all AI news
SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition. (arXiv:2204.04796v2 [cs.CV] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Learning an egocentric action recognition model from video data is
challenging due to distractors (e.g., irrelevant objects) in the background.
Further integrating object information into an action model is hence
beneficial. Existing methods often leverage a generic object detector to
identify and represent the objects in the scene. However, several important
issues remain. Object class annotations of good quality for the target domain
(dataset) are still required for learning good object representation. Besides,
previous methods deeply couple the existing action …
arxiv cv learning objects self-supervised learning supervised learning