friedrichor/MSR-VTT download history

friedrichor/MSR-VTT is a text to video dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,910 times (513 in the last 7 days), and 25,894 times in total. It ranks #11,689 among datasets by monthly downloads.

MSRVTT contains 10K video clips and 200K captions. We adopt the standard 1K-A split protocol, which was introduced in JSFusion and has since become the de facto benchmark split in the Text-Video Retrieval field. Train: train_7k: 7,010 videos, 140,200 captions train_9k: 9,000 videos, 180,000 cap

Models trained on MSR-VTT

6 models list it as training data.

Open friedrichor/MSR-VTT on Hugging Face

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