Current state-of-the-art action detection systems are tailored for offline batch-processing applications. However, for online applications like human-robot interaction, current systems fall short. In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging untrimmed action videos in which different action categories occur concurrently. In contrast to previous methods, we solve the linking, action labelling and temporal localization problems jointly in a single pass. We demonstrate superior online association accuracy and speed (1.8ms per frame) as compared to the current state-of-the-art offline and online systems.
Singh Behl, HarkiratSapienza, MichaelSingh, GurkirtSaha, SumanCuzzolin, FabioTorr, Philip H.S.
Faculty of Technology, Design and Environment\School of Engineering, Computing and Mathematics
Year of publication: 2018Date of RADAR deposit: 2018-09-20
© 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.