个人资料：
姓名：徐宁
职称：副教授/硕士生导师/博士生导师团
学科专业：信息与通信工程(一级学科)/信号与信息处理(二级学科)
通讯地址：天津大学电气自动化与信息工程学院26教学楼D区
电子信箱：ningxu@tju.edu.cn
个人主页：https://ningxu1990.github.io
主要经历：
(1) 2022.05-至今 天津大学电气自动化与信息工程学院，信息与通信工程，副教授
(2) 2019.07-2022.04 天津大学电气自动化与信息工程学院，信息与通信工程，讲师
(3) 2016.03-2017.03 新加坡国立大学，计算机学院，博士联合培养
(4) 2013.09-2019.06 天津大学电气自动化与信息工程学院，信息与通信工程，硕博连读
研究方向：
(1) 计算机视觉
(2) 大模型推理机制
(3) 多智能体协同推理
(4) 跨媒体内容理解与生成
主要科研项目：
(1) 2025.01-2028.12 国家自然科学基金面上项目，负责人
(2) 2021.01-2023.12 国家自然科学基金青年项目，负责人
(3) 2021.07-2023.06 中国博士后科学基金面上项目，负责人
(4) 2025.04-2027.03 天津市自然科学基金青年项目，天大负责人
(5) 2025.10-2028.09 南开大学眼科学研究院开放基金，负责人
(6) 2022.01-2025.12 国家自然科学基金联合重点项目，主要参与人
(7) 2020.11-2023.10 国家重点研发计划项目子课题，主要参与人
代表性论著、学术著作：
录用/发表学术论文50余篇，部分论文如下：
(1) Yifei Gao, Ning Xu*, Wenhui Li, Hongshuo Tian, Lanjun Wang, An-An Liu*: Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation Detection. ICLR 2026
(2) Ning Xu, Zimu Lu, Hongshuo Tian, Bolun Zheng, Jinbo Cao, An-An Liu*: MMToT: Multi-Modal Token-of-Thought Reasoning for Large Models. IEEE Trans. Multim. (10.1109/TMM.2026.3654463)
(3) Yingchen Zhai, Ning Xu*, Hongshuo Tian, Bolun Zheng, Chenggang Yan, Jinbo Cao, Rongbao Kang, An-An Liu*: Constituency-Tree-Induced Vision-Language Alignment for Multimodal Large Language Models. IEEE Trans. Circuits Syst. Video Technol. (10.1109/TCSVT.2025.3639574)
(4) Zimu Lu, Ning Xu*, Hongshuo Tian, Lanjun Wang, An-An Liu*: Medical VLP Model is Vulnerable: Towards Multimodal Adversarial Attack on Large Medical Vision-Language Models. IEEE Trans. Circuits Syst. Video Technol. (10.1109/TCSVT.2025.3602970)
(5) An-An Liu, Quanhan Wu, Ning Xu*, Hongshuo Tian, Lanjun Wang: Enriched Image Captioning based on Knowledge Divergence and Focus. IEEE Trans. Circuits Syst. Video Technol. 35(5): 4937-4948 (2025)
(6) Ning Xu, Xiaowen Wang, Jing Liu, Lanjun Wang, Xuanya Li, Mengxiao Zhu, Yongdong Zhang, An-An Liu*: Model can be subtle: Two important mechanisms for Social Media Popularity Prediction. ACM Trans. Multim. Comput. Commun. Appl. 21(2): 71:1-71:20 (2025)
(7) Ning Xu, Yifei Gao, Ting-Ting Zhang, Hongshuo Tian*, An-An Liu*: Cross-Modal Coherence-Enhanced Feedback Prompting for News Captioning. ACM Multimedia 2024: 9369-9377
(8) Ning Xu, Tingting Zhang, Hongshuo Tian, An-An Liu*: Rule-driven News Captioning. IEEE Trans. Circuits Syst. Video Techn. 34(11): 11657-11667 (2024)
(9) Hongshuo Tian, Ning Xu*, Mohan Kankanhalli, An-An Liu*: Gaussian Distribution-Aware Commonsense Knowledge Learning for Scene Graph Generation. IEEE Trans. Circuits Syst. Video Technol. 34(12): 13044-13057 (2024)
(10) Ning Xu, Yifei Gao, An-An Liu*, Hongshuo Tian, Yongdong Zhang: Multi-modal Validation and Domain Interaction Learning for Knowledge-based Visual Question Answering. IEEE Trans. Knowl. Data Eng. 36(11): 6628-6640 (2024)
(11) Ning Xu, Zimu Lu, Hongshuo Tian, Rongbao Kang, Jinbo Cao, Yongdong Zhang, An-An Liu*: Learning to Supervise Knowledge Retrieval over a Tree Structure for Visual Question Answering. IEEE Trans. Multim. 26: 6689-6700 (2024)
(12) An-An Liu, Yingchen Zhai, Ning Xu*, Hongshuo Tian, Weizhi Nie, Yongdong Zhang: Event-aware Retrospective Learning for Knowledge-based Image Captioning. IEEE Trans. Multim. 26: 4898-4911 (2024)
(13) An-An Liu, Chenxi Huang, Ning Xu*, Hongshuo Tian, Jing Liu, Yongdong Zhang: Counterfactual Visual Dialog: Robust Commonsense Knowledge Learning from Unbiased Training. IEEE Trans. Multim. 26: 1639-1651 (2024)
(14) An-An Liu, Hongshuo Tian, Ning Xu*, Weizhi Nie, Yongdong Zhang, M. Kankanhalli: Toward Region-Aware Attention Learning for Scene Graph Generation. IEEE Trans. Neural Networks Learn. Syst. 33(12): 7655-7666 (2022)
