World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
39
Citations
7053
World Ranking
9703
National Ranking
1220

Overview

Baoyuan Wu is affiliated with the Chinese University of Hong Kong, Shenzhen in China. Their research primarily spans the field of Computer Science, with focused contributions across several subfields including Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing, Information Systems, and Electrical and Electronic Engineering.

The scientist's work addresses multiple main topics within these domains. These include Adversarial Robustness in Machine Learning, Anomaly Detection Techniques and Applications, Generative Adversarial Networks and Image Synthesis, Advanced Malware Detection Techniques, Digital Media Forensic Detection, Domain Adaptation and Few-Shot Learning, and Advanced Neural Network Applications.

Baoyuan Wu has published extensively, with a notable number of papers in venues such as arXiv (Cornell University), IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, Pattern Recognition, and the 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Recent notable papers include:

  • LAS-AT: Adversarial Training with Learnable Attack Strategy, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Rethinking the Trigger of Backdoor Attack, 2020, arXiv (Cornell University)
  • Boosting Fast Adversarial Training With Learnable Adversarial Initialization, 2022, IEEE Transactions on Image Processing
  • Robust Physical-World Attacks on Face Recognition, 2022, Pattern Recognition
  • BackdoorBench: A Comprehensive Benchmark of Backdoor Learning, 2022, arXiv (Cornell University)

The scientist often collaborates with several frequent co-authors, including Yanbo Fan, Yong Zhang, Zhifeng Li, Zihao Zhu, and Shaokui Wei.

Best Publications

  • Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

    Zechun Liu;Baoyuan Wu;Wenhan Luo;Xin Yang

  • Backdoor Learning: A Survey

    Yiming Li;Baoyuan Wu;Yong Jiang;Zhifeng Li

  • Learning to Compose Dynamic Tree Structures for Visual Contexts

    Kaihua Tang;Hanwang Zhang;Baoyuan Wu;Wenhan Luo

  • The Seventh Visual Object Tracking VOT2019 Challenge Results

    Matej Kristan;Amanda Berg;Linyu Zheng;Litu Rout

  • Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition

    Yinpeng Dong;Hang Su;Baoyuan Wu;Zhifeng Li

  • Target-Aware Deep Tracking

    Xin Li;Chao Ma;Baoyuan Wu;Zhenyu He

  • TediGAN: Text-Guided Diverse Face Image Generation and Manipulation

    Weihao Xia;Yujiu Yang;Jing-Hao Xue;Baoyuan Wu

  • CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF

    Linchao Bao;Baoyuan Wu;Wei Liu

  • Constrained Clustering and Its Application to Face Clustering in Videos

    Baoyuan Wu;Yifan Zhang;Bao-Gang Hu;Qiang Ji

  • DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks

    Unknown

  • StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

    Unknown

  • LAS-AT: Adversarial Training with Learnable Attack Strategy

    Unknown

  • Multi-label learning with missing labels for image annotation and facial action unit recognition

    Baoyuan Wu;Siwei Lyu;Bao-Gang Hu;Qiang Ji

  • $ll _p$ ℓ p -Box ADMM: A Versatile Framework for Integer Programming

    Baoyuan Wu;Bernard Ghanem

  • Residual Regression With Semantic Prior for Crowd Counting

    Jia Wan;Wenhan Luo;Baoyuan Wu;Antoni B. Chan

  • ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph

    Baoyuan Wu;Siwei Lyu;Bernard Ghanem

  • Compressing Convolutional Neural Networks via Factorized Convolutional Filters

    Tuanhui Li;Baoyuan Wu;Yujiu Yang;Yanbo Fan

  • Multi-label Learning with Missing Labels

    Baoyuan Wu;Zhilei Liu;Shangfei Wang;Bao-Gang Hu

  • Rethinking the Trigger of Backdoor Attack

    Yiming Li;Tongqing Zhai;Baoyuan Wu;Yong Jiang

  • Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

    Zechun Liu;Wenhan Luo;Baoyuan Wu;Xin Yang

  • Multi-label Learning with Missing Labels Using Mixed Dependency Graphs

    Baoyuan Wu;Fan Jia;Wei Liu;Bernard Ghanem

  • Simultaneous Clustering and Tracklet Linking for Multi-face Tracking in Videos

    Baoyuan Wu;Siwei Lyu;Bao-Gang Hu;Qiang Ji

  • Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning

    Baoyuan Wu;Weidong Chen;Yanbo Fan;Yong Zhang

  • Sparse Adversarial Attack via Perturbation Factorization

    Yanbo Fan;Baoyuan Wu;Tuanhui Li;Yong Zhang

Frequent Co-Authors

Wei Liu
Wei Liu Tencent (China)
Zhifeng Li
Zhifeng Li Tencent (China)
Bernard Ghanem
Bernard Ghanem King Abdullah University of Science and Technology
Siwei Lyu
Siwei Lyu University at Buffalo, State University of New York
Qiang Ji
Qiang Ji Rensselaer Polytechnic Institute
Bao-Gang Hu
Bao-Gang Hu Chinese Academy of Sciences
Yong Zhang
Yong Zhang Chinese Academy of Sciences
Xiaopeng Zhang
Xiaopeng Zhang Chinese Academy of Sciences
Fumin Shen
Fumin Shen University of Electronic Science and Technology of China
Kwang-Ting Cheng
Kwang-Ting Cheng Hong Kong University of Science and Technology

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Beyond Computer Science, several online degrees and certifications can open doors to lucrative careers and further specialization. For those interested in technical fields, the best online electrical engineering programs USA offer flexible learning options and outstanding job prospects in various industries.

If you’re looking for a quicker route to a high-paying career, consider 3-month certificate programs that pay well. These short-term certifications can help you acquire in-demand skills and boost your resume without a long-term commitment.

For those aiming to advance their education rapidly, the shortest masters degree programs allow you to earn your graduate credentials in the least amount of time, helping you fast-track your professional goals.

Finally, exploring the most in demand masters degrees can guide you toward qualifications that are highly valued by employers, ensuring your future career stays on track in a competitive market.

Best Scientists Citing Baoyuan Wu

Trending Scientists

Recently Published Articles