TengfeiLiuCoder/MRVBench download history

TengfeiLiuCoder/MRVBench is a video text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 336 times (53 in the last 7 days), and 837 times in total. It ranks #44,937 among datasets by monthly downloads.

MRVBench MRVBench is a benchmark for multi-reference image-grounded video captioning. Each example pairs a video with an ordered set of reference images and a caption that locally binds visible subjects, objects, appearances, actions, or scene elements to <Image_n> tags. The reference

Open TengfeiLiuCoder/MRVBench on Hugging Face

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