ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More

arXiv:2403.12534v1 Announce Type: new
Abstract: Event cameras have recently been shown beneficial for practical vision tasks, such as action recognition, thanks to their high temporal resolution, power efficiency, and reduced privacy concerns. However, current research is hindered by 1) the difficulty in processing events because of their prolonged duration and dynamic actions with complex and ambiguous semantics and 2) the redundant action depiction of the event frame representation with fixed stacks. We find language naturally conveys abundant semantic information, rendering …

abstract action recognition arxiv cameras concerns cs.cv current efficiency event events however language power practical privacy processing reasoning recognition research tasks temporal type uncertainty vision