AVA v2.2

The AVA v2.2 dataset for spatiotemporal action localization contains the bounding box annotations and the corresponding action labels on keyframes.

Data and Resources

Cite this as

Zhifan Wan, Jie Zhang, Changzhen Li, Shiguang Shan (2024). Dataset: AVA v2.2. https://doi.org/10.57702/6p68znnc

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2212.04500
Citation
  • https://doi.org/10.48550/arXiv.2304.01199
Author Zhifan Wan
More Authors
Jie Zhang
Changzhen Li
Shiguang Shan
Homepage https://research.google.com/ava/index.html