English

Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition

Computer Vision and Pattern Recognition 2025-09-30 v1

Abstract

Action recognition models rely excessively on static cues rather than dynamic human motion, which is known as static bias. This bias leads to poor performance in real-world applications and zero-shot action recognition. In this paper, we propose a method to reduce static bias by separating temporal dynamic information from static scene information. Our approach uses a statistical independence loss between biased and unbiased streams, combined with a scene prediction loss. Our experiments demonstrate that this method effectively reduces static bias and confirm the importance of scene prediction loss.

Keywords

Cite

@article{arxiv.2509.23009,
  title  = {Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition},
  author = {Masato Kobayashi and Ning Ding and Toru Tamaki},
  journal= {arXiv preprint arXiv:2509.23009},
  year   = {2025}
}

Comments

in Proc. of ICCV2025 Workshop and Challenge on Disentangled Representation Learning for Controllable Generation (DRL4Real)

R2 v1 2026-07-01T06:00:04.420Z