【概况】

潘刚，博士，副教授，博士生导师。2012年博士毕业于天津大学，加拿大阿尔伯塔大学联合培养博士。从事人工智能、计算机视觉、跨模态融合方面的研究工作。近年发表学术论文50余篇，承担国家重点研发课题、国家自然科学基金在内的各类科研项目10余项。担任SCI期刊Journal of Electronic Imaging编委。担任国家科学技术奖励评审专家，教育部第五轮学科评估专家，天津市政务信息化专家库专家。主笔参与撰写我国行业标准4项，内容涉及到博物馆、市政、能源等领域的信息化标准建设。

【教育背景】

2008年9月 至 2012年6月 天津大学计算机应用(博士) 导师：孙济洲 教授 2009年9月 至 2010年9月 University fo Alberta（联合培养博士）导师：Martin Jagersand 教授 2006年9月 至 2008年6月 天津大学计算机软件与理论(硕士) 导师：张加万 教授 2002年9月 至 2006年6月 天津大学软件工程专业(学士)工商管理辅修学位

【学术经历】

2024年11月 至 今 天津大学学工部、学生处 副部长、副处长 2012年9月 至 2024年11月 天津大学未来技术学院 副书记、副院长 2012年9月 至 2012年9月 天津大学软件学院、智算学部 讲师、副教授

【讲授课程】

面向对象程序设计; 高级计算机视觉; 自然语言处理导论。

【教学成果】

主编出版行业专著2部。 牵头完成教育部产教协同育人项目。 近三年指导学生获省部级以上学科竞赛15项。 与腾讯、小米、百度、华为、国家管网、天津市政院等企事业单位有长期稳定的合作关系，开展研究生校企联合培养工作。

【研究方向】

人工智能算法在储能领域应用

【学术兼职】

2021--，Journal of Electronic Imaging的副主编

【科研项目及成果】

作为项目负责人，负责的主要项目有(下面列出近十几年负责的项目，在此前负责的项目略)， 1 2025-2027 多模态多目标融合分析的水下关键目标感知和损伤检测，国家重点研发计划项目课题 135万 2 2026-2029 面向多模态弱成对关系数据的统一可信信息抽取方法，国家自然科学基金面上项目 50万 3 2022-2025 ***，某JG项目 80万 4 2023-2024 基于飞桨平台的场景文本识别关键技术研究，CCF-松果基金 15万 5 2019-2023 关于油气管道周边工程关键目标识别算法系列项目，国家管网集团 150万

