VLM2Vec/MSR-VTT download history
VLM2Vec/MSR-VTT is a text to video dataset on the Hugging Face Hub. In the last 30 days it was downloaded 4,683 times (654 in the last 7 days), and 276,253 times in total. It ranks #5,998 among datasets by monthly downloads.
Clone from "friedrichor/MSR-VTT". 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 t