⛹️‍♂️Ji-Zhe ZHOU or Kat-Chit CHOW (周吉喆)🏊‍♂️, Tenure Associate Professor at the School of Computer Science, Sichuan University. I obtained my B.Sc., M.Sc., and Ph.D. (early graduation) from the University of Macau and was a student research assistant at CUHK. My primary research areas are the self-supervised learning theories and multimedia content security. I am the leader and supervisor of multiple influential works, including IML-ViT, IMDL-BenCo, SparseViT, and ForensicHub. My GitHub project repo received a total stars and my publication recieved a total citations.

周吉喆，四川大学副教授，TETCI副主编，四川省千人，四川省人工智能学院教师，主要研究内容生成与反生成方向，长期招收Self-supervised Learning/Content Security/3D Vision方向solid background and self-motivated的硕博与本科生（限川大），组内各研究方向和学生就业去向详见底部Supervised Students部分，欢迎联系邮件 jzzhou@scu.edu.cn 。
招收26秋的软件工程专业留学生硕士一名，欢迎联系。
1 quota for 26 fall international M.Sc student majoring in Software Engineering (accepting applications by 30th April, 2026).

🔥 News

• 2026.02 Publication: 🎉🎉SICA, we present the first FIDL model—SICA, which adopts a monolithic architecture and outperforms all domain-specific models in their respective domains (e.g., higher deepfake detection accuracy than Effort, higher IML accuracy than SparseViT, etc.). SICA achieves the best-ever performance for practical image forensics tasks. Supported by our co-authors, a public trial version of SICA, developed by Ant Group, will be made publicly available very soon.
• 2026.01 A&S Service: 🎉🎉Promoted as the Associate Editor for TETCI—IEEE Transactions on Emerging Topics in Computational Intelligence.
• 2026.01 A&S Service: Appointed as the Program Committee Member for MM 2026.
• 2026.01 Publication:  [TMM]🎉🎉PASK, our work on the sparse learning for adversarial example crafting is accepted to IEEE Transactions on Multimedia.
• 2026.01 A&S Service: Appointed as the Program Committee Member for ICML 2026.
• 2026.01 A&S Service: Appointed as the Program Committee Member for ECCV 2026.
• 2025.12 Publication:  [AAAI 2026]🎉🎉 FGM-HD, we introduce the classic Hausdorff Dimension into Fractal Generation Model, and the code will be available!
• 2025.11 Publication:  [TDSC]🎉🎉Defensive Adversarial CAPTCHA, our work on the semantics-driven framework for natural adversarial example generation is accepted to IEEE Transactions on Dependable and Secure Computing.
• 2025.10 Publication:  [TDSC]🎉🎉IO-RAE, our work on adversarial privacy is accepted to IEEE Transactions on Dependable and Secure Computing.
• 2025.09 A&S Service: Appointed as the Program Committee Member for ICLR 2026.
• 2025.07 A&S Service: Appointed as the Program Committee Member for AAAI 2026.
• 2025.05 Publication:  [NeurIPS 2025]🎉🎉ForensicsHub, we propose a new task termed “FIDL”, Fake Image Detection and Localization, unifying the 4 major subdomains of image forensics (IML, AIGC detection, DeepFake Detection, DocumentTamper Detection) into this single FIDL task.
• 2025.04 A&S Service: Appointed as the Program Committee Member for NeurIPS 2025.
• 2025.03 A&S Service: Appointed as the Program Committee Member for MM 2025.
• 2025.03 Publication:  [CVPR 2025]🎉🎉 Style Quantization for Data-Efficient GAN Training, our new quantization method for general GAN training is accepted by CVPR 2025!
• 2025.01 A&S Service: Appointed as the Editorial Board Member for Applied Energy
• 2024.12 A&S Service: Appointed as the Associate Editor for 《四川大学学报》&《计算机应用》.
• 2024.12 A&S Service: Appointed as the Program Committee Member for ICML25.
• 2024.12 Publication:  [AAAI 2025]🎉🎉 Mesorch, our new IML backbone model, which adopts a parallel CNN+Transformer structure to simultaneously deal with image semantics and non-semantics, is accepted by AAAI25!
• 2024.12 Publication:  [AAAI 2025]🎉🎉 Sparse-ViT, the very first solution of constructing the non-semantic feature extractor through a self-supervised manner in IML is proposed by us and accepted by AAAI 25!
• 2024.11 Competition:  🎉🎉 We won the
  —2nd Price in Alibaba Tianchi, Global AI Attack & Defense Challenge-Track 1: Safety vaccine injection for large model generated images (阿里天池全球AI攻防挑战赛-赛道一：大模型生图安全疫苗注入), meaning 2/1574.
  —9th Price in Alibaba Tianchi, Global AI Attack & Defense Challenge-Track 2: Financial certificate manipulation detection (阿里天池全球AI攻防挑战赛-赛道二：AI核身之金融场景凭证篡改检测), meaning 9/1162 .
  —Check My Exclusive Interview from Coverpage NEWS (封面新闻个人专访) and the Team Interview from SINA (新浪现场采访).
• 2024.10 A&S Service: Appointed as the Program Committee Member for CVPR25.
• 2024.09 Publication:  [NeurIPS 2024, Spotlight]🎉🎉 Our comprehensive benchmark and modular codebase on IML (addressing the model evaluation), IMDL-BenCo, is now fully released and under long-term maintenance and construction!
• 2024.09 A&S Service: Appointed as the Program Committee Member for ICLR25.
• 2024.09 Competition:  🎉🎉 We won the 1st Price in Tecent AI Arena Competition (腾讯开悟比赛多智能体博弈赛道), meaning 1/2000+ . Both of our teams are advanced to the grand finals, check Award List for details.
• 2024.07 Publication:  [MM 2024, Oral]🎉🎉 We raise the generative contrastive approach to address the person identification through chest bones, details are in Neural Boneprint.
• 2024.07 Publication:  [MM 2024, Oral]🎉🎉 We propose to revise the inaccuracies while restoring images through Diffusion models, details are in DPPS.
• 2024.06 A&S Service: Appointed as the Program Committee Member for AAAI25.
• 2024.06 Publication:  🎉🎉 Our latest framework and benchmark model on private object detection, PrivacyGuard, is now online; the code and training dataset will soon be available!
• 2024.04 A&S Service: Appointed as the Program Committee Member for NIPS24.
• 2024.01 A&S Service: Appointed as the Program Committee Member for MM24.
• 2023.12 Publication:  🎉🎉 Our latest benchmark model on IML, IML-ViT, is now fully outsourced!

