English

曾丹 博士，教授

办公室：

上海大学宝山校区东区通信B楼（12号楼）509室

通信地址(邮政编码):

上海市南陈路333号上海大学通信学院（200444）

电话：

 

电子邮件：

dzeng@shu.edu.cn

个人主页：

https://scie.shu.edu.cn/Prof/zengdan.htm

曾丹，女，1982年生于湖南。现任上海大学教授，通信工程系主任，国家级领军人才（教育部长江学者特聘教授）。

所属一级学科为信息与通信工程、电子科学与技术。1999-2008年就读于中国科学技术大学，分别于2003年和2008年获本科和博士学位。2015—2016年，获得国家留学基金委资助，在美国德州大学圣安东尼奥分校与华为AI首席科学家田奇合作，从事研究工作。2024年入选教育部长江学者奖励计划特聘教授项目，2021年入选教育部长江学者青年学者项目。2013年被评为上海大学优秀青年教师、2013年被评为上海大学三八红旗手等。兼任IEEE多媒体通信专委会副主席、IEEE第23、24届国际多媒体信号处理会议学术委员会主席、《IEEE TRANSACTIONS ON MULTIMEDIA》编委、《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》编委、IEEE第24届国际多媒体信号处理研讨会程序委员会主席、IEEE多媒体系统及应用技术委员会委员、IEEE多媒体信号处理专业委员会委员、中国通信学会青工委、中国图象图形学学会青工委委员等职务。

研究领域聚焦计算机视觉、多媒体内容分析与人工智能领域，重点从探索目标智能感知中的探测、检测、识别与定位的新方法及新方案出发，解决复杂场景下低质量目标实时智能感知及应用中的关键技术难题。近五年第一/通讯作者发表CCF-A/中科院一区论文近50篇，承担国家级重点、省重大等项目八千余万元，获2023上海市科技进步奖一等奖（排1）、2023中国产学研创新成果一等奖（排1）、2022中国图象图形学学会科技进步一等奖（排2）等。其中，牵头组织技术攻关，构建复杂工况下大、弱、小时变目标的精细感知技术体系并落地应用，为工厂全流程智能化升级提供百米级大目标实时精细测量、大误差设备校准及精密生产、大时变目标和环境监测分析等关键技术，实现高炉实时高精度测绘与建造、板坯智能精整、产品缺陷检测、工厂一体化监测等工程应用。关键技术形成系列子系统，推广应用于智能制造、航空航天等领域，推动行业科技进步。 

潜心教学，主编专业基础课教材，获全国高校电子信息类青教赛二等奖；产教融合教书育人，牵头教育部产学合作协同育人项目，获2023中国人工智能学会教学成果激励计划一等奖（排1）等，因教书育人成绩突出，多次获上海市记功奖章与教委重大贡献记功、上海市教育系统巾帼建功标兵等。文汇报、上海科技报、上观新闻等多家主流媒体，对其在科研、教学、社会服务等方面的工作进行了专题报道。 

