Qingzhe Pan

Qingzhe Pan

Auto-generated profile, based on publicly available information

Qingzhe Pan

School of Artificial Intelligence, Xidian University, Xi'an, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2020 in IEEE Access
Verified
Journal Article
Open access
ZZZhifu Zhao
Zhifu Zhao
Xuemei XieXuemei Xie
Xuemei Xie
WLWan Liu
Wan Liu
QPQingzhe Pan
Qingzhe Pan

4 November 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
QPQingzhe Pan
Qingzhe Pan
ZZZhifu Zhao
Zhifu Zhao
Xuemei XieXuemei Xie
Xuemei Xie
JLJianan Li
Jianan Li
YCYuhan Cao
Yuhan Cao
GSGuangming Shi
Guangming Shi
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.

23 September 2024 in Neurocomputing
Verified
Journal Article
Closed access
QPQingzhe Pan
Qingzhe Pan
Xuemei XieXuemei Xie
Xuemei Xie