📝 Selected Publications

Image Generation

• TIFS Personal privacy protection via irrelevant faces tracking and pixelation in video live streaming, Jizhe Zhou, Chi-Man Pun.
• ACM MM 2020 Privacy-sensitive objects pixelation for live video streaming, Jizhe Zhou, Chi-Man Pun, Yu Tong.
• TNNLS Shunting at Arbitrary Feature Levels via Spatial Disentanglement: Toward Selective Image Translation, Jian Wang, Xue Yang, Yuxin Tian, Jizhe Zhou, Jiancheng Lv.

Anti-Generation

• ICCV 2023 (oral) Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning, Jizhe Zhou, Xiaochen Ma, Xia Du, Ahmed Y Alhammadi, Wentao Feng,
• To Appear IML-ViT: Image Manipulation Localization by Vision Transformer. Xiaochen Ma, Bo Du, Zhuohang Jiang, Ahmed Y. Al Hammadi, Jizhe Zhou,
• ACM MM 2023 (oral) M2ATS: A Real-world Multimodal Air Traffic Situation Benchmark Dataset and Beyond, Dongyue Guo, Yi Lin, Zheng Zhang, Jizhe Zhou.

Reasoning under DNN

• ACL 2022 Word Segmentation by Separation Inference for East Asian Languages, Yu Tong, Jingzhi Guo, Jizhe Zhou, Ge Chen, Guokai Zheng.
• IJCAI 2022 Abstract rule learning for paraphrase generation, Xianggen Liu, Wenqiang Lei, Jiancheng Lv, Jizhe Zhou.
• TASLP Separation inference: A unified framework for word segmentation in east Asian languages, Yu Tong, Jingzhi Guo, Jizhe Zhou.
• TASLP Towards Recognition for Radio-echo Speech in Air Traffic Control: Dataset and a Contrastive Learning Approach. Yi Lin, Qingyang Wang, Xincheng Yu, Zichen Zhang, Dongyue Guo, Jizhe Zhou.

