C
Chang Tang
Researcher at China University of Geosciences (Wuhan)
Publications - 70
Citations - 3514
Chang Tang is an academic researcher from China University of Geosciences (Wuhan). The author has contributed to research in topics: Cluster analysis & Graph (abstract data type). The author has an hindex of 25, co-authored 67 publications receiving 2034 citations. Previous affiliations of Chang Tang include Information Technology University & Tianjin University.
Papers
More filters
Journal ArticleDOI
Action Recognition From Depth Maps Using Deep Convolutional Neural Networks
TL;DR: The proposed method maintained its performance on the large dataset, whereas the performance of existing methods decreased with the increased number of actions, and the method achieved 2-9% better results on most of the individual datasets.
Journal ArticleDOI
RGB-D-based action recognition datasets
TL;DR: In this article, a comprehensive review of the most commonly used action recognition related RGB-D video datasets, including 27 single-view, 10 multi-view and 7 multi-person datasets, is presented.
Journal ArticleDOI
Late Fusion Incomplete Multi-View Clustering
Xinwang Liu,Xinzhong Zhu,Miaomiao Li,Lei Wang,Chang Tang,Jianping Yin,Dinggang Shen,Huaimin Wang,Wen Gao +8 more
TL;DR: This work proposes Late Fusion Incomplete Multi-view Clustering (LF-IMVC) which effectively and efficiently integrates the incomplete clustering matrices generated by incomplete views and develops a three-step iterative algorithm to solve the resultant optimization problem with linear computational complexity and theoretically prove its convergence.
Journal ArticleDOI
Learning a Joint Affinity Graph for Multiview Subspace Clustering
TL;DR: A low-rank representation model is employed to learn a shared sample representation coefficient matrix to generate the affinity graph and diversity regularization is used to learn the optimal weights for each view, which can suppress the redundancy and enhance the diversity among different feature views.
Proceedings ArticleDOI
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks
TL;DR: A new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition from RGB-D data and takes better advantage of the trained ConvNets models over ImageNet.