5 datasets found

Temporal sentence grounding in videos (TSGV) is a task to retrieve a video segment that semantically corresponds to a query in natural language.

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

Charades-STA dataset contains 12,408/3720 segment-sentence pairs and 5338/1334 videos in training and test set, respectively.

The DiDeMo dataset is a large-scale video-text dataset, containing 10,000 videos and 40,000 annotations.

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...