Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition

arXiv:2404.11903v1 Announce Type: new
Abstract: The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to an action recognition model for extracting video features and learning the object relations for action recognition. However, since the action prior is unknown in the object detection stage, important objects could be easily overlooked, leading to inferior action recognition performance. In …

abstract action recognition arxiv cs.cv detection features fed human interactions object objects pipeline proposals reasoning recognition stage type video