计算机科学
虚假关系
人工智能
机器学习
质量(理念)
动作(物理)
可靠性(半导体)
限制
图形
钥匙(锁)
动作识别
事件(粒子物理)
任务分析
编码(集合论)
质量评定
相关性(法律)
因果推理
可解释性
深度学习
因果模型
仿形(计算机编程)
组分(热力学)
作者
Ruisheng Han,Kanglei Zhou,Amir Atapour–Abarghouei,Xiaohui Liang,Hubert P. H. Shum
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-06-11
卷期号:: 6008-6017
被引量:24
标识
DOI:10.1109/cvprw67362.2025.00599
摘要
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 spatiotemporal 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI