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

arXiv: https://arxiv.org/abs/2509.23009 · HTML: https://mlsanity.com/paper/2509.23009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Revealing Single Frame Bias for Video-and-Language Learning](https://mlsanity.com/paper/2206.03428/) (2022)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Only Time Can Tell: Discovering Temporal Data for Temporal Modeling](https://mlsanity.com/paper/1907.08340/) (2019)
- [Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning](https://mlsanity.com/paper/2009.05769/) (2020)
- [Semantic-Aware Scene Recognition](https://mlsanity.com/paper/1909.02410/) (2019)
- [Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground](https://mlsanity.com/paper/2211.12883/) (2022)
- [Time Is MattEr: Temporal Self-supervision for Video Transformers](https://mlsanity.com/paper/2207.09067/) (2022)
- [ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition](https://mlsanity.com/paper/2204.00239/) (2022)
- [DEVIAS: Learning Disentangled Video Representations of Action and Scene](https://mlsanity.com/paper/2312.00826/) (2023)
- [Can masking background and object reduce static bias for zero-shot action recognition?](https://mlsanity.com/paper/2501.12681/) (2025)
- [Learning Human Action Recognition Representations Without Real Humans](https://mlsanity.com/paper/2311.06231/) (2023)
- [ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition](https://mlsanity.com/paper/2502.00156/) (2025)
- [S3Aug: Segmentation, Sampling, and Shift for Action Recognition](https://mlsanity.com/paper/2310.14556/) (2023)

## Abstract (arXiv)

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.