1. 教育经历：

l  2003/9 - 2008/6，中国科学技术大学，电路与系统，工学博士

l  1999/9 - 2003/6，中国科学技术大学，电子科学与技术，理学学士           

2. 工作经历：

l  2008/7至今，  上海大学，通信与信息工程学院，讲师，副教授，教授

l  2015/1-2016/1，美国德州大学圣安东尼奥分校，计算机学院，国家留学基金委访问学者

3.本科生教学

l  本科生专业基础课：电路与电子线路基础2（模拟电子线路）

l  每年招收毕业设计5名、优秀本科生2-4名

4.研究生培养

l  研究生课程：计算机视觉与模式识别、机器学习

l  每年招收博士研究生2-3名、硕士研究生4-6名

5.近年主持的部分科研项目

    [1] 2024 - 2027 国家自然科学基金面上项目，基于视觉知识学习的遥感图像小样本目标识别方法研究，50万，主持

    [2] 2024 - 2026 浙江省“尖兵”（重大）研发攻关计划，多模大数据质量高精度真伪检测与追溯的关键技术研究，4241万，主持

    [3] 2024 - 2027 企业委托横向，基于频域直方图分析的摄像头自动对焦方法和系统，600万，主持

    [4] 2022 - 2023 青岛海检智能科技有限公司，动设备在线监测系统开发，500万，主持

    [5] 2021 - 2023 国家部委研究项目，基于**的**检测跟踪，90万，主持

    [6] 2018 - 2020 国家重点研发计划，**探测算法与软件研制，400万，主持

    [7] 2021.4-2021.6 深圳市仁仁医疗发展有限公司，基于人工智能的临床医学影像的系统设计与开发，300万，主持

    [8] 2021.4-2021.6 北京迈迪维斯科技有限公司，基于人工智能的临床医学影像的算法研究，300万，主持

    [9] 2021.3-2021.12 中国科学院上海技术物理研究所，智能化环境识别与探测器数据预处理研究技术，195万，主持

  [10] 2022.1-2022.12 上海逻辑数码，数字水印隐形码识别系统开发，100万，主持

6.近年发表的主要学术论文

    [1] Enquan Yang, Peng Xing, Hanyang Sun, Wenbo Guo, Yuanwei Ma, Zechao Li, Dan Zeng: 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly. AAAI 2025. (CCF-A)

    [2] Weiyi Lv, Yuhang Huang, Ning Zhang, Ruei-Sung Lin, Mei Han, Dan Zeng: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction. CVPR 2024: 19321-19330. (CCF-A)

    [3] Hansong Zhang, Shikun Li, Pengju Wang, Dan Zeng, Shiming Ge: M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy. AAAI 2024: 9314-9322. (CCF-A)

    [4] Junjie Zhang, Tianci Hu, Xiaoshui Huang, Yongshun Gong, Dan Zeng: 3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset. IJCAI 2024. (CCF-A)

    [5] Hansong Zhang, Shikun Li, Dan Zeng, Chenggang Yan, Shiming Ge: Coupled Confusion Correction: Learning from Crowds with Sparse Annotations. AAAI 2024: 16732-16740. (CCF-A)

    [6] Shiming Ge, Weijia Guo, Chenyu Li, Junzheng Zhang, Yong Li, Dan Zeng: Masked Face Recognition with Generative-to-Discriminative Representations. ICML 2024. (CCF-A)

    [7] Kangkai Zhang, Shiming Ge, Ruixin Shi, Dan Zeng: Low-Resolution Object Recognition With Cross-Resolution Relational Contrastive Distillation. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(4): 2374-2384 (2024). (中科院一区)

    [8] Weiyi Lv, Ning Zhang, Junjie Zhang, Dan Zeng: One-Shot Multiple Object Tracking With Robust ID Preservation. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(6): 4473-4488 (2024). (中科院一区)

    [9] Peng Xing, Yanpeng Sun, Dan Zeng, Zechao Li: Normal Image Guided Segmentation Framework for Unsupervised Anomaly Detection. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(6): 4639-4652 (2024). (中科院一区)

  [10] Xiaoqiang Zhu, Jiayu Zhou, Lihua You, Xiaosong Yang, Jian Chang, Jian Jun Zhang, Dan Zeng: DFIE3D: 3D-Aware Disentangled Face Inversion and Editing via Facial-Contrastive Learning. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(9): 8310-8326 (2024). (中科院一区)

  [11] Guanyi Li, Junjie Zhang, Enquan Yang, Haoran Jiang, Dan Zeng: Multi-level Information Fusion Network with Edge Information Injection for Single-band Cloud Detection. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(9): 8412-8426 (2024). (中科院一区)

  [12] Jia Li, Chenchen Li, Xianying He, Fangfang Cui, Jie Zhao, Fansheng Chen, Dan Zeng: Single-Band Stripe Noise Removal in Multispectral Remote Sensing Images Based on Semisupervised Disentangled Transformation Network. IEEE Trans. Geosci. Remote. Sens. (TGRS) 62: 1-13 (2024). (中科院一区)

  [13] Junjie Zhang, Qiming Zhang, Yongshun Gong, Jian Zhang, Liang Chen, Dan Zeng: Weakly Supervised Semantic Segmentation With Consistency-Constrained Multiclass Attention for Remote Sensing Scenes. IEEE Trans. Geosci. Remote. Sens. (TGRS) 62: 1-18 (2024). (中科院一区)