📖 Educations

• 2013, Bsc., Software Engineering, FST, University of Macau, Macau SAR.
• 2018, Msc., Software Engineering, FST, University of Macau, Macau SAR.
• 2021, Ph.D., Computer and Information Science, FST, University of Macau, Macau SAR.
• 2016 - 2018, Student Research Assistant, CSE, Chinese University of Hong Kong, Hong Kong SAR.
• 2019 - 2020, Student Research Assistant, Kakao Track, Yonsei University, Korean.

💬 Invited Talks

“A Song of Ice and Fire: Image Tampering Techniques in the Age of Large Generative Models”, PRML 2023, Urumqi, China.
“如何为直播中的人脸自动打码”, Academic Salon (a.k.a Job Talk), Sichuan Unviersity 2021.
“Multi-Object Online-Tracking”, University ML Camp (UMLC2019), Jeju, Korean.

📝 Academic Services

• SPC: IJCAI 2025
• Publicity Chair: CSAI 2023
• Technical Program Committee: PRML 2023
• Program Committee: CVPR 24-26, ICML 24-26, AAAI 2021 & 2022, WWW 2021, ICLR 2022, ACM MM 2021 & 2022 & 2023, TCSVT, TIP, TMM, TNNLS, etc..

📝 Supervised Students (2022-now)

• Graduated Students

  1. Xiaochen Ma 马晓晨, [Now Ph.D student in HKUST 港科大直博] (IML)
  2. Yu Tong 佟禹, [Now Lecturer, College of Engineering, Shantou University 汕头大学讲师] (LLM Inference)
  3. Xinyu Yang 杨欣宇, [Now Ph.D student in Tsinghua University 清华直博] (Data Synthesis for IML)
  4. Jian Zhang 张健, [Now working at Contemporary Amperex Technology Co. Limited. 宁德时代] (Defect Detection)
  5. Ruiyang Ni 倪瑞洋, [Now working at CETC Zhengzhou 中电科] (Graph Inference)
  6. Pengsen Liu 刘鹏森,[Now Ph.D Student in Lambda Lab, Nanjing University 南大博] (Game AI)
  7. Bingkui Tong 童炳魁, [Now Ph.D student in MBZUAI, UAE 阿联酋MBZUAI直博] (Graph Inference)
  8. Zhuohang Jiang 蒋卓航, [Now Ph.D student in PolyU, HongKong 港理工直博], Sichuan University (Deblur)
  9. Zeyu Lei 雷泽宇, [Now master student at the University of Southern California 南加大硕] (Fine-grained Classification)

• Current Students

  1. Bo Du 杜博, Master Student in CS, Sichuan University [Intern at Ant Group 蚂蚁核身业务实习] (FID)
  2. Xuekang Zhu 朱学康, Master Student in CS, Sichuan University [Intern at Ant Group 蚂蚁核身业务实习] (IML)
  3. Xiwen Wang 王汐文, Ph.D. Candidate in CS, Sichuan University (Large 3D Models)
  4. Yusheng He 何雨声, Ph.D. Candidate in CS, Sichuan University (Multimodal Large Model)
  5. Chaoqun Niu 牛超群, Ph.D. Candidate in CS, Sichuan University [CSC-founded visiting at NUS 留基委公派NUS] (AIGI)
  6. Lei Su 粟磊, Master Student in CS, Sichuan University [Intern at Tencent Group 腾讯大模型业务实习] (Anti-AIGI)
  7. Haowei Zhang 张皓为, Master Student in CS, Sichuan University, [Intern at Tencent Group 腾讯大模型业务实习] (AIGI)
  8. Jian Wang 王坚, Ph.D. Candidate in CS, Sichuan University (AIGI)
  9. Mingxi Guo 郭明熹, Ph.D. Candidate in CIS, University of Macau (Anti-AIGI)