Jiuqing Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiuqing Dong has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Bo Huang
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
1 shared publication - Heng Zhou
International Joint Research Lab of Intelligent Perception and Control, Shanghai University of Engineering Science, No. 333 Longteng Road, Shanghai 201620, China
1 shared publication - Hyo Jong Lee
Division of Computer Science and Engineering, CAIIT, Jeonbuk National University, Jeonju 54896, Republic of Korea
1 shared publication - Yifan Yao
International Joint Research Lab of Intelligent Perception and Control, Shanghai University of Engineering Science, No. 333 Longteng Road, Shanghai 201620, China
1 shared publication - Yongbin Gao
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China
1 shared publication - Zhijun Fang
School of Computer Science and Technology, Donghua University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 21 February 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (4) , 1482
Action Recognition Based on the Fusion of Graph Convolutional Networks with High Order Features
Skeleton-based action recognition is a widely used task in action related research because of its clear features and the invariance of human appearances and illumination. Furthermore, it can also effectively improve the robustness of the action recognition. Graph convolutional networks have been implemented on those skeletal data to recognize actions. Recent studies have shown that the graph convolutional neural network works well in the action recognition task using spatial and temporal features of skeleton data. The prevalent methods to extract the spatial and temporal features purely rely on a deep network to learn from primitive 3D position. In this paper, we propose a novel action recognition method applying high-order spatial and temporal features from skeleton data, such as velocity features, acceleration features, and relative distance between 3D joints. Meanwhile, a method of multi-stream feature fusion is adopted to fuse these high-order features we proposed. Extensive experiments on Two large and challenging datasets, NTU-RGBD and NTU-RGBD-120, indicate that our model achieves the state-of-the-art performance.
- 21 February 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (4) , 1482
Open AccessAction Recognition Based on the Fusion of Graph Convolutional Networks with High Order Features
Skeleton-based action recognition is a widely used task in action related research because of its clear features and the invariance of human appearances and illumination. Furthermore, it can also effectively improve the robustness of the action recognition. Graph convolutional networks have been implemented on those skeletal data to recognize actions. Recent studies have shown that the graph convolutional neural network works well in the action recognition task using spatial and temporal features of skeleton data. The prevalent methods to extract the spatial and temporal features purely rely on a deep network to learn from primitive 3D position. In this paper, we propose a novel action recognition method applying high-order spatial and temporal features from skeleton data, such as velocity features, acceleration features, and relative distance between 3D joints. Meanwhile, a method of multi-stream feature fusion is adopted to fuse these high-order features we proposed. Extensive experiments on Two large and challenging datasets, NTU-RGBD and NTU-RGBD-120, indicate that our model achieves the state-of-the-art performance.