  [14] Fanzhao Lin, Kexin Bao, Yong Li, Dan Zeng, Shiming Ge: Learning Contrast-Enhanced Shape-Biased Representations for Infrared Small Target Detection. IEEE Trans. Image Process. (TIP) 33: 3047-3058 (2024). (中科院一区)

  [15] Yanliang Jin, Ze-Yu Ji, Dan Zeng, Xiao-Ping (Steven) Zhang: VWP:An Efficient DRL-Based Autonomous Driving Model. IEEE Trans. Multim. (TMM) 26: 2096-2108 (2024). (中科院一区)

  [16] Junjie Zhang, Mingyan Wang, Haoran Jiang, Xinyu Zhang, Chenggang Yan, Dan Zeng: STAT: Multi-Object Tracking Based on Spatio-Temporal Topological Constraints. IEEE Trans. Multim. (TMM) 26: 4445-4457 (2024). (中科院一区)

  [17] Fanzhao Lin, Shiming Ge, Kexin Bao, Chenggang Yan, Dan Zeng: Learning Shape-Biased Representations for Infrared Small Target Detection. IEEE Trans. Multim. (TMM) 26: 4681-4692 (2024). (中科院一区)

  [18] Junjie Zhang, Yutao Rao, Xiaoshui Huang, Guanyi Li, Xin Zhou, Dan Zeng: Frequency-Aware Multi-Modal Fine-Tuning for Few-Shot Open-Set Remote Sensing Scene Classification. IEEE Trans. Multim. (TMM) 26: 7823-7837 (2024). (中科院一区)

  [19] Zheng Wang, Wei Zhang, Long Ye, Dan Zeng, Tao Mei: Cross-Modal Quantization for Co-Speech Gesture Generation. IEEE Trans. Multim. (TMM) 26: 10251-10263 (2024). (中科院一区)

  [20] Haoran Jiang, Xiangjie Wang, Junjie Zhang, Jian Zhang, Dan Zeng: DSENet: An Object-Wise Density-Informed Coarse-to-Fine Object Detector for Aerial Image. ICME 2024: 1-6. (CCF-B)

  [21] Yutao Rao, Liwei Sun, Junjie Zhang, Haoran Jiang, Jian Zhang, Dan Zeng: Densely Connected Transformer with Frequency Awareness and Sam Guidance for Semi-Supervised Hyperspectral Image Classification. ICME 2024: 1-6. (CCF-B)

  [22] Li Fu, Dongliang Ma, Xin Qu, Xin Jiang, Lie Shan, Dan Zeng: ParkScape: A Large-Scale Fisheye Dataset for Parking Slot Detection and a Benchmark Method. IEEE Trans. Instrum. Meas. (TIM) 73: 1-13 (2024).  (中科院二区)

  [23] Qichao Ying, Xiaoxiao Hu, Yangming Zhou, Zhenxing Qian, Dan Zeng, Shiming Ge: Bootstrapping Multi-View Representations for Fake News Detection. AAAI 2023: 5384-5392. (CCF-A)

  [24] Bochao Liu, Pengju Wang, Shikun Li, Dan Zeng, Shiming Ge: Model Conversion via Differentially Private Data-Free Distillation. IJCAI 2023: 2187-2195. (CCF-A)

  [25] Xiao Wang, Yuhang Huang, Dan Zeng, Guo-Jun Qi: CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-Adversarial Contrastive Learning. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 45(9): 10718-10730 (2023).  (中科院一区)

  [26] Gongyang Li, Yike Wang, Zhi Liu, Xinpeng Zhang, Dan Zeng: RGB-T Semantic Segmentation With Location, Activation, and Sharpening. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 33(3): 1223-1235 (2023).  (中科院一区)

  [27] Gongyang Li, Zhi Liu, Dan Zeng, Weisi Lin, Haibin Ling: Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images. IEEE Trans. Cybern. 53(1): 526-538 (2023). (中科院一区)

  [28] Jia Li, Junjie Zhang, Jungong Han, Chenggang Yan, Dan Zeng: Progressive Recurrent Neural Network for Multispectral Remote Sensing Image Destriping. IEEE Trans. Geosci. Remote. Sens. (TGRS) 61: 1-18 (2023). (中科院一区)

