PTL-LTM model for complex action recognition using local-weighted NMF and deep dual-manifold regularized NMF with sparsi
- PDF / 5,854,231 Bytes
- 23 Pages / 595.276 x 790.866 pts Page_size
- 71 Downloads / 149 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
PTL-LTM model for complex action recognition using local-weighted NMF and deep dual-manifold regularized NMF with sparsity constraint Ming Tong1 • He Bai1 • Xing Yue1 • Haili Bu1 Received: 20 April 2019 / Accepted: 7 February 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Complex action recognition possesses significant academic research value, potential commercial value and broad market application prospect. For improving its performance, a local-weighted nonnegative matrix factorization with rank regularization constraint (LWNMF_RC) is firstly presented, which removes complex background and then obtains motion salient regions. Secondly, a dual-manifold regularized nonnegative matrix factorization with sparsity constraint (DMNMF_SC) is proposed, which not only considers the short-term and middle-term temporal dependencies implied in data manifold, but also mines the geometric structure hidden in feature manifold. In addition, the introduction of sparsity constraint makes features possess better discriminativeness. Thirdly, a deep DMNMF_SC method is constructed, which acquires more hierarchical and discriminative features. Finally, a long-term temporal memory model with probability transfer learning (PTL-LTM) is proposed, which accurately memorizes the long-term temporal dependency among multiple simple action segments and, meanwhile, makes full use of the probability features of rich labeled simple actions and then applies the knowledge learned from simple actions for complex action recognition. Consequently, the performance is effectively improved. Keywords Complex action recognition Transfer learning Nonnegative matrix factorization Manifold structure
1 Introduction Human action recognition integrates the research contents of many fields such as image processing, machine learning and pattern recognition and is a hotspot and has a difficulty in the field of computer vision. In recent years, it has received extensive attentions from a large number of researchers and institutions due to its crucial academic value, potential commercial value and wide application prospects. More and more scholars and institutions have & Ming Tong [email protected] He Bai [email protected] Xing Yue [email protected] Haili Bu [email protected] 1
School of Electronic Engineering, Xidian University, Xi’an 710071, China
committed themselves to the research fever of this field. With the continuous deepening of research contents, the research focus has gradually developed from simple action recognition to the analysis, understanding and recognition for complex action. However, complex action recognition is a challenging research task. Firstly, there are many factors such as unconstrained complex environment, background clutter, motion speed variation and viewpoint changes, which result in large intra-class differences of the same class, whereas leading to weak separability among different classes. Secondly, unlike
Data Loading...
