Action Anticipation by Predicting Future Dynamic Images [chapter]

Cristian Rodriguez, Basura Fernando, Hongdong Li
2019 Lecture Notes in Computer Science  
2[0000−0002−2108−3904] , Basura Fernando 1,2[0000−0002−6920−9916] , and Hongdong Li 1,2[0000−0003−4125−1554] Abstract. Human action-anticipation methods predict what is the future action by observing only a few portion of an action in progress. This is critical for applications where computers have to react to human actions as early as possible such as autonomous driving, human-robotic interaction, assistive robotics among others. In this paper, we present a method for human action anticipation
more » ... by predicting the most plausible future human motion. We represent human motion using Dynamic Images [1] and make use of tailored loss functions to encourage a generative model to produce accurate future motion prediction. Our method outperforms the currently best performing action-anticipation methods by 4% on JHMDB-21, 5.2% on UT-Interaction and 5.1% on UCF 101-24 benchmarks.
doi:10.1007/978-3-030-11015-4_10 fatcat:kupdi2jxbbe5jmry24fcg6co54