HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908500033011712 |
|---|---|
| author | Wu, Junhao Gu, Xiuer Li, Zhiying Jin, Yeying Diao, Yunfeng Li, Zhiyu Song, Zhenbo Zhang, Xiaomei Fan, Zhaoxin |
| author_facet | Wu, Junhao Gu, Xiuer Li, Zhiying Jin, Yeying Diao, Yunfeng Li, Zhiyu Song, Zhenbo Zhang, Xiaomei Fan, Zhaoxin |
| contents | Evaluating human actions with clear and detailed feedback is important in areas such as sports, healthcare, and robotics, where decisions rely not only on final outcomes but also on interpretable reasoning. However, most existing methods provide only a final score without explanation or detailed analysis, limiting their practical applicability. To address this, we introduce HieroAction, a vision-language model that delivers accurate and structured assessments of human actions. HieroAction builds on two key ideas: (1) Stepwise Action Reasoning, a tailored chain of thought process designed specifically for action assessment, which guides the model to evaluate actions step by step, from overall recognition through sub action analysis to final scoring, thus enhancing interpretability and structured understanding; and (2) Hierarchical Policy Learning, a reinforcement learning strategy that enables the model to learn fine grained sub action dynamics and align them with high level action quality, thereby improving scoring precision. The reasoning pathway structures the evaluation process, while policy learning refines each stage through reward based optimization. Their integration ensures accurate and interpretable assessments, as demonstrated by superior performance across multiple benchmark datasets. Code will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis Wu, Junhao Gu, Xiuer Li, Zhiying Jin, Yeying Diao, Yunfeng Li, Zhiyu Song, Zhenbo Zhang, Xiaomei Fan, Zhaoxin Computer Vision and Pattern Recognition Evaluating human actions with clear and detailed feedback is important in areas such as sports, healthcare, and robotics, where decisions rely not only on final outcomes but also on interpretable reasoning. However, most existing methods provide only a final score without explanation or detailed analysis, limiting their practical applicability. To address this, we introduce HieroAction, a vision-language model that delivers accurate and structured assessments of human actions. HieroAction builds on two key ideas: (1) Stepwise Action Reasoning, a tailored chain of thought process designed specifically for action assessment, which guides the model to evaluate actions step by step, from overall recognition through sub action analysis to final scoring, thus enhancing interpretability and structured understanding; and (2) Hierarchical Policy Learning, a reinforcement learning strategy that enables the model to learn fine grained sub action dynamics and align them with high level action quality, thereby improving scoring precision. The reasoning pathway structures the evaluation process, while policy learning refines each stage through reward based optimization. Their integration ensures accurate and interpretable assessments, as demonstrated by superior performance across multiple benchmark datasets. Code will be released upon acceptance. |
| title | HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.16942 |