Learning to Discriminate Information for Online Action Detection

Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 809-818

Abstract


From a streaming video, online action detection aims to identify actions in the present. For this task, previous methods use recurrent networks to model the temporal sequence of current action frames. However, these methods overlook the fact that an input image sequence includes background and irrelevant actions as well as the action of interest. For online action detection, in this paper, we propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others. Our unit, named Information Discrimination Unit (IDU), decides whether to accumulate input information based on its relevance to the current action. This enables our recurrent network with IDU to learn a more discriminative representation for identifying ongoing actions. In experiments on two benchmark datasets, TVSeries and THUMOS-14, the proposed method outperforms state-of-the-art methods by a significant margin. Moreover, we demonstrate the effectiveness of our recurrent unit by conducting comprehensive ablation studies.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Eun_2020_CVPR,
author = {Eun, Hyunjun and Moon, Jinyoung and Park, Jongyoul and Jung, Chanho and Kim, Changick},
title = {Learning to Discriminate Information for Online Action Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}