Name：Fan Qi
Title：Professor
Type of tutor：Doctoral supervisor, master's supervisor
Email：fanqi@email.tjut.edu.cn
Address：1-305
Telephone：022-60216906
I am currently a professor and doctoral supervisor at School of Computer Science and Engineering, Tianjin University of Technology, P. R. China. In 2016，I graduated from Beijing Jiaotong University with a bachelor degree. In 2021, I received a Ph.D. from Hefei University of Technology. I has authored more than 30+ CCF-A papers in international conferences and journals including CVPR,ICML,WWW,ACM MM,T-PAMI, TIP, TMM, TNNLS, TCSVT, etc. My research interests include multimedia, computer vision, and machine learning.
Multimodal Computing
AI Security
1. “Research on Key Technologies of Multimodal Federated Intelligent Collaborative Optimization”, National Natural Science Foundation of China (PI) ，2026.01-2029.12
2. “Research on the Theory and Method of Generating Genuine and Natural Long Videos Empowered by Emotions”, Key Subproject of the National Natural Science Foundation of China (PI) ,2026.01-2030.12
3. “Integration and processing components of multi-source heterogeneous artificial intelligence models”, External Cooperation Project of a Certain Model Program (PI) , 2024.09-2025.09
4. “Video sentiment diversification Analysis for Privacy Protection”, National Natural Science Foundation of China (PI) ,2023.01-2025.12
5. “Federated affective computing for non-independent and uniformly distributed data”, Natural Science Foundation of Tianjin Municipality (PI) ,2022.10-2024.09
6. “Key technologies for big data multimodal interactive collaboration”, National Key Research and Development Program of China (Participant)
7. “Personalized health management based on real-Time behavioral data”, NSFC International (Regional) Cooperation and Exchange Program (Participant)
[1] Fan Qi, Daxu Shi , Chuokun Xu , Shuai Li , Changsheng Xu. Rethinking the Temperature for Federated Heterogeneous Distillation. ICML 2025. (CCF-A)
[2] Fan Qi*, Kunsheng Ma, Changsheng Xu. Customized Condition Controllable Generation for Video Soundtrack. CVPR 2025. (CCF-A)
[3] Fan Qi, Ao Liu, Zixin Zhang, Changsheng Xu. FORGET ME: Federated Unlearning for Face Generation Models. MM 2025. (CCF-A)
[4] Kunsheng Ma, Fan Qi*, Changsheng Xu. Granular Music Attribute Transformation with Proximal Policy Optimization Adapters for Diffusion Model. MM 2025. (CCF-A)
[5] Fan Qi, Zhan Wang, Changsheng Xu, Huaiwen Zhang. Fine-tuning Bias Neurons for Fair Text-to-Image Generation. MM 2025. (CCF-A)
[6] Zixin Zhang, Fan Qi*, Changsheng Xu. Knowledge-guided Label Distribution Calibration for Federated Affective Computing. TNNLS 2025. (JCR-1)
[7] Huaiwen Zhang, Yang Yang, Fan Qi *, Qian Shengsheng, Xu Changsheng. Active Supervised Cross-Modal Retrieval. TPAMI 2025. (JCR-1 TOP/CCF-A)
[8] Zixin Zhang, Fan Qi *, Changsheng Xu. Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models. ICML 2024. (CCF-A)
[9] Fan Qi * , Shuai Li. Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning. CVPR 2024. (CCF-A)
[10] Fan Qi , Ruijie Pan , Huaiwen Zhang, Changsheng Xu. Fedvad: Enhancing federated video anomaly detection with gpt-driven semantic distillation. ECCV 2024. (CAAI-A)
[11] Fan Qi, Yu Duan, Huaiwen Zhang, Changsheng Xu. SignGen: End-to-End Sign Language Video Generation with Latent Diffusion. ECCV 2024. (CAAI-A)
[12] Fan Qi, Huaiwen Zhang, Xiaoshan Yang, Changsheng Xu. A Versatile Multimodal Learning Framework For Zero-shot Emotion Recognition. TCSVT 2024. (JCR-1)
[13] Li Shuai, Fan Qi *, Zixin Zhang, Changsheng Xu. Cross-Modal Meta Consensus for Heterogeneous Federated Learning. ACM MM 2024. (CCF-A)
[14] Fan Qi, Zixin Zhang, Xiaoshan Yang, Changsheng Xu. Feeling Without Sharing: A Federated Video Emotion Recognition Framework Via Privacy-Agnostic Hybrid Aggregation. ACM MM 2022.（CCF-A）
[15] Fan Qi, Xiaoshan Yang, Changsheng Xu. Zero-shot video emotion recognition via multimodal protagonist-aware transformer network. ACM MM 2021.（CCF-A）
[16] Fan Qi, Xiaoshan Yang, Changsheng Xu. Emotion knowledge driven video highlight detection[J]. TMM 2020. (JCR-1)
[17] Fan Qi, Xiaoshan Yang, Changsheng Xu. A unified framework for multimodal domain adaptation. MM 2018. (CCF-A）
Cryptography (Undergraduate)
Intrusion Detection Technology (Undergraduate)
Machine Vision (Graduate)
Reviewer for TIP, TIFS, TDSC, TMM,, TNNLS, TCSVT, TOMM, CVPR, ACM MM, ICML, ICLR, WWW, and AAAI etc.
2025–Present, Academic Committee (AC) Member, CCF YOCSEF Tianjin.
2025–Present, Vice Principal for Science (Adjunct), Tianjin No.11 High School.