【代表性论著】

Jinyuan Li, Ziyan Li, Han Li, Jianfei Yu, Rui Xia, Di Sun, Gang Pan(corresponding author). Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation, IEEE Transactions on Multimedia, 2025.(中科院一区) Gang Pan, Meihua Liu, Lei Zhou, Jiahao Wang, Di Sun. Image Retargeting based on Text Region Awareness, ACM MM, 2025.(CCF A) Gang Pan, Hongen Liu, Di Sun. Formula Spotting Based on Synergy Perception and Representation Mining, ACM MM, 2025.(CCF A) Gang Pan, Liming Pan, Hongze Mi, Rongyu Xiong, Jiahao Wang, Di Sun. AFFIR: Dual-Modal Attention Feature Fusion for Scene Text Image Retargeting, ACM MM, 2025.(CCF A) Hongze Mi, Jinyuan Li, Xuying Zhang, Haoran Cheng, Jiahao Wang, Di Sun, Gang Pan(corresponding author). VP-MEL: Visual Prompts Guided Multimodal Entity Linking, ACL, 2025.(CCF A) Zhu Huang, Gang Pan(corresponding author), Chao Kang, and YaoZhi Lv. Semi-Supervised Pipe Video Temporal Defect Interval Localization, Computer-Aided Civil and Infrastructure Engineering, 2025.(封面文章，中科院一区) Jiahao Wang, Gang Pan(corresponding author), Di Sun, Jiawan Zhang.AFAN: An Attention-Driven Forgery Adversarial Network for Blind Image Inpainting, IEEE Transactions on Multimedia, 2025.(中科院一区) Gang Pan, Chen Wang, Zhijie Sui, Shuai Guo, Yaozhi Lv, Honglie Li, Di Sun, and Zixia Xia.Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network,Computer-Aided Civil and Infrastructure Engineering, 2025.(中科院一区) Zhu Huang, Gang Pan(corresponding author), Chao Kang and YaoZhi Lv. Temporal Defect Point Localization in Pipe CCTV Videos with Transformers, Automation in Construction, 2025.(中科院一区) Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, Gang Pan(corresponding author).LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition, ACL,2024.( CCF A) Qi Wang,Haomin Zhu,Gang Pan(corresponding author),Jianguo Wei,Chen Zhang,Zhu Huang,Guowei Ling. Distributed decision making for unmanned aerial vehicle inspection with limited energy constraint, Energy and AI, Volume 18, 2024.(中科院一区) Chenhao Yang, Feifei Zheng, Zoran Kapelan, Dragan Savic, Gang Pan, Yu Feng, Yiyi Ma. Automated Quantification of Sewage Pipe Cracks Using Deep Learning for Urban, Tunnelling and Underground Space Technology, 2024.(中科院一区) Gang Pan, Kang Liu, Jingxin Li, Jiahao Wang, and Di Sun. Domain Adaptive Object Detection with Dehazing Module, ICIC, 2024. Chengkun Xin, Qian Han, Gang Pan(corresponding author). Corelation Matters: A Stock Price Predication Model Based on the Graph Convolutional Network, ICIC, 2024. Jinyuan Li, Han Li, Zhuo Pan, Di Sun, Jiahao Wang, Wenkun Zhang, Gang Pan(corresponding author). Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge, EMNLP, 2023.(CCF B) Dingxiaofei Tian, Jinyan Chen, Zheyan Gao, Gang Pan. Linear Transformer-GAN: A Novel Architecture to Symbolic Music Generation, ICANN, 2023. Zixia Xia, Shuai Guo, Di Sun, Yaozhi Lv, Honglie Li, Gang Pan(corresponding author). Structure-aware dehazing of sewer inspection images based on monocular depth cues, Computer-Aided Civil and Infrastructure Engineering, 2022.(中科院一区, JCR Q1) Xumeng Han,Xuehui Yu, Guorong Li, Jian Zhao,Gang Pan, Qixiang Ye,Jianbin Jiao, Zhenjun Han.Rethinking Sampling Strategies for Unsupervised Person Re-identification, IEEE Transaction on Image Processing(TIP), 2022.(中科院一区，CCF A) Jiahao Wang, Gang Pan(corresponding author), Di Sun, Jiawan Zhang. Chinese Character Inpainting with Contextual Semantic Constraints, ACM Multimedia, 2021.(CCF A) Wenxu Li, Gang Pan(corresponding author), Chen Wang, Zhen Xing, etc. From Coarse to Fine: Hierarchical Structure-Aware Video Summarization, Transactions on Multimedia Computing Communications and Applications, 2021.(JCR Q1, CCF B) Yu Du, Shuai Guo, Gang Pan, Yaozhi Lv. Comparative Analysis of Pipelines Condition Assessment Protocols at Home and Abroad, China Water & Waste Water, 37(16), 8, 2021. Gang Pan, Yaoxian Zheng, Shuai Guo, Yaozhi Lv. Automatic sewer pipe defect semantic segmentation based on improved U-Net, Automation in Construction,Vol 119,2020,103383.(JCR Q1) Gang Pan, Bao Wang, Shuai Guo, Wenming Zhang, Stephen Edwini-Bonsu. Statistical analysis of sewer odour based on 10-year complaint data. Water Sci Technol 15 March 2020; 81 (6): 1221–1230.