V-JEPA 2结合AQA：山地自行车跳跃的阶段评分与参考反馈
原标题：V-JEPA 2 Meets AQA: Phase-Based Scoring and Reference-Based Feedback for Mountain Biking
AI 摘要
该研究针对山地自行车跳跃动作质量评估（AQA），在仅有二值弱标签（好/差技术）和95段现场视频的条件下，利用冻结的V-JEPA 2视频特征结合二维姿态与运动测量，构建了基于阶段的评分器与参考层反馈生成流程。五折交叉验证中完整评分器取得AUROC 0.768、平均精度0.812，但作者指出该结果属探索性，存在测试折选择训练轮次、未按骑手划分数据等偏差；外部探针上评分准确率仅0.412，候选反馈精度0.118。研究结论明确不主张该流程可用于独立于骑手的评分或可靠的纠正性反馈，而是提出该领域所需的实证评估议程。
正文节选
V-JEPA 2 Meets AQA: Phase-Based Scoring and Reference-Based Feedback for Mountain Biking Abstract We study mountain-bike action quality assessment (AQA) with weak labels and candidate feedback. The training corpus comprises 95 field-recorded jump clips with binary labels denoting good or poor technique. These are coarse categorical labels, not continuous expert quality scores; phase-boundary and aspect-level annotations are unavailable. Our pipeline summarizes four heuristic phases using frozen