Temporally smooth online action detection using cycle-consistent future anticipation

Open Webpage

Young Hwi Kim, Seonghyeon Nam, Seon Joo Kim

Published: 01 Jan 2021, Last Modified: 06 Nov 2025Pattern Recognit. 2021EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose a novel network that anticipates future and applies temporal smoothness for online action detection.•The future anticipation is trained by an unsupervised method with a novel cycle-consistency loss function.•Our proposed temporal smoothing architecture can be applied in the online setting.•Our framework achieves the state-of-the-art performance among the recent methods of online action detection.