  [29] Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, Dan Zeng: Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation. IEEE Trans. Image Process. (TIP) 32: 116-127 (2023). (中科院一区)

  [30] Shikun Li, Tongliang Liu, Jiyong Tan, Dan Zeng, Shiming Ge: Trustable Co-Label Learning From Multiple Noisy Annotators. IEEE Trans. Multim. (TMM) 25: 1045-1057 (2023). (中科院一区)

  [31] Yingjie Song, Zhi Liu, Gongyang Li, Dan Zeng, Tianhong Zhang, Lihua Xu, Jijun Wang: RINet: Relative Importance-Aware Network for Fixation Prediction. IEEE Trans. Multim. (TMM) 25: 9263-9277 (2023). (中科院一区)

  [32] Daichi Zhang, Fanzhao Lin, Yingying Hua, Pengju Wang, Dan Zeng, Shiming Ge: Deepfake Video Detection with Spatiotemporal Dropout Transformer. ACM Multimedia 2022: 5833-5841. (CCF-A)

  [33] Yuhang Huang, Junjie Zhang, Shuyan Liu, Qian Bao, Dan Zeng, Zhineng Chen, Wu Liu: Genre-Conditioned Long-Term 3D Dance Generation Driven by Music. ICASSP 2022: 4858-4862. (CCF-B)

  [34] Hang Du, Hailin Shi, Dan Zeng, Xiao-Ping Zhang, Tao Mei: The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances. ACM Comput. Surv. 54(10s): 212:1-212:42 (2022). (中科院一区)

  [35] Kangkai Zhang, Chunhui Zhang, Shikun Li, Dan Zeng, Shiming Ge: Student Network Learning via Evolutionary Knowledge Distillation. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 32(4): 2251-2263 (2022). (中科院一区)

  [36] Hangtong Wu, Dan Zeng, Yibo Hu, Hailin Shi, Tao Mei: Dual Spoof Disentanglement Generation for Face Anti-Spoofing With Depth Uncertainty Learning. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 32(7): 4626-4638 (2022). (中科院一区)

  [37] Jia Li, Junjie Zhang, Fansheng Chen, Kai Zhao, Dan Zeng: Adaptive Material Matching for Hyperspectral Imagery Destriping. IEEE Trans. Geosci. Remote. Sens. (TGRS) 60: 1-20 (2022). (中科院一区)

  [38] Jian Zhang, Alan Hanjalic, Ramesh C. Jain, Xian-Sheng Hua, Shin'ichi Satoh, Yazhou Yao, Dan Zeng: Guest Editorial: Learning From Noisy Multimedia Data. IEEE Trans. Multim. (TMM) 24: 1247-1252 (2022). (中科院一区)

  [39] Dan Zeng, Yuhang Huang, Qian Bao, Junjie Zhang, Chi Su, Wu Liu: Neural Architecture Search for Joint Human Parsing and Pose Estimation. ICCV 2021: 11365-11374. (CCF-A)

  [40] Daichi Zhang, Chenyu Li, Fanzhao Lin, Dan Zeng, Shiming Ge: Detecting Deepfake Videos with Temporal Dropout 3DCNN. IJCAI 2021: 1288-1294. (CCF-A)

  [41] Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang: Flexible Auto-Weighted Local-Coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering. IEEE Trans. Knowl. Data Eng. 33(4): 1523-1539 (2021). (中科院一区)

  [42] Shiming Ge, Chunhui Zhang, Shikun Li, Dan Zeng, Dacheng Tao: Cascaded Correlation Refinement for Robust Deep Tracking. IEEE Trans. Neural Networks Learn. Syst. (TNNLS) 32(3): 1276-1288 (2021). (中科院一区)

  [43] Chunhui Zhang, Shiming Ge, Kangkai Zhang, Dan Zeng: Accurate UAV Tracking with Distance-Injected Overlap Maximization. ACM Multimedia 2020: 565-573. (CCF-A)

