Something-Something V1 & V2 and Kinetics-400

Three large-scale video datasets for action recognition: Something-Something V1 & V2 and Kinetics-400.

Data and Resources

Cite this as

Mingyu Wu, Boyuan Jiang, Donghao Luo, Junchi Yan, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xiaokang Yang (2024). Dataset: Something-Something V1 & V2 and Kinetics-400. https://doi.org/10.57702/00eeo956

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.2103.12278
Author Mingyu Wu
More Authors
Boyuan Jiang
Donghao Luo
Junchi Yan
Yabiao Wang
Ying Tai
Chengjie Wang
Jilin Li
Feiyue Huang
Xiaokang Yang
Homepage https://www.aaai.org/Papers/AAAI/2021/AAAI12144.pdf