I am a four-year Ph.D. student and luckily advised by the brilliant and kind researcher Prof. Cairong Zhao. I am passionate about computer vision research in the following topics:

  1. Video Surveillance: Trustworthy Person Re-identification-Robust, Security, and Privacy-Preserving (Now)
  2. MSRA Research Intern Directions: Infographic understanding & NAS benchmark
  3. Classification: Hyperspectral Image Classification, 3D Point Cloud Classification (Master's degree)

Currently, I base my research topics on emerging abilities in foundation models such as LVLM for Occluded ReID and LLM for VIS. I am always grateful to those more senior who have a deep understanding of these topics for their advice. Besides, I am always willing to collaborate with people interested in relevant issues and provide corresponding guidance to younger students (undergrad or master).


You can download my CV at here.

I am actively seeking a Research Scientist or Postdoc Research Fellow. Please feel free to reach out if you have any suitable positions!


Feb 14, 2024 : I have been invited to be a Reviewer for the ECCV 2024 Conference (European Conference on Computer Vision 2024).

Jan 26, 2024 : I arrived in Detroit and started an exciting short-term visiting scholar program.

Dec 12, 2023 : I received the Tongji Excellent Doctoral Scholarship (2023).

Dec 06, 2023 : I have been invited to be a Reviewer for the 41st International Conference on Machine Learning (ICML 2024).

Nov 19, 2023 : I have been invited to be a Reviewer for the CVPR 2024 Conference (Conference on Computer Vision and Pattern Recognition 2024).

Oct 21, 2023 : I received an offer letter from Prof. Liu Xiaoming of MSU to start a six-month visiting trip as a visiting student.

Sep 29, 2023 : A paper on ‘Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification’ is accepted by IEEE T-IFS 2023 (CCF A).

Aug 27, 2023 : I have been invited to be a Reviewer for the ICLR 2024 Conference (Twelfth International Conference on Learning Representations).

see all news

Google Scholar IEEE Student Member
SH021, Shanghai, China.


Invisible backdoor attack with dynamic triggers against person re-identification

Existing backdoor attack methods follow an all-to-one or all-to-all attack scenario, where all the target classes in the test set have already been seen in the training set. However, ReID is a much more complex fine-grained open-set recognition problem, where the identities in the test set are not contained in the training set. Thus, previous backdoor attack methods for classification are not applicable to ReID. To ameliorate this issue, we propose a novel backdoor attack on deep ReID under a new all-to-unknown scenario, called Dynamic Triggers Invisible Backdoor Attack (DT-IBA). Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities.

Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao


pdf / project page / code (GitHub) / Website Online

EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search Benchmark

We present the first large-scale energy-aware benchmark that allows studying AutoML methods to achieve better trade-offs between performance and search energy consumption, named EA-HAS-Bench. EA-HAS-Bench provides a large-scale architecture/hyperparameter joint search space, covering diversified configurations related to energy consumption.

Shuguang Dou, Xinyang Jiang, Cairong Zhao, Dongsheng Li

ICLR 23 Spotlight

pdf / project page / code (GitHub) / Website Online

Human Co-Parsing Guided Alignment for Occluded Person Re-identification

We propose a novel Human Co-parsing Guided Alignment (HCGA) framework that alternately trains the human co-parsing network and the ReID network, where the human co-paring network is trained in a weakly supervised manner to obtain paring results without any extra annotation.

Shuguang Dou, Cairong Zhao, Xinyang Jiang, Shanshan Zhang, Member, IEEE, Wei-Shi Zheng, Wangmeng Zuo, Senior Member, IEEE


pdf / project page / code (GitHub) / Website Online

Detecting Overlapped Objects in X-ray Security Imagery by a Label-aware Mechanism

One of the key challenges to the X-ray security checkis to detect the overlapped items in backpacks or suitcases inthe X-ray images. Most existing methods improve the robustnessof models to the object overlapping problem by enhancingthe underlying visual information such as colors and edges.However, this strategy ignores the situations that the objectshave similar visual clues as to the background, and objectsoverlapping each other. Since the two cases rarely appear inexisting datasets, we contribute a novel dataset – Cutters andLiquid Containers X-ray Dataset (CLCXray) to complete therelated research.

Cairong Zhao, Liang Zhu, Shuguang Dou, Weihong Deng, and Liang Wang, Fellow, IEEE


pdf / project page / code (GitHub) / Website Online

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID

To address the occlusion problem, we propose a novel Incremental Generative Occlusion Adversarial Suppression (IGOAS) network.

Cairong Zhao, Xinbi Lv, Shuguang Dou*, Shanshan Zhang, Member, IEEE, Jun Wu, Senior Member, IEEE, and Liang Wang, Fellow, IEEE


pdf / project page / code (GitHub) / Website Online

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

The connection structure in the convolutional layers of most deep learning-based algorithms used for the classification of hyperspectral images (HSIs) has typically been in the forward direction. In this study, an end-to-end alternately updated spectral–spatial convolutional network (AUSSC) with a recurrent feedback structure is used to learn refined spectral and spatial features for HSI classification.

Wenju Wang, Shuguang Dou *, Sen Wang

Remote sensing 2019

pdf / project page / code (GitHub) / Website Online

A fast dense spectral-spatial convolutional network framework for hyperspectral image classification

To reduce the training time and improve accuracy, in this paper we propose an end-to-end fast dense spectral–spatial convolution (FDSSC) framework for HSI classification.

Wenju Wang, Shuguang Dou *, Zhongmin Jiang and Liujie Sun

Remote sensing 2018

pdf / project page / code (GitHub) / Website Online

see all publications


YuanPeng Tu (https://yuanpengtu.github.io/) : The most abstract man in ViLL Lab.

Shuyang Feng : The most thoughtful man in ViLL Lab.

Qingsong Zhao : A stubborn person who knows his own path.

Junyao Gao : A sincere person in Vill Lab.

Yubin Wang : The most trustworthy person in Vill lab.

Wenli Sun : My makeup artist in Vill lab.

Yan Li : Colleague in the MSRA and MSRA first Winners and Hard Worker.

Longtao Tang : Colleague in the MSRA and the man I admire most in the MSRA.

see all friends


Research on Feature Learning and Application of Three-dimensional Point Cloud

Learning deep features from 3D point cloud for classification and retrieval. This work will be done before 12/2019.

Shuguang Dou

Master Thesis, College of Communication and Art Design, University of Shanghai for Science and Technology; December, 2019

pdf in Chinese (Temporarily unavailable)