Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning

• URL: http://arxiv.org/abs/2512.15153v1
• Date: Wed, 17 Dec 2025 07:35:03 GMT
• Title: Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning
• Abstract summary: We define a new Human Action Form Assessment task and introduce a new diverse dataset CoT-AFA.<n>We enrich the CoT-AFA dataset with a novel Chain-of-Thought explanation paradigm.<n>We propose a framework named Explainable Fitness Assessor, which can not only judge an action but also explain why and provide a solution.
• Score: 45.80546806373221
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating whether human action is standard or not and providing reasonable feedback to improve action standardization is very crucial but challenging in real-world scenarios. However, current video understanding methods are mainly concerned with what and where the action is, which is unable to meet the requirements. Meanwhile, most of the existing datasets lack the labels indicating the degree of action standardization, and the action quality assessment datasets lack explainability and detailed feedback. Therefore, we define a new Human Action Form Assessment (AFA) task, and introduce a new diverse dataset CoT-AFA, which contains a large scale of fitness and martial arts videos with multi-level annotations for comprehensive video analysis. We enrich the CoT-AFA dataset with a novel Chain-of-Thought explanation paradigm. Instead of offering isolated feedback, our explanations provide a complete reasoning process--from identifying an action step to analyzing its outcome and proposing a concrete solution. Furthermore, we propose a framework named Explainable Fitness Assessor, which can not only judge an action but also explain why and provide a solution. This framework employs two parallel processing streams and a dynamic gating mechanism to fuse visual and semantic information, thereby boosting its analytical capabilities. The experimental results demonstrate that our method has achieved improvements in explanation generation (e.g., +16.0% in CIDEr), action classification (+2.7% in accuracy) and quality assessment (+2.1% in accuracy), revealing great potential of CoT-AFA for future studies. Our dataset and source code is available at https://github.com/MICLAB-BUPT/EFA.

Related papers

• HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis [33.807258169748465]
  HieroAction is a vision-language model that delivers accurate and structured assessments of human actions.<n>The reasoning pathway structures the evaluation process, while policy learning refines each stage through reward based optimization.<n>Their integration ensures accurate and interpretable assessments, as demonstrated by superior performance across multiple benchmark datasets.
  arXiv  Detail & Related papers  (2025-08-23T08:19:27Z)
• Combining Abstract Argumentation and Machine Learning for Efficiently Analyzing Low-Level Process Event Streams [18.821902752237204]
  We propose a data/computation-efficient neuro-symbolic approach to the interpretation problem.<n>Considering the urgent need of developing Green AI solutions, we propose a data/computation-efficient neuro-symbolic approach to the problem.
  arXiv  Detail & Related papers  (2025-05-09T08:45:07Z)
• Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression [46.25518274714238]
  Action Assessment (AQA) aims at automatic and fair evaluation of athletic performance.<n>Current methods focus on segmenting video into fixed frames, which disrupts the temporal continuity of sub-actions.<n>We propose a novel action quality assessment method through hierarchically pose-guided multi-stage contrastive regression.
  arXiv  Detail & Related papers  (2025-01-07T10:20:16Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos [49.07140708026425]
  Anomaly detection and localization in visual data, including images and videos, are crucial in machine learning and real-world applications.<n>This paper provides the first comprehensive survey focused specifically on explainable 2D visual anomaly detection (X-VAD)<n>We present a literature review of explainable methods, categorized by their underlying techniques.<n>We discuss promising future directions and open problems, including quantifying explanation quality.
  arXiv  Detail & Related papers  (2023-02-13T20:17:41Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval [152.3504607706575]
  This research aims to conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and define two real practical instance-level retrieval tasks. We exploit to train a more effective cross-modal model which is adaptively capable of incorporating key concept information from the multi-modal data.
  arXiv  Detail & Related papers  (2022-06-17T15:40:45Z)
• FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment [93.09267863425492]
  We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. We construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures.
  arXiv  Detail & Related papers  (2022-04-07T17:59:32Z)
• Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework [15.656965429236235]
  We take steps towards making automatic video summarization more realistic by addressing several challenges. Firstly, the currently available datasets either have very short videos or have few long videos of only a particular type. We introduce a new benchmarking dataset VISIOCITY which comprises of longer videos across six different categories.
  arXiv  Detail & Related papers  (2020-07-29T02:44:35Z)

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.