TY - JOUR
T1 - Learning to discriminate information for online action detection
AU - Eun, Hyunjun
AU - Moon, Jinyoung
AU - Park, Jongyoul
AU - Jung, Chanho
AU - Kim, Changick
N1 - Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85094661015&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.00089
DO - 10.1109/CVPR42600.2020.00089
M3 - Conference article
AN - SCOPUS:85094661015
SN - 1063-6919
SP - 806
EP - 815
JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
M1 - 9157233
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Y2 - 14 June 2020 through 19 June 2020
ER -