超越运动模式：人体运动理解中物理力的实证研究
Beyond Motion Pattern: An Empirical Study of Physical Forces for Human Motion Understanding
AI总结：
本研究通过引入物理推断的力，提升了人体运动理解在步态识别、动作识别和视频描述中的性能。
摘要：
人类运动理解通过基于视觉的识别、跟踪和描述技术取得了快速进展。然而，现有大多数方法忽视了诸如关节驱动力等物理线索，这些线索在生物力学中是基础性的。这一差距促使我们的研究：何时以及何时物理推断的力能增强运动理解？通过将力纳入已建立的运动理解流程中，我们系统地评估了其在三个主要任务上的影响：步态识别、动作识别和细粒度视频描述。在8个基准测试中，纳入力带来了持续的性能提升；例如，在CASIA-B上，Rank-1步态识别准确率从89.52%提升至90.39%（+0.87），在挑战性条件下观察到更大的提升：穿着外套时+2.7%，侧视时+3.0%。在Gait3D上，性能也从46.0%提升至47.3%（+1.3）。在动作识别中，CTR-GCN在Penn Action上实现了+2.00%，而高力度类别如拳击/拍打提高了6.96%。即使在视频描述中，Qwen2.5-VL的ROUGE-L分数从0.310提升到0.339（+0.029），表明物理推断的力增强了时间定位和语义丰富性。这些结果表明，在动态、遮挡或外观变化的条件下，力线索可以显著补充视觉和运动学特征。
英文摘要：
Human motion understanding has advanced rapidly through vision-based progress in recognition, tracking, and captioning. However, most existing methods overlook physical cues such as joint actuation forces that are fundamental in biomechanics. This gap motivates our study: if and when do physically inferred forces enhance motion understanding? By incorporating forces into established motion understanding pipelines, we systematically evaluate their impact across baseline models on 3 major tasks: gait recognition, action recognition, and fine-grained video captioning. Across 8 benchmarks, incorporating forces yields consistent performance gains; for example, on CASIA-B, Rank-1 gait recognition accuracy improved from 89.52% to 90.39% (+0.87), with larger gain observed under challenging conditions: +2.7% when wearing a coat and +3.0% at the side view. On Gait3D, performance also increases from 46.0% to 47.3% (+1.3). In action recognition, CTR-GCN achieved +2.00% on Penn Action, while high-exertion classes like punching/slapping improved by +6.96%. Even in video captioning, Qwen2.5-VL's ROUGE-L score rose from 0.310 to 0.339 (+0.029), indicating that physics-inferred forces enhance temporal grounding and semantic richness. These results demonstrate that force cues can substantially complement visual and kinematic features under dynamic, occluded, or appearance-varying conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
