pith. sign in

arxiv: 1808.00141 · v1 · pith:CW5JPO7Inew · submitted 2018-08-01 · 💻 cs.CV

Action Anticipation By Predicting Future Dynamic Images

classification 💻 cs.CV
keywords humanactionfuturemotionaction-anticipationanticipationdynamicimages
0
0 comments X
read the original 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 by predicting the most plausible future human motion. We represent human motion using Dynamic Images 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.