PATS自适应采样，让多视角运动技能评估更连贯准确
PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessment
- 根据动作特性自适应分段，保证每个片段完整包含关键动作
- 在EgoExo4D上提升0.65%~3.05%，攀岩任务提升26.22%
- 适合需要连续动作分析的真实场景运动评估
自动运动技能评估需捕捉区分专家与新手的关键动作模式，但现有视频采样方法破坏了评估所需的时间连续性。为此，我们提出熟练度感知时间采样（PATS），一种新型采样策略，通过保留连续时间段内的完整基础动作，实现多视角技能评估。PATS自适应地分割视频，确保每个分析片段包含关键动作的完整执行，并在多个片段中重复该过程以最大化信息覆盖，同时保持时间连贯性。在EgoExo4D基准上使用SkillFormer评估，PATS在所有视角配置下均超越当前最优性能（提升0.65%至3.05%），在挑战性任务中取得显著进展（攀岩+26.22%，音乐+2.39%，篮球+1.13%）。系统性分析表明，PATS能有效适应不同活动特征——对动态运动采用高频采样，对序列技能进行细粒度分段，证明其作为自适应时间采样方法的有效性，推动真实场景下的自动化技能评估发展。
原文摘要 · Abstract (English)
Automated sports skill assessment requires capturing fundamental movement patterns that distinguish expert from novice performance, yet current video sampling methods disrupt the temporal continuity essential for proficiency evaluation. To this end, we introduce Proficiency-Aware Temporal Sampling (PATS), a novel sampling strategy that preserves complete fundamental movements within continuous temporal segments for multi-view skill assessment. PATS adaptively segments videos to ensure each analyzed portion contains full execution of critical performance components, repeating this process across multiple segments to maximize information coverage while maintaining temporal coherence. Evaluated on the EgoExo4D benchmark with SkillFormer, PATS surpasses the state-of-the-art accuracy across all viewing configurations (+0.65% to +3.05%) and delivers substantial gains in challenging domains (+26.22% bouldering, +2.39% music, +1.13% basketball). Systematic analysis reveals that PATS successfully adapts to diverse activity characteristics-from high-frequency sampling for dynamic sports to fine-grained segmentation for sequential skills-demonstrating its effectiveness as an adaptive approach to temporal sampling that advances automated skill assessment for real-world applications. Visit our project page at https://edowhite.github.io/PATS
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。