Skip to the content.


I received my B.S. degree from the School of Mathematics and Computational Science at Hunan University of Science and Technology. I am currently a Master student at the Institute of Information Engineering at Chinese Academy of Sciences and the School of Cyber Security at the University of Chinese Academy of Sciences. My major research interests include machine learning, contrastive learning and visual tracking. [Google Scholar] [Github]


*One paper has been accepted by MICCAI 2021.

*One paper has been accepted by IEEE TCSVT 2021.

*One paper was published in IEEE TNNLS 2021.

*We won the first prize in Anti-UAV 2020 challenge, CVPRW 2020.

*One paper was accepted in ACM MM 2020.


Selected research projects and papers.

TNNLS 2021: Cascaded Correlation Refinement for Robust Deep Tracking

In this paper, we propose a cascaded correlation refinement approach to facilitate the robustness of deep tracking. Our approach cascades multiple stages of correlation refinement to progressively refine target localization. We introduce an explicit measure to identify the tracking failure and then leverage a simple yet effective look-back scheme to adaptively incorporate the initial model and on-the-fly model to update the tracking model.
[Project] [Paper] [Code]

ACM MM 2020: Accurate UAV Tracking with Distance-Injected Overlap Maximization

In this work, we propose distance-injected overlap maximization for accurate UAV tracking. We use distance-injected semantic IoU loss to alleviate the drift problem caused by dual-dynamic disturbances. Furthermore, we conduct feature recalibration network and multi-scale feature concat that improve adaptive feature extraction for UAV targets.
[Project] [Paper] [Code]


Yixiong Chen*, Chunhui Zhang*, Li Liu, Cheng Feng, Changfeng Dong, Yongfang Luo, Xiang Wan, USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning, MICCAI 2021 (Co-first author, Oral) [PDF(arXiv)] [BibTex] [code]

Kangkai Zhang, Chunhui Zhang, Shikun Li, Dan Zeng, Shiming Ge, Student Network Learning via Evolutionary Knowledge Distillation, IEEE TCSVT 2021 [PDF(baidu)] [PDF(google)] [BibTex] [code]

Shiming Ge, Chunhui Zhang, Shikun Li, Dan Zeng, Dacheng Tao, Cascaded Correlation Refinement for Robust Deep Tracking, IEEE TNNLS 2021 (Student First Author)[PDF(baidu)] [PDF(google)] [BibTex] [code]

Chunhui Zhang, Shiming Ge, Kangkai Zhang, Dan Zeng, Accurate UAV Tracking with Distance-Injected Overlap Maximization, ACM MM 2020 (Oral) [PDF(baidu)] [PDF(google)] [BibTex] [code]

Shiming Ge, Zhao Luo, Chunhui Zhang, Yingying Hua, Dacheng Tao, Distilling Channels for Efficient Deep Tracking, IEEE TIP 2020 [PDF(baidu)] [PDF(google)] [BibTex]

Shikun Li, Shiming Ge, Yingying Hua, Chunhui Zhang, Hao Wen, Tengfei Liu, Weiqiang Wang, Coupled-View Deep Classifier Learning from Multiple Noisy Annotators, AAAI 2020 [PDF(baidu)] [PDF(google)] [BibTex] [code]

Chunhui Zhang, Shiming Ge, Yingying Hua, Dan Zeng, Robust Deep Tracking with Two-step Augmentation Discriminative Correlation Filters, ICME 2019 [PDF(baidu)] [PDF(google)] [BibTex] [code]


The First Prize in Anti-UAV 2020 Challenge, CVPR Workshops 2020.

The First Prize in VisDrone 2019 Task 3: Single-object Tracking Challenge, ICCV Workshops 2019.

The First Prize in the Post-graduate Group of the Eighth MathorCup Mathematical Modeling Challenge 2018.

The First Prize in the China Post-graduate Mathematical Contest in Modeling 2017.

The Honor of “Excellent Graduate” of the Hunan Province 2016.

The Second Prize in the American University Students Mathematical Contest in Modeling 2016.

The National Scholarship 2015.

The Second Prize in the National University Students Mathematical Modeling Contest 2015.

The First Prize in the National University Students Mathematical Modeling Contest 2014.

The National Encouragement Scholarship 2013.

Committees or panels

Student Member of Chinese Society of Industrial and Applied Mathematics, 2018-present.

Review experience

A reviewer of the IEEE TNNLS, IEEE TIP, AAAI, ICCV and CVPR, etc.

Support or Contact