FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912301763788800 |
|---|---|
| author | Han, Ruisheng Zhou, Kanglei Atapour-Abarghouei, Amir Liang, Xiaohui Shum, Hubert P. H. |
| author_facet | Han, Ruisheng Zhou, Kanglei Atapour-Abarghouei, Amir Liang, Xiaohui Shum, Hubert P. H. |
| contents | Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vulnerable to spurious correlations, limiting both their reliability and interpretability. In this paper, we introduce FineCausal, a novel causal-based framework that achieves state-of-the-art performance on the FineDiving-HM dataset. Our approach leverages a Graph Attention Network-based causal intervention module to disentangle human-centric foreground cues from background confounders, and incorporates a temporal causal attention module to capture fine-grained temporal dependencies across action stages. This dual-module strategy enables FineCausal to generate detailed spatio-temporal representations that not only achieve state-of-the-art scoring performance but also provide transparent, interpretable feedback on which features drive the assessment. Despite its strong performance, FineCausal requires extensive expert knowledge to define causal structures and depends on high-quality annotations, challenges that we discuss and address as future research directions. Code is available at https://github.com/Harrison21/FineCausal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23911 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment Han, Ruisheng Zhou, Kanglei Atapour-Abarghouei, Amir Liang, Xiaohui Shum, Hubert P. H. Computer Vision and Pattern Recognition Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vulnerable to spurious correlations, limiting both their reliability and interpretability. In this paper, we introduce FineCausal, a novel causal-based framework that achieves state-of-the-art performance on the FineDiving-HM dataset. Our approach leverages a Graph Attention Network-based causal intervention module to disentangle human-centric foreground cues from background confounders, and incorporates a temporal causal attention module to capture fine-grained temporal dependencies across action stages. This dual-module strategy enables FineCausal to generate detailed spatio-temporal representations that not only achieve state-of-the-art scoring performance but also provide transparent, interpretable feedback on which features drive the assessment. Despite its strong performance, FineCausal requires extensive expert knowledge to define causal structures and depends on high-quality annotations, challenges that we discuss and address as future research directions. Code is available at https://github.com/Harrison21/FineCausal. |
| title | FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23911 |