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

TL;DR

This paper introduces a new task and dataset for explainable human action form assessment, employing a Chain-of-Thought reasoning paradigm to evaluate, explain, and improve action standardization in videos.

Contribution

The paper presents a novel dataset CoT-AFA with multi-level annotations and a framework that provides both action assessment and detailed explanations using multimodal reasoning.

Findings

Improved explanation generation by +16.0% CIDEr score

Enhanced action classification accuracy by +2.7%

Better quality assessment accuracy by +2.1%

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.