  [44] Dan Zeng, Han Liu, Hui Lin, Shiming Ge: Talking Face Generation with Expression-Tailored Generative Adversarial Network. ACM Multimedia 2020: 1716-1724. (CCF-A)

  [45] Ning Zhang, Tong Shen, Yue Chen, Wei Zhang, Dan Zeng, Jingen Liu, Tao Mei: AI-SAS: Automated In-match Soccer Analysis System. ACM Multimedia 2020: 4515-4517. (CCF-A)

  [46] Hang Du, Hailin Shi, Yuchi Liu, Jun Wang, Zhen Lei, Dan Zeng, Tao Mei: Semi-Siamese Training for Shallow Face Learning. ECCV (4) 2020: 36-53. (CCF-B)

  [47] Shiming Ge, Chenyu Li, Shengwei Zhao, Dan Zeng: Occluded Face Recognition in the Wild by Identity-Diversity Inpainting. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 30(10): 3387-3397 (2020). (中科院一区)

 

 

 

 

 

 

中 文

Dan Zeng, Ph.D, Professor

Office：

B509, 333 Nanchen Road, Shanghai University, Shanghai

Mail Address(Zip Code)：

Box 83, 99 Shangda Road, Shanghai University, Shanghai (200444)

Phone：

 

Email：

dzeng@shu.edu.cn

URL：

https://scie.shu.edu.cn/Prof/zengdan.htm

Zeng Dan, female, was born in 1982 in Hunan Province, China. She is currently a Professor at Shanghai University, serving as the Head of the Department of Communication Engineering. She is also a recipient of the National Leading Talent Program and a Distinguished Professor under the Ministry of Education’s Changjiang Scholars Program.

Her primary academic disciplines are Information and Communication Engineering and Electronic Science and Technology. From 1999 to 2008, she studied at the University of Science and Technology of China (USTC), where she obtained her Master's degree in 2003 and Ph.D. degree in 2008. From 2015 to 2016, she conducted research at the University of Texas at San Antonio, supported by the China Scholarship Council. In 2024, she was selected as a Distinguished Professor in the Changjiang Scholars Program and was named a Young Changjiang Scholar in 2021. In 2013, she was honored as an Outstanding Young Faculty Member and awarded the “March 8th Red-Banner Pacesetter” title by Shanghai University. She serves as Vice Chair of the IEEE Technical Committee on Multimedia Communications, Technical Program Chair of the 23rd and 24th IEEE International Workshop on Multimedia Signal Processing (MMSP), Editorial Board Member of IEEE Transactions on Multimedia and IEEE Transactions on Circuits and Systems for Video Technology, and Program Chair of IEEE MMSP 2024. She is also a member of the IEEE Technical Committees on Multimedia Systems and Applications, and Multimedia Signal Processing, as well as a member of the Youth Working Committees of the China Institute of Communications and the China Society of Image and Graphics.

Her research interests lie in computer vision, multimedia content analysis, and pattern recognition, with a recent focus on intelligent perception of visual targets in complex scenarios. Her work aims to address key technical challenges in real-time perception of low-quality targets, exploring novel methods for detection, recognition, and localization. She has led and participated in major national and provincial projects totaling over 80 million RMB. She was recognized as a Shanghai Education System Model Worker in 2022, and received multiple national awards including First Prize of the 2023 Shanghai Science and Technology Progress Award (1st contributor), First Prize of the 2023 Teaching Achievement Award from the Chinese Association for Artificial Intelligence (1st contributor), First Prize of the 2023 China Industry-University-Research Cooperation Innovation Achievement Award (1st contributor), and First Prize of the 2022 Technical Progress Award from the China Society of Image and Graphics (2nd contributor). She has led major technology breakthroughs in fine-grained perception of large-scale, weak, and time-varying targets under complex industrial conditions. These efforts resulted in the development and deployment of critical subsystems supporting real-time large-object measurement, high-accuracy equipment calibration, precision manufacturing, and dynamic monitoring of industrial environments. Her technologies have been widely applied in domains such as metallurgy and aerospace, significantly advancing intelligent manufacturing processes. Specific industrial applications include high-precision 3D mapping of blast furnaces, intelligent slab finishing, defect detection, and integrated factory monitoring.

