Something-Something

The Something-Something dataset consists of 174 fine-grained action categories that depict humans performing everyday actions with common objects. Recognizing actions in the Something-Something dataset heavily relies on identifying key regions and frames.

Data and Resources

Cite this as

Yi Tan, Zhaofan Qiu, Yanbin Hao, Ting Yao, Xiangnan He, Tao Mei (2024). Dataset: Something-Something. https://doi.org/10.57702/wy28dyay

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2309.09534
Author Yi Tan
More Authors
Zhaofan Qiu
Yanbin Hao
Ting Yao
Xiangnan He
Tao Mei