从3D姿态到文本：基于生物力学的视觉-语言教练
From 3D Pose to Prose: Biomechanics-Grounded Vision-Language Coaching
将3D骨骼运动学与视觉外观通过交叉注意力融合，用于生成可解释的健身指导文本；其运动学约束建模和参数高效训练策略可迁移到其他需要细粒度动作理解的视觉-语言任务。
原文依据 BioCoach fuses two signals, visual appearance and 3D skeletal kinematics, through a novel three-stage pipeline
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出BioCoach，一个基于生物力学的视觉-语言框架，用于从流式视频中进行健身指导。BioCoach通过新颖的三阶段流程融合视觉外观和3D骨骼运动学两种信号：一个针对特定动作的自由度选择器，将分析聚焦于关键关节；一个结构化的生物力学上下文，将个体形态测量与周期和约束分析配对；以及一个视觉-生物力学条件反馈模块，应用交叉注意力生成精确、可操作的文本。采用冻结视觉和语言骨干网络的参数高效训练，BioCoach产生透明、个性化的推理而非模式匹配。为了支持学习和公平评估，我们通过添加面向生物力学的反馈来增强QEVD-fit-coach，创建了QEVD-bio-fit-coach，并引入了一个生物力学感知的LLM评判指标。BioCoach在QEVD-bio-fit-coach上在词汇和评判指标上均取得明显提升，同时保持时序触发；在原始QEVD-fit-coach上，它以接近持平的时间性能提高了文本质量和正确性，表明显式运动学和约束是准确、相位感知指导的关键。
英文原文摘要 1222 字符
We present BioCoach, a biomechanics-grounded vision-language framework for fitness coaching from streaming video. BioCoach fuses two signals, visual appearance and 3D skeletal kinematics, through a novel three-stage pipeline: an exercise-specific degree-of-freedom selector that focuses analysis on salient joints; a structured biomechanical context that pairs individualized morphometrics with cycle and constraint analysis; and a vision-biomechanics conditioned feedback module that applies cross-attention to generate precise, actionable text. Using parameter-efficient training that freezes the vision and language backbones, BioCoach yields transparent, personalized reasoning rather than pattern matching. To enable learning and fair evaluation, we augment QEVD-fit-coach with biomechanics-oriented feedback to create QEVD-bio-fit-coach, and we introduce a biomechanics-aware LLM judge metric. BioCoach delivers clear gains on QEVD-bio-fit-coach across lexical and judgment metrics while maintaining temporal triggering; on the original QEVD-fit-coach, it improves text quality and correctness with near-parity timing, demonstrating that explicit kinematics and constraints are key to accurate, phase-aware coaching.