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

• URL: http://arxiv.org/abs/2509.23009v1
• Date: Sat, 27 Sep 2025 00:03:41 GMT
• Title: Disentangling Static and Dynamic Information for Reducing Static Bias in Action Recognition
• Authors: Masato Kobayashi, Ning Ding, Toru Tamaki,
• Abstract summary: Action recognition models rely excessively on static cues rather than dynamic human motion.<n>This bias leads to poor performance in real-world applications and zero-shot action recognition.<n>We propose a method to reduce static bias by separating temporal dynamic information from static scene information.
• Score: 7.926707765944282
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition [52.537021302246664]
  Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance)<n>We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes.<n>We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51.
  arXiv  Detail & Related papers  (2025-01-31T20:47:06Z)
• Sequential Disentanglement by Extracting Static Information From A Single Sequence Element [7.631288333466648]
  One of the fundamental representation learning tasks is unsupervised sequential disentanglement. We propose a novel and simple architecture that mitigates information leakage by offering a simple and effective subtraction inductive bias. We show beyond state-of-the-art results on generation and prediction tasks in comparison to several strong baselines.
  arXiv  Detail & Related papers  (2024-06-26T07:32:47Z)
• Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination [54.865941973768905]
  We propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings. CRISPR automatically determines biased outputs and categorizes neurons that affect the biased outputs as bias neurons using an explainability method. Experimental results demonstrate the effectiveness of our method in mitigating biases under zero-shot instruction-following settings without losing the model's task performance and existing knowledge.
  arXiv  Detail & Related papers  (2023-11-16T07:16:55Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground [59.916365866505636]
  Shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution generalization. In this paper, we empirically verify the existence of foreground static bias by creating test videos with conflicting signals from the static and moving portions of the video. StillMix identifies bias-inducing video frames using a 2D reference network and mixes them with videos for training, serving as effective bias suppression.
  arXiv  Detail & Related papers  (2022-11-23T11:40:02Z)
• Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks [29.47784194895489]
  Action recognition, automatic video object segmentation (AVOS) and video instance segmentation (VIS) are studied. Most examined models are biased toward static information. Some datasets that are assumed to be biased toward dynamics are actually biased toward static information.
  arXiv  Detail & Related papers  (2022-11-03T13:17:53Z)
• A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information [34.595367958746856]
  We analyse two widely studied tasks, action recognition and video object segmentation. Most examined models are biased toward static information. Certain two-stream architectures with cross-connections show a better balance between the static and dynamic information captured.
  arXiv  Detail & Related papers  (2022-06-06T18:39:37Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)
• Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior [63.11478060678794]
  We propose an effective motion-excited sampler to obtain motion-aware noise prior. By using the sparked prior in gradient estimation, we can successfully attack a variety of video classification models with fewer number of queries.
  arXiv  Detail & Related papers  (2020-03-17T10:54:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.