Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation

arXiv:2404.18206v1 Announce Type: new
Abstract: Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that have missing or inaccurate joints. This paper addresses the issue of enhancing action recognition using low-quality skeletons through a general knowledge distillation framework. The proposed framework employs a teacher-student model setup, where a teacher model trained on high-quality skeletons guides the learning of …

abstract action recognition applications arxiv challenges cs.cv data distillation diverse domains human human-centric issue knowledge low paper part quality quality data recognition type via videos vital