10 April 2018 Multi-task learning with group information for human action recognition
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106150W (2018) https://doi.org/10.1117/12.2303514
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Human action recognition is an important and challenging task in computer vision research, due to the variations in human motion performance, interpersonal differences and recording settings. In this paper, we propose a novel multi-task learning framework with group information (MTL-GI) for accurate and efficient human action recognition. Specifically, we firstly obtain group information through calculating the mutual information according to the latent relationship between Gaussian components and action categories, and clustering similar action categories into the same group by affinity propagation clustering. Additionally, in order to explore the relationships of related tasks, we incorporate group information into multi-task learning. Experimental results evaluated on two popular benchmarks (UCF50 and HMDB51 datasets) demonstrate the superiority of our proposed MTL-GI framework.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Qian, Song Wu, Nan Pu, Shulin Xu, Guoqiang Xiao, "Multi-task learning with group information for human action recognition", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150W (10 April 2018); doi: 10.1117/12.2303514; https://doi.org/10.1117/12.2303514
PROCEEDINGS
9 PAGES


SHARE
Back to Top