2021/12/19 by W. G. Price, Will Price, Price, Will +4 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Pose and Action Recognition #cs.CV
paper · pdf · doi:10.48550/arxiv.2112.10194
Accepted at IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2022
openalex publication_date 2021/12/19 · arxiv created 2022/04/04 · arxiv updated 2022/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Our lives can be seen as a complex weaving of activities; we switch from one activity to another, to maximise our achievements or in reaction to demands placed upon us. Observing a video of unscripted daily activities, we parse the video into its constituent activity threads through a process we call unweaving. To accomplish this, we introduce a video representation explicitly capturing activity threads called a thread bank, along with a neural controller capable of detecting goal changes and resuming of past activities, together forming UnweaveNet. We train and evaluate UnweaveNet on sequences from the unscripted egocentric dataset EPIC-KITCHENS. We propose and showcase the efficacy of pretraining UnweaveNet in a self-supervised manner.