用单阶段变压器实现精准到秒下的康复动作分割
HRTR: A Single-stage Transformer for Fine-grained Sub-second Action Segmentation in Stroke Rehabilitation
- 设计单阶段高分辨率时序变换器，直接定位与分类细粒度动作
- 在3个数据集上刷新性能，最高编辑得分88.4
- 适合需要精确动作分析的康复训练场景
中风康复常需精准追踪患者动作以评估进展，但康复动作复杂，面临两个关键挑战：细粒度与亚秒级（小于1秒）动作检测。本文提出高分辨率时序变换器（HRTR），在单阶段架构中实现高分辨率（细粒度）、亚秒级动作的时间定位与分类，无需多阶段流程或后处理。无需任何优化，HRTR在中风相关和通用数据集上均超越现有最优系统，在StrokeRehab Video数据集上取得70.1的编辑得分（ES），StrokeRehab IMU上为69.4，50Salads上达88.4。
原文摘要 · Abstract (English)
Stroke rehabilitation often demands precise tracking of patient movements to monitor progress, with complexities of rehabilitation exercises presenting two critical challenges: fine-grained and sub-second (under one-second) action detection. In this work, we propose the High Resolution Temporal Transformer (HRTR), to time-localize and classify high-resolution (fine-grained), sub-second actions in a single-stage transformer, eliminating the need for multi-stage methods and post-processing. Without any refinements, HRTR outperforms state-of-the-art systems on both stroke related and general datasets, achieving Edit Score (ES) of 70.1 on StrokeRehab Video, 69.4 on StrokeRehab IMU, and 88.4 on 50Salads.
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。