annotated segments with...