Hi, I am Zhiheng Fu (付志恒).
I’m currently an Undergrad student in the School of Software, Shandong University, under the supervision of Prof. Liqiang Nie and Prof. Yupeng Hu. My research interests include multimedia computing, information retrieval.
🤗 All the major projects I involved in have been open-sourced. We invite you to explore our projects, share your feedback, and connect with us for further discussion.
🏫 And I am a member of the Intelligent Media Research Center (iLearn), all the lab projects are open-source. Please visit iLearn Lab and feel free to share your valuable feedback.
Projects
Here’s the link to our repo! Feel free to check it out. Any feedback or support are always welcome. Thanks for taking a look! ✨
 TEMA (ACL'26 Main) Paper | Web | Code |  ConeSep (CVPR'26) Paper | Web | Code |  Air-Know (CVPR'26) Paper | Web | Code |
 HABIT (AAAI'26) Paper | Web | Code |  ReTrack (AAAI'26) Paper | Web | Code |  INTENT (AAAI'26) Paper | Web | Code |
 HUD (ACM MM'25) Web | Code | Paper |  OFFSET (ACM MM'25) Web | Code | Paper |  ENCODER (AAAI'25) Web | Code | Paper |
🔥 News
- 2026.05.14: 🎉🎉 Thrilled to share that our team won two 1st places🏅, two 2nd places🥈, and one 3rd place🥉 across multiple CVPR 2026 Challenges (HD-EPIC, EPIC-KITCHENS, and EgoCross)! Congratulations to all members!
- 2026.04.07: 🎉🎉 One paper (TEMA), was accepted by ACL 2026! Thanks to all co-authors!
- 2026.03.17: 🎉🎉 One paper (STABLE), was accepted by TKDE 2026! Congratulations to all co-authors!
- 2026.02.21: 🎉🎉 Two papers (ConeSep, Air-Know), were accepted by CVPR 2026! Thanks and Congratulations to all co-authors!
- 2025.11.08: 🎉🎉 Three papers were accepted by AAAI 2026! Thanks and Congratulations to all co-authors!
- 2025.10.18: 🎉🎉 As the core member, our team wins the Grand Prize in the CICAS Smart Power Scenario Competition. Congratulations to all team members!
- 2025.07.05: 🎉🎉 Two papers have been accepted by ACM MM 2025! Congratulations to our co-authors!
- 2024.12.10: 🎉🎉 One paper has been accepted by AAAI 2025! Congratulations to our co-authors!
# 📝 Publications
TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval [Paper] [Web] [Code]
Zixu Li, Yupeng Hu✉, Zhiheng Fu, Zhiwei Chen, Yongqi Li, Liqiang Nie
Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval [Paper] [Web] [Code]
Zhiheng Fu, Yupeng Hu, Qianyun Yang, Shiqi Zhang, Zhiwei Chen, Zixu Li
ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval [Paper] [Web] [Code]
Zixu Li, Yupeng Hu, Zhiwei Chen, Mingyu Zhang, Zhiheng Fu, Liqiang Nie
INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval [Paper] [Web] [Code]
Zhiwei Chen, Yupeng Hu, Zhiheng Fu, Zixu Li, Jiale Huang, Qinlei Huang, Yinwei Wei
FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval [PDF] [Web] [Code]
Zixu Li, Zhiheng Fu, Yupeng Hu, Zhiwei Chen, Haokun Wen, Liqiang Nie
ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval [PDF] [Web] [Code]
Zixu Li, Zhiwei Chen, Haokun Wen, Zhiheng Fu, Yupeng Hu, Weili Guan
📝 Challenge Technical Report
(“†” denotes project leader, “✉” denotes corresponding author)
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge [Coming Soon]
Zixu Li, Yupeng Hu, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Weili Guan, Liqiang Nie
EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge [Coming Soon]
Zhiwei Chen, Yupeng Hu, Zixu Li†, Zhiheng Fu, Guozhi Qiu, Weili Guan, Liqiang Nie
OmniEgo-R2: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026 [Coming Soon]
Zixu Li, Zhiwei Chen, Zhiheng Fu, Wenbo Wang, Yupeng Hu, Weili Guan, Liqiang Nie
EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026 [Coming Soon]
Zhiheng Fu, Zixu Li†, Zhiwei Chen, Fangxu Liu, Yupeng Hu, Weili Guan, Liqiang Nie
🔖 Patent
- 基于实体挖掘和修改关系绑定的组合图像检索方法及系统 - 公开号: CN120067365A - [详情]
- 基于自适应中间粒度聚合网络的组合图像检索方法及系统 - 公开号: CN120104822A - [详情]
- 一种基于分割焦点偏移修正的组合图像检索方法及系统 - 公开号: CN120144812A - [详情]
- 基于互补性引导解耦的组合图像检索方法及系统 - 公开号: CN120144811A - [详情]
🏆 Honors and Awards
- 2025.10, National Scholarship (国家奖学金).
- 2025.10, Grand Prize in the CICAS Smart Power Scenario Competition.
🏆 Competition
- 1st place 🏅, CVPR HD-EPIC VQA Challenge, 2026. [Link]
- 1st place 🏅, CVPR EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge, 2026. [Link]
- 2nd place 🥈, CVPR EgoCross (Source-Limited Track): Cross Domain Ego-centric VQA Challenge, 2026. [Link]
- 2nd place 🥈, CVPR EgoCross (Open-Source Track): Cross Domain Ego-centric VQA Challenge, 2026. [Link]
- 3rd place 🥉, CVPR EPIC-KITCHENS-100 Action Detection Challenge, 2026. [Link]
📖 Educations
- 2022.09 - Present, Undergrad in the School of Software, Shandong University.
📃 Services
- Conference PC Member: AAAI