Skeleton-Based Human Action Recognition with Noisy Labels

arXiv:2403.09975v1 Announce Type: new
Abstract: Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model's training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so …

action recognition arxiv cs.cv cs.ro eess.iv human labels recognition type