SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System

arXiv:2311.08094v2 Announce Type: replace-cross
Abstract: Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than the processing of video frames. With the emergence of deep learning models, it has become very popular to represent the skeleton data in pseudo-image form and apply CNN for action recognition. Thereafter, studies concentrated on finding effective methods for forming pseudo-images. Recently, attention networks, more specifically transformers have provided …

abstract action recognition arxiv attention become consensus cs.ai cs.cv cs.lg cs.ro deep learning emergence popular processing recognition researchers robust transformers type video vision vision transformers