Qingzhe Pan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qingzhe Pan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Xuemei Xie
School of Artificial Intelligence, Xidian University, Xian, China
3 shared publications - Zhifu Zhao
Xidian University
2 shared publications - Guangming Shi
Peng Cheng Laboratory, Shenzhen, Guangdong, China
1 shared publication - Jianan Li
Xidian University, Xi’an, China
1 shared publication - Wan Liu
Shaanxi Key Laboratory of Degradable Biomedical Materials and Shanxi R&D Center of Biomaterials and Fermentation Engineering, School of Chemical Engineering, Northwest University, Xi’an, Shaanxi 710069, China
1 shared publication Yuhan Cao
School of Artificial Intelligence, Xidian University, Xi'an, China
1 shared publication
Latest Publications
- 23 September 2024
- Published by Elsevier in Neurocomputing
- Vol. 613
Language-guided temporal primitive modeling for skeleton-based action recognition
- 23 September 2024
- Published by Elsevier in Neurocomputing
- Vol. 613
Language-guided temporal primitive modeling for skeleton-based action recognition
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (12) , 7398-7412
View-Normalized and Subject-Independent Skeleton Generation for Action Recognition
Skeleton-based action recognition has attracted great interest in computer vision. For this task, a challenging problem concerns the large intraclass variances of skeleton data, which are mainly caused by diverse viewpoints and subjects, and greatly increase the difficulty of modeling actions through a network. To address the above problem, we propose a variance reduction (VaRe) framework for skeleton-based action recognition, which consists of a view-normalization generative adversarial network (VN-GAN), a subject-independent network (SINet) and a classification network. First, the VN-GAN is responsible for reducing view-induced intraclass variances. Specifically, this network, comprising a generator and a discriminator, is aimed at learning a mapping from a diverse-view skeleton distribution to a unified-view skeleton distribution in an unsupervised manner, thereby generating a view-normalized skeleton. Second, taking the view-normalized skeleton as input, the SINet focuses on reducing the influences of the personal habits of subjects on action recognition. To generate SI skeleton data, the SINet automatically adjusts the human pose according to the human kinematic structure under a classification loss constraint. Finally, without the interference of view- and subject-induced variances, the classification network can concentrate more on learning discriminative action features to predict classes. Furthermore, by combining the joint and bone modalities, the proposed framework achieves competitive performance on three benchmarks: NTU RGB+D, NTU-120 RGB+D and Northwestern-UCLA Multiview Action 3D.
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (12) , 7398-7412
View-Normalized and Subject-Independent Skeleton Generation for Action Recognition
Skeleton-based action recognition has attracted great interest in computer vision. For this task, a challenging problem concerns the large intraclass variances of skeleton data, which are mainly caused by diverse viewpoints and subjects, and greatly increase the difficulty of modeling actions through a network. To address the above problem, we propose a variance reduction (VaRe) framework for skeleton-based action recognition, which consists of a view-normalization generative adversarial network (VN-GAN), a subject-independent network (SINet) and a classification network. First, the VN-GAN is responsible for reducing view-induced intraclass variances. Specifically, this network, comprising a generator and a discriminator, is aimed at learning a mapping from a diverse-view skeleton distribution to a unified-view skeleton distribution in an unsupervised manner, thereby generating a view-normalized skeleton. Second, taking the view-normalized skeleton as input, the SINet focuses on reducing the influences of the personal habits of subjects on action recognition. To generate SI skeleton data, the SINet automatically adjusts the human pose according to the human kinematic structure under a classification loss constraint. Finally, without the interference of view- and subject-induced variances, the classification network can concentrate more on learning discriminative action features to predict classes. Furthermore, by combining the joint and bone modalities, the proposed framework achieves competitive performance on three benchmarks: NTU RGB+D, NTU-120 RGB+D and Northwestern-UCLA Multiview Action 3D.
- Open Access
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 20503-20513
A Hybrid-3D Convolutional Network for Video Compressive Sensing
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 20503-20513
Open AccessA Hybrid-3D Convolutional Network for Video Compressive Sensing