7 datasets found

CSL-Daily is a Chinese sign language (CSL) dataset that mainly focuses on people’s daily lives. It includes 18401, 1077, and 1176 available examples in the training, validation,...

PHOENIX-2014T is a German sign language (DGS) dataset that mainly includes weather forecast content from TV programs. It consists of 7096, 519, and 642 video text pairs in...

How2Sign is a large-scale continuous American Sign Language (ASL) dataset. After removing invalid text-video pairs, we retain 31019, 1738, and 2348 available pairs in the...

Sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. The proposed framework addresses these issues by...

Video moment retrieval task, which only retrieves the video clip with certain action given a query.

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels.

The dataset used in the paper is a video question answering dataset, which is a large-scale video-language pre-training task.