Prof. Zeng is also deeply committed to education. She is the chief editor of a textbook on fundamental courses in her field and has received the Second Prize in the National Young Faculty Teaching Competition for Electronic Information Majors. She has actively promoted the integration of industry and education, leading collaborative education projects supported by the Ministry of Education. Her teaching achievements have earned her the First Prize in the National Teaching Achievement Awards of the Chinese Association for Artificial Intelligence. For her outstanding contributions to education, she has received multiple commendations from the Shanghai Municipal Education Commission. Her work in research, teaching, and public service has been featured in major media outlets such as Wenhui Daily, Shanghai Science and Technology News, and The Paper (Shangguan News).

1. Education：

2003 - 2008    PhD, Circuits and System, School of Circuits and Systems,  University of Science and Technology of China, China.

2004 - 2008    BSc, Electronic Science and Technology, School of Electronic Science and Technology, University of Science and Technology of China, China.        

2. Experience：

2008 - Current   Lecturer/Associate Professor/Professor, Department of Communication Engineering, Shanghai University, China.

2015 - 2016     Visiting Scholar, Department of Computer Science, University of Texas at San Antonio, United States.  Advisor: Dr. Qi Tian, IEEE Fellow, BSc Tsinghua University, PhD UIUC.

3.Undergraduate Teaching

Core Courses for Undergraduates: Fundamentals of Circuits and Electronic Circuits 2 (Analog Electronic Circuits)

Undergraduate Courses: Network Programming Technology, Fundamentals of Computer Vision, Multimedia Technology and Communication

Supervision of 6 students for their graduation projects annually, and 2-4 outstanding undergraduates

4.Graduate Supervision

Graduate Courses: Computer Vision and Pattern Recognition, Machine Learning

Supervision of 3-5 PhD and Master's students annually

5.Selected Projects

[1]  2024 - 2027 PI. “Research on Small Sample Target Recognition Method for Remote Sensing Images Based on Visual Knowledge Learning.” National Natural Science Foundation of China.

[2]  2024 - 2026 PI. “Research on Key Technologies for High-Precision Authenticity Detection and Tracing of Multi-modal Big Data Quality.” Zhejiang Provincial Science and Technology Department.

[3]  2021 - 2023 PI. “*** Detection and Recognition Technology.” National Ministry Research Project.

[4]  2018 - 2020 PI. “Development of *** Detection Algorithms and Software.” National Key R&D Program.

[5]  2016 - 2019 PI. "Study on three-dimensional spherical Mosaic of geostationary meteorological satellite multi-source remote sensing images." Natural Science Foundation of China.

[6]  2019 - 2020 PI. “*** Recognition ***” Ministry Pre-Research Project.

[7]  2019 - 2020 PI. “*** Learning***” Ministry Pre-Research Project.

[8]  2014 - 2022 PI. “Research on key technologies of MBB innovation platform.” Huawei Technology Co., Ltd.

[9]  2021 - 2022 PI. “Research on Intelligent Environment Recognition and Detector Data Preprocessing.” Confidential Institute.

[10] 2021/01 - 2021/12 PI. “Research on AI-Based Algorithms for Clinical Medical Imaging.” Beijing MediWise.

[11] 2018 - 2019 PI. “Research on the enhancement, detection and recognition of moving objects in complex background.” Confidential Institute.

[12] 2014 - 2016 PI. “Research on image mosaics of non-limited scene under sparse sampling.” National Natural Science Foundation of China.

6.Selected Publications

    [1] Weiyi Lv, Yuhang Huang, Ning Zhang, Ruei-Sung Lin, Mei Han, Dan Zeng: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction. CVPR 2024: 19321-19330.

    [2] Hansong Zhang, Shikun Li, Pengju Wang, Dan Zeng, Shiming Ge: M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy. AAAI 2024: 9314-9322

    [3] Junjie Zhang, Tianci Hu, Xiaoshui Huang, Yongshun Gong, Dan Zeng: 3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset. IJCAI 2024.

