Live and Learn: Continual Action Clustering with Incremental Views

arXiv:2404.07962v1 Announce Type: cross
Abstract: Multi-view action clustering leverages the complementary information from different camera views to enhance the clustering performance. Although existing approaches have achieved significant progress, they assume all camera views are available in advance, which is impractical when the camera view is incremental over time. Besides, learning the invariant information among multiple camera views is still a challenging issue, especially in continual learning scenario. Aiming at these problems, we propose a novel continual action clustering (CAC) method, …

abstract advance arxiv clustering continual cs.cv cs.lg incremental information learn performance progress type view