News

• 2026.06 🔥 Our Awesome Project for AIGC detection has received 400+ stars. Continuously updating.
• 2026.05 🎉 VideoVeritas was accepted by ICML 2026.
• 2026.05 🎉 SSPA was accepted by IEEE TCSVT.
• 2026.03 🏆 Won 1st place in NTIRE 2026 Robust AI-Generated Image Detection Challenge.
• 2026.02 🔥 Veritas was selected as ICLR 2026 Oral presentation.
• 2026.01 🎉 Veritas was accepted by ICLR 2026.
• 2025.03 🎉 RAM was accepted by CVPR 2025.
• 2025.01 🎉 One paper on pedestrian attribute recognition appeared in IEEE TMM.
• 2023.12 🎉 One paper was accepted by AAAI 2024.
• 2023.09 🏆 Won 1st place in the 4th CSIG Challenge on Pedestrian Attribute Recognition.
• 2023.01 🏆 Won 1st place in the Pedestrian Attribute Recognition Challenge at WACV 2023.

Education

• 2023 - 2028
  Ph.D. Student, MAIS, Institute of Automation, Chinese Academy of Sciences (CASIA) Computer Science and Technology. Advisor: Prof. Jun Wan and Prof. Zhen Lei
• 2019 - 2023
  B.E. in South China University of Technology (SCUT) GPA: 3.94 Rank: 2/82 School of Automation Science and Engineering Outstanding Graduate of South China University of Technology

Experience

Publications

Selected first-author publications and representative co-authored work.

VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning

Hao Tan, Jun Lan, Senyuan Shi, Zichang Tan, Zijian Yu, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei

International Conference on Machine Learning (ICML), 2026.

[Paper] [Code]

Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning

Hao Tan, Jun Lan, Zichang Tan, Senyuan Shi, Ajian Liu, Chuanbiao Song, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei

International Conference on Learning Representations (ICLR), Oral, 2026.

[Paper] [Code]

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

Hao Tan, Zichang Tan, Jun Li, Ajian Liu, Jun Wan, Zhen Lei

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

[Paper] [Code]

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

Hao Tan, Jun Li, Yizhuang Zhou, Jun Wan, Zhen Lei, Xiangyu Zhang

AAAI Conference on Artificial Intelligence (AAAI), 2024.

[Paper] [Code]

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

Hao Tan, Zichang Tan, Jun Li, Jun Wan, Zhen Lei, Stan Z. Li

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2026.

[Paper]

Vision Transformer with Relation Exploration for Pedestrian Attribute Recognition

Hao Tan, Zichang Tan, Dunfang Weng, Ajian Liu, Jun Wan, Zhen Lei, Stan Z. Li

IEEE Transactions on Multimedia (TMM), 2025.

[Paper]

HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection

Senyuan Shi*, Hao Tan*, Zichang Tan, Shuhan Feng, Ajian Liu, Sergio Escalera, Jun Wan

ACM MM 2026.

[Paper]

Awards

• National Scholarship for Ph.D. Students
• National Scholarship for Master's Students (before transferring to Ph.D.)
• National Scholarship for Undergraduate Students
• Annual Academic Figure, School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences
• Outstanding Graduate of South China University of Technology
• Merit Student, South China University of Technology
• Merit Student, University of Chinese Academy of Sciences
• Champion, Pedestrian Attribute Recognition and Attribute-based Person Retrieval Challenge at WACV 2023
• Champion, the 4th CSIG Image and Graphics Technology Challenge on Pedestrian Attribute Recognition