TY - JOUR
T1 - Multi-Mutual Consistency Induced Transfer Subspace Learning for Human Motion Segmentation
AU - Zhou, Tao
AU - Fu, Huazhu
AU - Gong, Chen
AU - Shen, Jianbing
AU - Shao, Ling
AU - Porikli, Fatih
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - Human motion segmentation based on transfer subspace learning is a rising interest in action-related tasks. Although progress has been made, there are still several issues within the existing methods. First, existing methods transfer knowledge from source data to target tasks by learning domain-invariant features, but they ignore to preserve domain-specific knowledge. Second, the transfer subspace learning is employed in either low-level or high-level feature spaces, but few methods consider fusing multi-level features for subspace learning. To this end, we propose a novel multi-mutual consistency induced transfer subspace learning framework for human motion segmentation. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces and reduces the distribution gap between them through a multi-mutual consistency learning strategy. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Our model also conducts the transfer subspace learning on different layers to capture multi-level structural information. Further, to preserve the temporal correlations, we project the learned representations into a block-like space. The proposed model is efficiently optimized by using the Augmented Lagrange Multiplier (ALM) algorithm. Experimental results on four human motion datasets demonstrate the effectiveness of our method over other state-of-the-art approaches.
AB - Human motion segmentation based on transfer subspace learning is a rising interest in action-related tasks. Although progress has been made, there are still several issues within the existing methods. First, existing methods transfer knowledge from source data to target tasks by learning domain-invariant features, but they ignore to preserve domain-specific knowledge. Second, the transfer subspace learning is employed in either low-level or high-level feature spaces, but few methods consider fusing multi-level features for subspace learning. To this end, we propose a novel multi-mutual consistency induced transfer subspace learning framework for human motion segmentation. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces and reduces the distribution gap between them through a multi-mutual consistency learning strategy. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Our model also conducts the transfer subspace learning on different layers to capture multi-level structural information. Further, to preserve the temporal correlations, we project the learned representations into a block-like space. The proposed model is efficiently optimized by using the Augmented Lagrange Multiplier (ALM) algorithm. Experimental results on four human motion datasets demonstrate the effectiveness of our method over other state-of-the-art approaches.
UR - http://www.scopus.com/inward/record.url?scp=85092733629&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.01029
DO - 10.1109/CVPR42600.2020.01029
M3 - Conference article
AN - SCOPUS:85092733629
SN - 1063-6919
SP - 10274
EP - 10283
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 - 9156399
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Y2 - 14 June 2020 through 19 June 2020
ER -