(15) Yanhui Wang, Ning Xu*, An-An Liu*, Wenhui Li, Yongdong Zhang: High-Order Interaction Learning for Image Captioning. IEEE Trans. Circuits Syst. Video Techn. 32(7): 4417-4430 (2022)
(16) An-An Liu, Yingchen Zhai, Ning Xu∗, Weizhi Nie, Wenhui Li∗, Yongdong Zhang: Region-Aware Image Captioning via Interaction Learning. IEEE Trans. Circuits Syst. Video Technol. 32(6): 3685-3696 (2022)
(17) Ning Xu, An-An Liu*, Yongkang Wong, Weizhi Nie, Yuting Su, Mohan S. Kankanhalli: Scene Graph Inference via Multi-Scale Context Modeling. IEEE Trans. Circuits Syst. Video Technol. 31(3): 1031-1041 (2021)
(18) An-An Liu, Yanhui Wang, Ning Xu*, Weizhi Nie, Jie Nie*, Yongdong Zhang: Adaptively Clustering-Driven Learning for Visual Relationship Detection. IEEE Trans. Multim. 23: 4515-4525 (2021)
(19) Weizhi Nie, Jiesi Li, Ning Xu*, An-An Liu*, Xuanya Li, Yongdong Zhang: Triangle-Reward Reinforcement Learning: A Visual-Linguistic Semantic Alignment for Image Captioning. ACM Multimedia 2021: 4510-4518
(20) Ning Xu, Hongshuo Tian, Yanhui Wang, Weizhi Nie, Dan Song, An-An Liu*, Wu Liu: Coupled-dynamic learning for vision and language: Exploring Interaction between different tasks. Pattern Recognit.113:107829 (2021)
(21) Ning Xu, Hanwang Zhang, An-An Liu*, Weizhi Nie, Yuting Su, Jie Nie*, Yongdong Zhang: Multi-Level Policy and Reward-Based Deep Reinforcement Learning Framework for Image Captioning. IEEE Trans. Multim. 22(5): 1372-1383 (2020)
(22) Hongshuo Tian, Ning Xu*, An-An Liu*, Yongdong Zhang: Part-Aware Interactive Learning for Scene Graph Generation. ACM Multimedia 2020: 3155-3163
(23) Ning Xu, An-An Liu*, Yongkang Wong, Yongdong Zhang, Weizhi Nie, Yuting Su, Mohan S. Kankanhalli: Dual-Stream Recurrent Neural Network for Video Captioning. IEEE Trans. Circuits Syst. Video Technol. 29(8): 2482-2493 (2019)
(24) An-An Liu*, Ning Xu*, Weizhi Nie*, Yuting Su, Yong-Dong Zhang: Multi-Domain and Multi-Task Learning for Human Action Recognition. IEEE Trans. Image Process. 28(2): 853-867 (2019)
(25) Ning Xu, An-An Liu*, Jing Liu*, Weizhi Nie, Yuting Su: Scene graph captioner: Image captioning based on structural visual representation. J. Visual Communication and Image Representation 58: 477-485 (2019)
(26) Ning Xu, An-An Liu*, Weizhi Nie, Yuting Su: Attention-in-Attention Networks for Surveillance Video Understanding in Internet of Things. IEEE Internet of Things Journal 5(5): 3419-3429 (2018)
(27) An-An Liu*, Ning Xu, Hanwang Zhang, Weizhi Nie, Yuting Su, Yongdong Zhang: Multi-Level Policy and Reward Reinforcement Learning for Image Captioning. IJCAI 2018: 821-827
(28) An-An Liu*, Ning Xu, Weizhi Nie, Yuting Su*, Yongkang Wong, Mohan S. Kankanhalli: Benchmarking a Multimodal and Multiview and Interactive Dataset for Human Action Recognition. IEEE Trans. Cybern. 47(7): 1781-1794 (2017)
授权国内外发明专利9项，部分授权专利如下：
(1) 基于常识引导的文本到图像生成方法及装置, 专利号:ZL202310690876.2
(2) 基于视觉语义关系的社交媒体流行度预测方法及装置, 专利号:ZL202110895131.0
(3) 一种基于多模态学习的视觉对话生成方法及装置, 专利号: ZL202110848206.X
(4) Visual relationship detection method and system based on region-aware learning mechanisms, Patent No: US 11,301,725 B2
(5) Visual relationship detection method and system based on adaptive clustering learning, Patent No: US 11,361,186 B2
主要讲授课程：
(1) 2022年至今，“视觉-语言”智能理解与生成（本科生）
(2) 2021年至今，信号处理实践（本科生）
(3) 2021年至今，视觉大数据学习和理解（博士生）
主要学术成就、奖励及荣誉：
(1) 2022年度天津市科学技术进步奖特等奖
(2) ACM Multimedia 2016 Grand Challenge MSR Video to Language, 排名第六（50个参赛队）
(3) TRECVID 2015国际顶级评测单项第一
其他（社会兼职等）：
(1) 学术组织：CCF多媒体技术专委会委员、CSIG数字媒体取证与安全专委会委员、CSIG图像智能边缘计算专委会委员
(2) SCI期刊客座编辑：Information Processing & Management
(3) 审稿人：IEEE T-NNLS、IEEE T-MM、IEEE T-CSVT、ACM MM、AAAI、IJCAI等
招生信息：
欢迎电子信息类、计算机类、软件类、数学类等有科研热情的同学参与课题研究
