从3D姿态到 prose：基于生物力学的视觉-语言指导框架
From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching
AI总结：
BioCoach通过融合视觉和3D骨骼运动学，提出一种生物力学导向的视觉-语言框架，利用三阶段流程生成精准文本反馈，提升健身指导的个性化和准确性。
摘要：
我们提出了BioCoach，一种基于生物力学的视觉-语言框架，用于从流媒体视频中进行健身指导。BioCoach通过一种新颖的三阶段流程融合视觉外观和3D骨骼运动学：一种特定运动的自由度选择器，专注于显著关节；一种结构化的生物力学上下文，将个性化形态学与周期和约束分析相结合；以及一个视觉-生物力学条件反馈模块，通过交叉注意力生成精确的可操作文本。使用参数高效训练冻结视觉和语言骨干，BioCoach产生透明的个性化推理而非模式匹配。为使学习和公平评估，我们增强了QEVD-fit-coach的生物力学导向反馈，创建QEVD-bio-fit-coach，并引入一个生物力学意识的LLM判断指标。BioCoach在QEVD-bio-fit-coach上在词汇和判断指标上实现了显著提升，同时保持时间触发；在原始QEVD-fit-coach上，它提高了文本质量和正确性，时间接近一致，证明了显式运动学和约束对准确、相位感知指导的重要性。
英文摘要：
We present BioCoach, a biomechanics-grounded vision--language framework for fitness coaching from streaming video. BioCoach fuses 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.
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。
