Biography

šŸ‘€ Mengnan, Zhao received his Ms. degree under the supervision of Prof. Bo Wang in 2021. He is pursuing his Ph.D degree under the supervision of Prof. Baocai Yin, Prof. Lihe Zhang and Dr. Yuqiu Kong. The current research of him focuses on AI security and computer vision, specifically on machine unlearn, adversarial attack and defense, biased/unbiased scene graph generation, 3D scene understanding, and knowledge graph reasoning.

šŸ‘‹ Hi, Iā€™m zmn (CV). Feel free to contact me by Email or WeChat(15822843520).

šŸ™ 2024Lucky -> ME <- 2024Lucky šŸ™ Negative examples: AAAI2024 Rej-(wa,wa,wa,wr); CVPR2024 Rej-(wa,wa,wr).

šŸ’žļø News.

TOP [C]/[J]: ICCV, ECCV, TIFS, TCSVT, PR

  • [July 2024] 1 paper is accepted by ECCV.
  • [Jan 2024] 1 paper is accepted by IEEE TIFS.
  • [Dec 2023] 1 paper is accepted by PR.
  • [Oct 2023] 1 paper is accepted by Applied Intelligence.
  • [Oct 2023] 1 paper is accepted by ICCV.
  • [Sep 2023] 1 paper is accepted by Neurocomputing.
  • [Jul 2022] 1 paper is accepted by ICAIS.
  • [Jun 2022] 1 paper is accepted by IEEE TIFS.
  • [Dec 2020] 1 paper is accepted by IEEE TCSVT.
  • [Aug 2020] 1 paper is accepted by IEEE TCSVT.
  • [Dec 2019] 1 paper is accepted by IEEE Access (Direct Accept. Before Warning).

šŸ“ 1st Author Papers.

  • Catastrophic Overfitting: A Potential Blessing in Disguise [link].
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, & Baocai Yin. (2024).
    European Conference on Computer Vision.
  • Adversarial Attacks on Scene Graph Generation [link] [code].
    Mengnan Zhao, Lihe Zhang, Wei Wang, Yuqiu Kong, & Baocai Yin. (2024).
    IEEE Transactions on Information Forensics and Security.
  • Class Correlation Correction for Unbised Scene Graph Generation [link] [code].
    Mengnan Zhao, Yuqiu Kong, Lihe Zhang, & Baocai Yin. (2023).
    Pattern Recognition, 1-16.
  • Temporal Knowledge Graph Reasoning Triggered by Memories [link] [code].
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, & Baocai Yin. (2023). Applied Intelligence, 1-16.
  • Fast adversarial training with smooth convergence [link] [code].
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, & Baocai Yin. (2023).
    IEEE/CVF International Conference on Computer Vision (pp. 4720-4729).
  • Protecting by Attacking: A Personal Information Protecting Method with Cross-Modal Adversarial Examples [link] [code].
    Mengnan Zhao, Bo Wang, Weikuo Guo, Wei Wang. (2023).
    Neurocomputing, 551, 126481.
  • Further Understanding Towards Sparsity Adversarial Attacks [link] [code].
    Mengnan Zhao, Xiaorui Dai, Bo Wang, Fei Yu, & Fei Wei. (2022).
    International Conference on Artificial Intelligence and Security (pp. 200-212).
  • Guided erasable adversarial attack (GEAA) toward shared data protection [link] [code].
    Mengnan Zhao, Bo Wang, Wei Wang, Tianhang Zheng, & Kui Ren. (2022).
    IEEE Transactions on Information Forensics and Security, 17, 2468-2482.
  • Adversarial analysis for source camera identification [link] [code].
    Bo Wang (Ms. Tutor), Mengnan Zhao, Wei Wang, Xiaorui Dai, Yi Li & Yanqing Guo. (2021).
    IEEE Transactions on Circuits and Systems for Video Technology, 31(11), 4174-4186.
  • Are You Confident That You Have Successfully Generated Adversarial Examples [link].
    Bo Wang (Ms. Tutor), Mengnan Zhao, Wei Wang, Fei Wei, Zhan Qin & Kui Ren. (2020).
    IEEE Transactions on Circuits and Systems for Video Technology, 31(6), 2089-2099.
  • Source Camera Identification Based on Coupling Coding and Adaptive Filter [link] [code].
    Mengnan Zhao, Bo Wang, Fei Wei, Meineng Zhu & Xue Sui. (2019).
    IEEE Access, Direct accept, 8, 54431-54440.

šŸ“« Patents.

  • A Reasonable Adv Analysis Method for Source Camera Recognition [link].
    CN112381149A
    Mengnan Zhao, Bo Wang
  • An Source Identification Method Based on Adaptive Filtering and Coupled Encoding [link].
    ZL201910871685.X; CN110659679
    Mengnan Zhao, Bo Wang
  • A Point Attack Method Based on Weighted Spectrum Generation of Adv Samples [link].
    ZL201911050075.X; CN110866287B
    Mengnan Zhao, Bo Wang
  • A Defense Method Based on Deceptive Attackers to Adv Samples [link].
    ZL201911050099.5; CN110852363B
    Bo Wang (Ms. Tutor), Mengnan Zhao
  • A Targeted Adv Poisoning Attack Method for Shared Data Protection [link]
    CN113821770A
    Mengnan Zhao, Bo Wang

šŸŒ± Professional Service.

Reviewer for:

  • ACM Multimedia, CCF-A [link]
  • IEEE Transactions on Neural Networks and Learning Systems, SCI1-Top [link]
  • IEEE Transactions on Multimedia, SCI1-Top [link]
  • IEEE Transactions on Circuits and Systems for Video Technology, SCI1-Top [link]
  • European Conference on Computer Vision, CV Top-conf [link]
  • IEEE Transactions on Network Science and Engineering, SCI1 & SCI2 [link]
  • Journal of King Saud University-Computer and Information Sciences SCI2 [link]
  • International Journal of Machine Learning and Cybernetics, SCI3 [link].

šŸ’» Internships.

  • Institute of Automation, Chinese Academy of Sciences. w. Prof. Wei Wang.

šŸ“ Peer Review.

  • EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation [link].
    to IEEE Transactions on Neural Networks and Learning Systems
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, & Baocai Yin. (2024).
  • Separable Multi-Concept Erasure from Diffusion Models [link].
    to International Conference on Machine Learning
    Mengnan Zhao, Lihe Zhang, Tianhang Zheng, Yuqiu Kong, & Baocai Yin. (2024).