avatar

Mo Zhou

Ph.D. Student
Johns Hopkins University
mzhou32 (at) jhu.edu


About Me

I am currently a third-year Ph.D. student in the Electrical and Computer Engineering Dept at Johns Hopkins University. I am advised by Prof. Vishal M. Patel.

Prior to this, I graduated from Xidian University with a Bachelor’s and Master’s degree, and was advised by Prof. Zhenxing Niu. I have worked as a research intern with Dr. Saeed Amizadeh and Dr. Kazuhito Koishida at Microsoft Research; as a research intern with Dr. Yiding Yang, Dr. Haoxiang Li, and Dr. Gang Hua at Wormpex AI Research; as a research assistant with Prof. Le Wang and Prof. Sanping Zhou at Xi’an Jiaotong University.

My research interest lies in computer vision and machine learning, especially securing deep neural network performance under distribution shifts.

I’ve been an official Debian GNU/Linux developer since 2018.

Research Interests

News

Publications

  1. TPAMI
    Adversarial Attack and Defense in Deep Ranking
    Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Nanning Zheng, Gang Hua
    Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024.
    PDF arXiv Code
  2. NeurIPS
    Resource-Adaptive Federated Learning with All-In-One Neural Composition
    Yiqun Mei, Pengfei Guo, Mo Zhou, Vishal M. Patel
    Advances in Neural Information Processing Systems (NeurIPS), 2022.
    PDF Github
  3. CVPR
    Enhancing Adversarial Robustness for Deep Metric Learning
    Mo Zhou, Vishal M. Patel
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
    PDF arXiv Code
  4. T-MM
    Adaptive Ladder Loss for Learning Coherent Visual-Semantic Embedding
    Le Wang, Mo Zhou, Zhenxing Niu, Qilin Zhang, Nanning Zheng
    IEEE Transactions on Multimedia (T-MM), 2021.
    PDF
  5. ICCV
    Practical Relative Order Attack in Deep Ranking
    Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Yinghui Xu, Nanning Zheng, Gang Hua
    IEEE International Conference on Computer Vision (ICCV), 2021.
    PDF arXiv Code
  6. CVPR
    SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
    Liushuai Shi, Le Wang, Chengjiang Long, Sanping Zhou, Mo Zhou, Zhenxing Niu, Gang Hua
    IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.
    PDF arXiv Code
  7. ECCV
    Adversarial Ranking Attack and Defense
    Mo Zhou, Zhenxing Niu, Le Wang, Qilin Zhang, Gang Hua
    European Conference on Computer Vision (ECCV), 2020.
    PDF arXiv Code
  8. AAAI
    Ladder Loss for Coherent Visual-Semantic Embedding
    Mo Zhou, Zhenxing Niu, Le Wang, Zhanning Gao, Qilin Zhang, Gang Hua
    AAAI Conference on Artificial Intelligence (AAAI), 2020.
    PDF arXiv Code
  9. ICCV
    Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding
    Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua
    IEEE International Conference on Computer Vision (ICCV), 2017.
    PDF
  10. CVPR
    Ordinal Regression with Multiple Output CNN for Age Estimation
    Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua
    IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.
    PDF

Preprints

  1. arXiv
    Deployment Prior Injection for Run-time Calibratable Object Detection
    Mo Zhou, Yiding Yang, Haoxiang Li, Vishal M. Patel, Gang Hua
    arXiv (preprint), 2024.
    arXiv
  2. arXiv
    MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
    Yatong Bai, Mo Zhou, Vishal M. Patel, Somayeh Sojoudi
    arXiv (preprint), 2024.
    arXiv
  3. arXiv
    T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalities
    Kangfu Mei, Mo Zhou, Vishal M. Patel
    arXiv (preprint), 2023.
    arXiv
  4. arXiv
    On Trace of PGD-Like Adversarial Attacks
    Mo Zhou, Vishal M. Patel
    arXiv (preprint), 2022.
    arXiv
  5. arXiv
    Securing Deep Generative Models with Universal Adversarial Signature
    Yu Zeng, Mo Zhou, Yuan Xue, Vishal M. Patel
    arXiv (preprint), 2023.
    arXiv

Services

Conference Reviewers

Journal Reviewers

Workshop Organizer


Powered by Jekyll and Minimal Light theme.