    [4] Hansong Zhang, Shikun Li, Dan Zeng, Chenggang Yan, Shiming Ge: Coupled Confusion Correction: Learning from Crowds with Sparse Annotations. AAAI 2024: 16732-16740

    [5] Kangkai Zhang, Shiming Ge, Ruixin Shi, Dan Zeng: Low-Resolution Object Recognition With Cross-Resolution Relational Contrastive Distillation. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 34(4): 2374-2384 (2024)

    [6] Junjie Zhang, Qiming Zhang, Yongshun Gong, Jian Zhang, Liang Chen, Dan Zeng: Weakly Supervised Semantic Segmentation With Consistency-Constrained Multiclass Attention for Remote Sensing Scenes. IEEE Trans. Geosci. Remote. Sens. (TGRS) 62: 1-18 (2024)

    [7] Fanzhao Lin, Kexin Bao, Yong Li, Dan Zeng, Shiming Ge: Learning Contrast-Enhanced Shape-Biased Representations for Infrared Small Target Detection. IEEE Trans. Image Process. (TIP) 33: 3047-3058 (2024)

    [8] Yanliang Jin, Ze-Yu Ji, Dan Zeng, Xiao-Ping (Steven) Zhang: VWP:An Efficient DRL-Based Autonomous Driving Model. IEEE Trans. Multim. (TMM) 26: 2096-2108 (2024)

    [9] Junjie Zhang, Mingyan Wang, Haoran Jiang, Xinyu Zhang, Chenggang Yan, Dan Zeng: STAT: Multi-Object Tracking Based on Spatio-Temporal Topological Constraints. IEEE Trans. Multim. (TMM) 26: 4445-4457 (2024)

 [10] Fanzhao Lin, Shiming Ge, Kexin Bao, Chenggang Yan, Dan Zeng: Learning Shape-Biased Representations for Infrared Small Target Detection. IEEE Trans. Multim. (TMM) 26: 4681-4692 (2024)

 [11] Junjie Zhang, Yutao Rao, Xiaoshui Huang, Guanyi Li, Xin Zhou, Dan Zeng: Frequency-Aware Multi-Modal Fine-Tuning for Few-Shot Open-Set Remote Sensing Scene Classification. IEEE Trans. Multim. (TMM) 26: 7823-7837 (2024)

 [12] Guanyi Li, Junjie Zhang, Enquan Yang, Haoran Jiang, Dan Zeng: Multi-level Information Fusion Network with Edge Information Injection for Single-band Cloud Detection. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) (2024)

 [13] Xiao Wang, Yuhang Huang, Dan Zeng, Guo-Jun Qi: CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-Adversarial Contrastive Learning. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 45(9): 10718-10730 (2023)

 [14] Gongyang Li, Yike Wang, Zhi Liu, Xinpeng Zhang, Dan Zeng: RGB-T Semantic Segmentation With Location, Activation, and Sharpening. IEEE Trans. Circuits Syst. Video Technol. (TCSVT) 33(3): 1223-1235 (2023)

 [15] Gongyang Li, Zhi Liu, Dan Zeng, Weisi Lin, Haibin Ling: Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images. IEEE Trans. Cybern. 53(1): 526-538 (2023)

 [16] Jia Li, Junjie Zhang, Jungong Han, Chenggang Yan, Dan Zeng: Progressive Recurrent Neural Network for Multispectral Remote Sensing Image Destriping. IEEE Trans. Geosci. Remote. Sens. (TGRS) 61: 1-18 (2023)

 [17] Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, Dan Zeng: Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation. IEEE Trans. Image Process. 32: 116-127 (2023)

 [18] Shikun Li, Tongliang Liu, Jiyong Tan, Dan Zeng, Shiming Ge: Trustable Co-Label Learning From Multiple Noisy Annotators. IEEE Trans. Multim. 25: 1045-1057 (2023)

 [19] Yingjie Song, Zhi Liu, Gongyang Li, Dan Zeng, Tianhong Zhang, Lihua Xu, Jijun Wang: RINet: Relative Importance-Aware Network for Fixation Prediction. IEEE Trans. Multim. (TMM) 25: 9263-9277 (2023)

 [20] Qichao Ying, Xiaoxiao Hu, Yangming Zhou, Zhenxing Qian, Dan Zeng, Shiming Ge: Bootstrapping Multi-View Representations for Fake News Detection. AAAI 2023: 5384-5392