Exploring Ordinal Bias in Action Recognition for Instructional Videos

• URL: http://arxiv.org/abs/2504.06580v1
• Date: Wed, 09 Apr 2025 05:03:51 GMT
• Title: Exploring Ordinal Bias in Action Recognition for Instructional Videos
• Authors: Joochan Kim, Minjoon Jung, Byoung-Tak Zhang,
• Abstract summary: Action recognition models often rely on dominant, dataset-specific action sequences rather than true video comprehension.<n>We propose two effective video manipulation methods: Action Masking, which masks frames of frequently co-occurring actions, and Sequence Shuffling, which randomizes the order of action segments.
• Score: 18.30575202965141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as ordinal bias. To address this issue, we propose two effective video manipulation methods: Action Masking, which masks frames of frequently co-occurring actions, and Sequence Shuffling, which randomizes the order of action segments. Through comprehensive experiments, we demonstrate that current models exhibit significant performance drops when confronted with nonstandard action sequences, underscoring their vulnerability to ordinal bias. Our findings emphasize the importance of rethinking evaluation strategies and developing models capable of generalizing beyond fixed action patterns in diverse instructional videos.

Related papers

• Temporal Divide-and-Conquer Anomaly Actions Localization in Semi-Supervised Videos with Hierarchical Transformer [0.9208007322096532]
  Anomaly action detection and localization play an essential role in security and advanced surveillance systems. We propose a hierarchical transformer model designed to evaluate the significance of observed actions in anomalous videos. Our approach segments a parent video hierarchically into multiple temporal children instances and measures the influence of the children nodes in classifying the abnormality of the parent video.
  arXiv  Detail & Related papers  (2024-08-24T18:12:58Z)
• SOAR: Scene-debiasing Open-set Action Recognition [81.8198917049666]
  We propose Scene-debiasing Open-set Action Recognition (SOAR), which features an adversarial scene reconstruction module and an adaptive adversarial scene classification module. The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning. The latter aims to confuse scene type classification given video features, with a specific emphasis on the action foreground, and helps to learn scene-invariant information.
  arXiv  Detail & Related papers  (2023-09-03T20:20:48Z)
• Diffusion Action Segmentation [63.061058214427085]
  We propose a novel framework via denoising diffusion models, which shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions.
  arXiv  Detail & Related papers  (2023-03-31T10:53:24Z)
• Leveraging Self-Supervised Training for Unintentional Action Recognition [82.19777933440143]
  We seek to identify the points in videos where the actions transition from intentional to unintentional. We propose a multi-stage framework that exploits inherent biases such as motion speed, motion direction, and order to recognize unintentional actions.
  arXiv  Detail & Related papers  (2022-09-23T21:36:36Z)
• Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization [87.47977407022492]
  This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in weakly-supervised action localization. Under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting. Our method achieves state-of-the-art performance on two popular benchmarks.
  arXiv  Detail & Related papers  (2022-03-31T05:13:50Z)
• Learning to Align Sequential Actions in the Wild [123.62879270881807]
  We propose an approach to align sequential actions in the wild that involve diverse temporal variations. Our model accounts for both monotonic and non-monotonic sequences. We demonstrate that our approach consistently outperforms the state-of-the-art in self-supervised sequential action representation learning.
  arXiv  Detail & Related papers  (2021-11-17T18:55:36Z)
• Evidential Deep Learning for Open Set Action Recognition [36.350348194248014]
  We formulate the action recognition problem from the evidential deep learning (EDL) perspective. We propose a plug-and-play module to debias the learned representation through contrastive learning.
  arXiv  Detail & Related papers  (2021-07-21T15:45:37Z)
• Intra- and Inter-Action Understanding via Temporal Action Parsing [118.32912239230272]
  We construct a new dataset developed on sport videos with manual annotations of sub-actions, and conduct a study on temporal action parsing on top. Our study shows that a sport activity usually consists of multiple sub-actions and that the awareness of such temporal structures is beneficial to action recognition. We also investigate a number of temporal parsing methods, and thereon devise an improved method that is capable of mining sub-actions from training data without knowing the labels of them.
  arXiv  Detail & Related papers  (2020-05-20T17:45:18Z)

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.