VidParse：在线解析自我中心程序，无需训练

AI 摘要

VidParse 是一个无需训练的在线自我中心程序解析框架，利用冻结的 DINOv2 和手-物检测器构建操作锚定特征，通过时间相似性矩阵和棋盘核检测动作边界，并使用图约束波束搜索强制执行程序性任务图。在 GTEA 和 EgoPER 基准上，该方法在复杂多步解析准确率上比强在线基线提升高达 10 倍，且无需梯度更新。

正文节选

VidParse: Online Parsing of Egocentric Procedures Like a Pro Abstract Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motion, transient occlusions, and the high intra-class variability of unscripted human-object interactions cause standard frame-level online temporal models to struggle, often resulting in severe over-segmentation and structural collapse. To bridge the gap between unstable low-level

发布时间：2026-08-31 12:00

抓取时间：2026-08-31 13:01

来源机构：arXiv