- h
MSR-VTT
- huggingface.co
Updated Apr 8, 2025
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteVLM2Vec (2025). MSR-VTT [Dataset]. https://huggingface.co/datasets/VLM2Vec/MSR-VTTDataset updatedApr 8, 2025Dataset authored and provided byVLM2VecDescriptionClone 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
train_9k: 9,000 videos, 180,000 captionsTest:
test_1k: 1,000 videos, 1,000 captions
🌟 Citation@inproceedings{xu2016msrvtt, title={Msr-vtt: A large video description dataset… See the full description on the dataset page: https://huggingface.co/datasets/VLM2Vec/MSR-VTT.
- h
MSR-VTT
- huggingface.co
Updated Feb 28, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteKong (2025). MSR-VTT [Dataset]. https://huggingface.co/datasets/friedrichor/MSR-VTTCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedFeb 28, 2025AuthorsKongDescriptionMSRVTT 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 captionsTest:
test_1k: 1,000 videos, 1,000 captions
🌟 Citation@inproceedings{xu2016msrvtt, title={Msr-vtt: A large video description dataset for bridging video and language}… See the full description on the dataset page: https://huggingface.co/datasets/friedrichor/MSR-VTT.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailClone 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
train_9k: 9,000 videos, 180,000 captions
Test:
test_1k: 1,000 videos, 1,000 captions
🌟 Citation
@inproceedings{xu2016msrvtt, title={Msr-vtt: A large video description dataset… See the full description on the dataset page: https://huggingface.co/datasets/VLM2Vec/MSR-VTT.