MSR-VTT

The dataset used in the paper is MSR-VTT, a large video description dataset for bridging video and language. The dataset contains 10k video clips with length varying from 10 to 32 seconds, and each video is provided with 20 related captions for training.

Data and Resources

Cite this as

Jun Xu, Tao Mei, Ting Yao, Yong Rui (2024). Dataset: MSR-VTT. https://doi.org/10.57702/hi8ky096

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2109.14084
Citation
  • https://doi.org/10.48550/arXiv.2305.10474
  • https://doi.org/10.48550/arXiv.2405.16009
  • https://doi.org/10.48550/arXiv.2111.12476
  • https://doi.org/10.48550/arXiv.2404.13425
  • https://doi.org/10.48550/arXiv.2310.12190
  • https://doi.org/10.48550/arXiv.2106.05438
  • https://doi.org/10.48550/arXiv.2406.08656
  • https://doi.org/10.48550/arXiv.2312.07509
  • https://doi.org/10.48550/arXiv.2103.15686
  • https://doi.org/10.48550/arXiv.2211.11427
  • https://doi.org/10.48550/arXiv.2307.09972
  • https://doi.org/10.48550/arXiv.2402.03161
  • https://doi.org/10.48550/arXiv.2209.13853
  • https://doi.org/10.1609/aaai.v37i3.25483
  • https://doi.org/10.48550/arXiv.1804.05448
  • https://doi.org/10.48550/arXiv.2007.02503
  • https://doi.org/10.48550/arXiv.2311.13073
  • https://doi.org/10.48550/arXiv.2312.08870
  • https://doi.org/10.48550/arXiv.1704.01502
  • https://doi.org/10.48550/arXiv.2402.04324
  • https://doi.org/10.48550/arXiv.2205.08508
Author Jun Xu
More Authors
Tao Mei
Ting Yao
Yong Rui
Homepage https://msrvtt.github.io/