Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition

Skeleton-based action recognition has recently made significant progress. However, data imbalance is still a great challenge in real-world scenarios. The performance of current action recognition algorithms declines sharply when training data suffers from heavy class imbalance. The imbalanced data actually degrades the representations learned by these methods and becomes the bottleneck for action recognition. How to learn unbiased representations from imbalanced action data is the key to long-tailed action recognition.

Data and Resources

Cite this as

Hongda Liu, Yunlong Wang, Min Ren, Junxing Hu, Zhengquan Luo, Guangqi Hou, Zhenan Sun (2024). Dataset: Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition. https://doi.org/10.57702/eibgp0mr

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.2308.14024
Author Hongda Liu
More Authors
Yunlong Wang
Min Ren
Junxing Hu
Zhengquan Luo
Guangqi Hou
Zhenan Sun
Homepage https://github.com/firework8/BRL