Multi-View Video-Based Learning: Leveraging Weak Labels for Frame-Level Perception

arXiv:2403.11616v1 Announce Type: new
Abstract: For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are called as weak labels. However, training a multi-view video-based action recognition model with weak labels for frame-level perception is challenging. In this paper, we propose a novel learning framework, where the weak labels are first used to train a multi-view video-based base …

abstract action recognition annotations arxiv cs.cv easy however kind labels perception recognition training type video view