Welcome to Intelligent Media Analysis Group (IMAG) in School of Computer Science, Nanjing Univeristy of Science and Technology. Our group focuses on analyzing the big media and aims to develop frontier technologies to address the analysis, understanding and management tasks of the big multimedia data. Besides, we also pay attention to the real-world applications, such as multimedia retrieval, face recognition and recommendation.


  • 欢迎多媒体检索及计算机视觉相关领域的青年才俊加入南京理工大学智能媒体分析研究室。感兴趣者请联系唐金辉教授(jinhuitang AT njust DOT edu DOT cn)

  • 实验室正在招收具有多媒体和计算机视觉研究背景的博士生和博士后,非常欢迎具有优秀的科研经验和编程能力的学生加入IMAG实验室。联系时请发简历到唐金辉教授邮箱(jinhuitang AT njust DOT edu DOT cn)

  • 2017年1月7日, 举办“高通量视觉计算”第三次研讨会

  • 2016年12月14日, 举办“高通量视觉计算”第二次研讨会

  • 2016年5月17日, 清华大学鲁继文副教授在IMAG实验室作报告,报告题目:"Binary Feature Learning"

  • On July 29th, 2015, Prof.Jiebo Luo of the University of Rochester give a talk "Social Multimedia As Sensors" in IMAG

  • On July 4th, 2015, Prof.Ling Shao of Northumbria University give a talk "Feature Engineering vs. Feature Learning for Human Action Recognition" in IMAG

  • On June 6th, 2015, Prof.Guojun Qi of the University of Central Florida give a talk "Differential Recurrent Networks for Human Action Recognition" in IMAG

  • 2015年5月22日, 清华大学林闯教授在IMAG实验室作报告,报告题目:"How to Do Research and How to Write Paper"

  • 2015年4月9日, 上海交通大学熊红凯教授在IMAG实验室作报告,报告题目: "Sparse Modeling and Learning in Multi-Dimensional Signal Representation"

  • 2014年9月27日, 北京大学高文教授在IMAG实验室作报告,报告题目:"计算机与人工智能"

  • 2014年9月26日,IMAG实验室举办“高通量图像视频计算”研讨会

  • 2014年8月23日, 浙江大学何晓飞教授在IMAG实验室作报告,报告题目:"Deep Learning and Its Application"

  • Selected Publications

    1. Jinhui Tang, Xiangbo Shu, Quo-Jun Qi, Zechao Li, Meng Wang, Shuicheng Yan, Ramesh Jain:
      Tri-Clustered Tensor Completion for Social-Aware Image Tag Refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, DOI: 10.1109/TPAMI.2016.2608882.
    2. Jinhui Tang, Shiyu Chang, Guo-Jun Qi, Qi Tian, Yong Rui, Thomas S. Huang:
      LEGO-MM: LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia. IEEE Transactions on Image Processing, 26(1): 196-207, 2017.
    3. Zechao Li, Jinhui Tang:
      Weakly Supervised Deep Matrix Factorization for Social Image Understanding. IEEE Transactions on Image Processing, 26(1): 276-288, 2017.
    4. Jinhui Tang, Xiangbo Shu, Zechao Li, Quo-Jun Qi, Jingdong Wang:
      Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains. ACM Transactions on Multimedia Computing, Communications, and Applications, 12(4s), 2016.
    5. Zechao Li, Jing Liu, Jinhui Tang, Hanqing Lu:
      Robust Structured Subspace Learning for Data Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(10): 2085-2098, 2015.
    6. Jinhui Tang, Zechao Li, Meng Wang, Ruizhen Zhao:
      Neighborhood Discriminant Hashing for Large-Scale Image Retrieval, IEEE Transactions on Image Processing, 4(9): 2827-2840, 2015.