Yan Hui

Mrs. Yan Hui

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
12 July 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Xiuhua HuXiuhua Hu
Xiuhua Hu
HLHuan Liu
Huan Liu
YHYan Hui
Yan Hui
XWXi Wu
Xi Wu
JZJing Zhao
Jing Zhao
This paper proposes a tracking method combining feature enhancement and template update, aiming to solve the problems of existing trackers lacking global information attention, weak feature characterization ability, and not being well adapted to the changing appearance of the target. Pre-extracted features are enhanced in context and on channels through a feature enhancement network consisting of channel attention and transformer architectures. The enhanced feature information is input into classification and regression networks to achieve the final target state estimation. At the same time, the template update strategy is introduced to update the sample template judiciously. Experimental results show that the proposed tracking method exhibits good tracking performance on the OTB100, LaSOT, and GOT-10k benchmark datasets.

26 September 2022 in IEEE Access
Verified
Journal Article
Open access
YHYan Hui
Yan Hui
XWXi Wu
Xi Wu
XHXiuhua Hu
Xiuhua Hu
HLHuan Liu
Huan Liu
SYShijie You
Shijie You
Most unsupervised cross-domain person re-identification methods based on clustering suffer from a lack of feature discrimination and clustering generates pseudo-labels noise, leading to a decrease in accuracy. To solve these problems, this paper proposes an unsupervised cross-domain person re-identification method based on attention block and refined clustering. Firstly, ResNet50 is selected as the backbone network, coordinate attention and triple attention are concatenated and embedded in ResNet50 to extract fine-grained features, perform feature aggregation, and mine fine-grained information. Secondly, a refined clustering strategy is proposed to achieve a coarse-to-fine clustering process by designing the measurement standards for clustering, determining its reliability, and eliminating noisy samples. Finally, the hybrid memory bank dynamically stores cluster centers and continues to update them with iterations, adapting to changes in clusters and performing invariant learning. The experimental results show that the new method designed in the paper improves the accuracy of rank-1 and mAP by 0.4% and 2.4%, respectively, on the target domain Market-1501 dataset, and improves the accuracy of rank-1 and mAP by 0.4% and 1.1%, respectively, on the target domain DukeMTMC-ReID dataset, compared with other typical methods.

1 February 2022 in International Journal of Pattern Recognition and Artificial Intelligence
Verified
Journal Article
Closed access
PDF file
YHYan Hui
Yan Hui
YLYingyu Liang
Yingyu Liang
Xiuhua HuXiuhua Hu
Xiuhua Hu
XWXi Wu
Xi Wu
HLHuan Liu
Huan Liu

10 February 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
YHYan Hui
Yan Hui
FLFengyu Li
Fengyu Li
XHXiuhua Hu
Xiuhua Hu
XGXin Guo
Xin Guo
CSChao Shen
Chao Shen
To address the limitations in data augmentation and neglect of joint dependencies in self-supervised human action recognition, this paper proposes a hybrid framework that integrates topology-masked motion modeling with contrastive learning. The proposed motion topology-masking technique jointly encodes skeletal topology and motion dynamics, preventing the model from over-focusing on temporally salient regions of prominent motions. We employ a multi-stage hybrid augmentation strategy, combining conventional and extreme augmentation methods to generate diverse, enriched positive pairs for contrastive learning. Additionally, we introduce a trajectory-guided feature dropping module, which selectively discards critical features based on trajectory attention maps, preventing the model from avoiding excessive focus on local joint trajectories. This approach effectively leverages large-scale unlabeled skeleton data through self-supervised learning, significantly reducing reliance on costly annotated datasets. Extensive experiments on NTU-60, NTU-120, and PKU-MMD demonstrate that the proposed model achieves superior performance in both occluded scenarios under complex environments and low-supervision conditions. It effectively mitigates visual interference and annotation scarcity while substantially improving action recognition accuracy.

1 October 2016
Verified
Conference Paper
Closed access
JLJun Li
Jun Li
YHYan Hui
Yan Hui
ZYZhang Yangfei
Zhang Yangfei
ZYZhang Yuqiong
Zhang Yuqiong
HSHao Sipeng
Hao Sipeng
JHJin Huafeng
Jin Huafeng
In order to improve levels of power loss and local voltage magnitudes of distribution network, the optimization allocation problem of distribution generations (DG) in active distribution network is developed. A multi-objective model consisting of the total construction and operation cost and power loss is built, and the algorithm based on glowworm adaptive step strategy is proposed to obtain some optimize allocation pareto sets of DG in distribution network. Then the best allocation set is selected from the above candidate pareto sets by the interactive fuzzy decision technique. The simulation and analysis of IEEE 33-bus system is carried out. Simulation results show the proposed model and algorithm feasible and effective.

1 January 2023 in International Journal of Data Mining and Bioinformatics
Verified
Journal Article
Closed access
PYPing Yu
Ping Yu
FXFahuan Xie
Fahuan Xie
YLYunxin Long
Yunxin Long
DLDuo Long
Duo Long
YHYan Hui
Yan Hui