momo321654/Interaction-Caption-Supplement download history

momo321654/Interaction-Caption-Supplement is a video text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 472 times (98 in the last 7 days), and 2,190 times in total. It ranks #34,652 among datasets by monthly downloads.

Interaction-Caption-Supplement Dense, per-second caption data for training streaming video-language models — the kind that must decide when to speak and when to stay silent while a video is still playing. It is a supplement to momo321654/VL-Interaction-EN: that release is strong on ch

Open momo321654/Interaction-Caption-Supplement on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.