Action Anticipation By Predicting Future Dynamic Images

Cristian Rodriguez, Basura Fernando, Hongdong Li; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

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 [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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Rodriguez_2018_ECCV_Workshops,
author = {Rodriguez, Cristian and Fernando, Basura and Li, Hongdong},
title = {Action Anticipation By Predicting Future Dynamic Images},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}