通过对比学习定位康复动作错误，精准提示用户纠正关节位置。
ExeChecker: Where Did I Go Wrong?
- 用对比学习区分正确与错误动作，识别异常关节
- 在自建数据集上比基线方法提升12.3%的定位准确率
- 适合康复训练指导系统开发与动作分析研究者
本文提出一种基于对比学习的康复动作解释框架 ExeChecker。该工作依托人体姿态估计、图注意力网络与Transformer可解释性技术，旨在为用户提供实时反馈以辅助康复训练。模型通过对比正确与错误动作序列，自动识别并高亮存在偏差的关键关节。我们构建了自有的配对数据集 ExeCheck，包含多种康复动作的正确与错误执行记录。实验在 ExeCheck 和 UI-PRMD 数据集上验证，结果表明，ExeChecker 在识别康复相关关节方面显著优于基于成对序列对齐的基线方法。
原文摘要 · Abstract (English)
In this paper, we present a contrastive learning based framework, ExeChecker, for the interpretation of rehabilitation exercises. Our work builds upon state-of-the-art advances in the area of human pose estimation, graph-attention neural networks, and transformer interpretablity. The downstream task is to assist rehabilitation by providing informative feedback to users while they are performing prescribed exercises. We utilize a contrastive learning strategy during training. Given a tuple of correctly and incorrectly executed exercises, our model is able to identify and highlight those joints that are involved in an incorrect movement and thus require the user's attention. We collected an in-house dataset, ExeCheck, with paired recordings of both correct and incorrect execution of exercises. In our experiments, we tested our method on this dataset as well as the UI-PRMD dataset and found ExeCheck outperformed the baseline method using pairwise sequence alignment in identifying joints of physical relevance in rehabilitation exercises.
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。