I am a Ph.D. Student at School of Computer Science & Engineering, South China University of Technology, supervised by Prof. Xuemiao Xu.

My research interests include privacy and security in computer vision and AIGC.

🔥 New

• 2025-09: Two paper were accepted by Conference on Neural Information Processing Systems, Neurips 2025.
• 2025-08: A paper was accepted by IEEE Transactions on Circuits and Systems for Video Technology, TCSVT 2025.
• 2025-07: A paper was accepted by Transactions on Pattern Analysis and Machine Intelligence, TPAMI 2025.
• 2025-06: A paper was accepted by International Conference on Computer Vision, ICCV 2025.
• 2025-03: A paper was accepted by IEEE Transactions on Information Forensics and Security (TIFS).

📝 Publications

      *: Equal contribution            #: Corresponding Authors

• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models. The Thirty-ninth Annual Conference on Neural Information Processing Systems (CCF-A, 人工智能顶会). Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu, Yuyang Yu, Zikai Huang, Yi Wang, Shengfeng He.
• Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection. The Thirty-ninth Annual Conference on Neural Information Processing Systems (CCF-A, 人工智能顶会). Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang, Haoxin Yang, Yongwei Nie, Shengfeng He.
• StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion. IEEE Transactions on Circuits and Systems for Video Technology (SCI 一区, 人工智能TOP Trans). Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He.
• GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving. IEEE Transactions on Pattern Analysis and Machine Intelligence(SCI 一区, 人工智能TOP Trans). Bangzhen Liu, Yuyang Yu, Xuemiao Xu, Cheng Xu, Chenxi Zheng, Haoxin Yang, Shaoyu Huang, and Shengfeng He,
• ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition. International Conference on Computer Vision, ICCV 2025 (CCF-A, 计算机视觉顶会). Ronggang Huang, Haoxin Yang*#, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He.
• SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation. IEEE Transactions on Information Forensics and Security (SCI 一区, 信息安全TOP Trans). Jingdan Kang, Haoxin Yang*, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He.
• SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation. IEEE International Conference on Multimedia& Expo, ICME 2025 (CCF-B 会议). Weihong Chen, Xuemiao Xu, Haoxin Yang#, Yi Xie, Peng Xiao, Cheng Xu, Huaidong Zhang, Pheng-Ann Heng.
• G²Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors. IEEE Transactions on Information Forensics and Security (SCI 一区, 信息安全TOP Trans). Haoxin Yang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Jing Qin, Yi Wang, Pheng-Ann Heng, Shengfeng He.
• Hierarchical damage correlations for old photo restoration. Information Fusion(SCI 一区). Weiwei Cai, Xuemiao Xu, Jiajia Xu, Huaidong Zhang, Haoxin Yang, Kun Zhang, Shengfeng He.
• Individual property inference over collaborative learning in deep feature space. IEEE International Conference on Multimedia& Expo, ICME 2022 (CCF-B 会议). Haoxin Yang; Yi Wang; Bin Li.

🧾 Patents

• 一种动态视觉智能售货柜商品检测追踪与后处理方法. CN118298356A. 徐雪妙;杨灏鑫;黄少遇;吴惊声;魏钦煜.
• 一种基于深度特征与梯度信息的数据重建方法及系统(已授权). CN202111524383.9. 杨灏鑫; 李斌; 王艺.
• 协同训练数据属性的推断方法、装置、设备及存储介质. CN114287009A(已授权). 王艺; 杨灏鑫; 李斌.

📕 Educations

• 2022.09 - Now   Ph.D Student   School of Computer Science & Engineering, South China University of Technology   Supervisor Prof. Xuemiao Xu.

• 2019.09 - 2022.06   Master   College of Electronics and Information Engineering, Shenzhen University   Supervisors Prof. Bin Li & Prof. Yi Wang.

• 2015.09 - 2019.06   Undergraduate   College of Electronic Engineering, South China Agricultural University

🛠️ Projects

• Intelligent Vision Vending Machine – Key technologies: YOLO obb detection and tracking, image retrieval.

The source code is forked from academicpages, thanks for the great work.