用反事实方法提升动作质量评估的长期稳定性与准确性
CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow
- 通过双向时序流与反事实正则化，解耦因果与干扰因素
- 在多个长时动作评估数据集上超越现有方法，表现最佳
- 适合需要精准长期动作分析的体育、康复等领域
动作质量评估（AQA）从动作视频中预测细粒度执行分数，广泛应用于体育、康复和技能评价。长时AQA（如花样滑冰、韵律体操）尤其具有挑战性，需建模长时间动态并抵御上下文混杂因素影响。现有方法或依赖昂贵标注，或采用单向时序建模，易受虚假相关性影响且长期表示不稳定。为此，我们提出CaFlow，一个统一框架，融合反事实去混杂与双向时序流。因果反事实正则化（CCR）模块以自监督方式解耦因果与混杂特征，并通过反事实干预强化因果鲁棒性；双时序流（BiT-Flow）模块在循环一致性约束下建模前后向动态，生成更平滑、连贯的表示。在多个长时AQA基准上的实验表明，CaFlow达到当前最优性能。代码已开源。
原文摘要 · Abstract (English)
Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counterfactual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。