TY - JOUR
T1 - Jointly learning heterogeneous features for RGB-D activity recognition
AU - Hu, Jian-Fang
AU - Zheng, Wei-Shi
AU - Lai, Jianhuang
AU - Zhang, Jianguo
N1 - This work was supported partially by the National Key Research and Development Program of China(2016YFB1001002, 2016YFB1001003), NSFC (61573387,61472456, 61522115, 61661130157, 61628212), Guangdong Natural Science Funds for Distinguished Young Scholar under Grant S2013050014265, the GuangDong Program (2015B010105005), the Guangdong Science and Technology Planning Project (2016A010102012,2014B010118003), and Guangdong Program for Support of Top-notch Young Professionals (2014TQ01X779).
PY - 2017/11
Y1 - 2017/11
N2 - In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogenous multi-task learning. The proposed model in an unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to enable the multi-task classifier learning, and 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces. To efficiently train the joint model, a three-step iterative optimization algorithm is proposed, followed by two inference models. Extensive results on three activity datasets have demonstrated the efficacy of the proposed method. In addition, a novel RGB-D activity dataset focusing on human-object interaction is collected for evaluating the proposed method, which will be made available to the community for RGB-D activity benchmarking and analysis
AB - In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogenous multi-task learning. The proposed model in an unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to enable the multi-task classifier learning, and 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces. To efficiently train the joint model, a three-step iterative optimization algorithm is proposed, followed by two inference models. Extensive results on three activity datasets have demonstrated the efficacy of the proposed method. In addition, a novel RGB-D activity dataset focusing on human-object interaction is collected for evaluating the proposed method, which will be made available to the community for RGB-D activity benchmarking and analysis
KW - heterogeneous features learning
KW - RGB-D activity recognition
KW - action recognition
U2 - 10.1109/TPAMI.2016.2640292
DO - 10.1109/TPAMI.2016.2640292
M3 - Article
C2 - 28026749
SN - 0162-8828
VL - 39
SP - 2186
EP - 2200
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 11
T2 - The IEEE Conference on Computer Vision and Pattern Recognition
Y2 - 7 June 2015 through 12 June 2015
ER -
