Welcome to Tang Sheng's Homepage

Dr. Tang Sheng (唐胜), Associate Professor

Multimedia Computing Group,
Institute of Computing Technology,
Chinese Academy of Sciences (CAS), China

TEL: +8610-62600617; FAX: +8610-62601356
Address: Room 617, No.6 Kexueyuan South Road, Zhongguancun,
             Haidian District, Beijing, China. PostCode: 100190
Email: ts@ict.ac.cn

Homepage: http://mcg.ict.ac.cn/people/shengtang.htm
ICT Website: Link from the Institute of Computing Technology, CAS
CAS Website: Link from the Graduate University of CAS

-Biography


Dr. Tang Sheng received his Ph.D. degree in computer application technology at the Institute of Computing Technology, Chinese Academy of Sciences (ICT-CAS), China, in March 2006. He is now an associate professor in the ICT-CAS.

He was the ICT team (MCG-ICT-CAS) leader of TREC Video Retrieval Evaluation (TRECVid) from 2006 to 2008, and ICT team (MCG-ICT-CAS) leader of ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2015 and 2016, and was invited to give presentations at the TRECVID 2008 workshop and the 2nd ImageNet and COCO Visual Recognition Challenges Joint Workshop in conjunction with ECCV 2016.

From Feb., 2009 to Feb., 2010, he worked as a visiting research fellow in NUS under the instruction of Prof. Chua Tat-Seng. In 2014, He organized the Large Scale Video Retrieval and Recognition Challenge in China which attracted 28 team participants from top universities and institutes such as Tsinghua, Peking, Fudan Universities, and Institute of Automation, Chinese Academy of Sciences, etc. His current research interests are in the fields of pattern recognition and machine learning, multimedia information processing, in particular, on indexing, retrieval and extraction of information in image and video.

He was awarded first prize of Beijing Science and Technology in 2006 and 2014, and the “2012 CCF Award for Science and Technology” by China Computer Federation (CCF) in 2012, and the Top 10% Paper Award in the 17th IEEE International Workshop on Multimedia Signal Processing (MMSP 2015).

Dr. Tang is active in the international research community. He serves as the PC member of top conference IJCAI 2015, the reviewer for a number of famous international conferences and journals, such as ACM TIST, IEEE TIP, TNNLS, TIFS, TMM, ICMR 2015, CIVR 2008, etc. He is a member of ACM, IEEE, and senior member of CCF.

-Research


Pattern recognition and Machine learning, Multimedia information processing, in particular, on indexing, retrieval and recognition of information in image and video. The main focus is on the semantic analysis and retrieval of video with deep learning.

-Academic/Professional Qualifications


-Career History


-Honors and Awards


-Recent Projects


-Ph.D Thesis


-Chinese Patents


  1. Sheng Tang, Linghui Li, Yong-Dong Zhang, Jin-Tao Li; A method and system for generating a natural language describing the content of an image, 2016112441165, Applied in 2016.
  2. Sheng Tang, Yong-Dong Zhang, Jin-Tao Li, Zuoxin Xu; Dictionary learning, visual word feature extraction method and retrieval system, 201410287639.2, Applied in 2014.
  3. Sheng Tang, Ji Wan, Method, device and system for training model parameters, 201410579249.2, Applied in 2014.
  4. Sheng Tang, Qi Han, Yong-Dong Zhang, Jin-Tao Li; A Pattern Training and Recognition Method based on Ensemble Learning, 2011103033624, Applied in 2011.
  5. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang, Cheng Xie; An efficient training and testing method for image classification, ZL200910092710.0, Authorized on Mar. 6th, 2013.
  6. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang; Robust Image Hashing, ZL200510077454.X, Authorized on Jan. 9th, 2008.
  7. Sheng Tang, Yue-Liang Qian, etal; A Database based on Disturbing Stroke Order an Evaluation System for On-line Handwritten Chinese Character Recognition, ZL200410000823.0, Authorized on May 23th, 2007.
  8. Yue-Liang Qian, Sheng Tang, Jin-Tao Li, etal; Remote Serial Communication System for PDA and its Flux Control Method, 01119940.7, Authorized on Aug. 11th, 2004.

-Selected Journal Papers


  1. Sheng Tang, Yan-Tao Zheng, Yu Wang, Tat-Seng Chua, “Sparse Ensemble Learning for Concept Detection”, IEEE Transactions on Multimedia, Volume: 14 Issue: 1, pages: 43-54, February 2012.
    [CameraReady paper]
    [90 minutes' Invited Speech at China Samsung Telecom R&D Center]
    [Invited Speech at Computer Science department of Reykjavik University, Iceland] [Slides]
    [Dataset, Demo Video]
  2. Sheng Tang, Yong-Dong Zhang, Zuo-Xin Xu, et al; “An Efficient Concept Detection System Via Sparse Ensemble Learning”, Neurocomputing, Volume 169, Pages 124-133, December 2015.
  3. Rui Zhang, Sheng Tang, Wu Liu, Yongdong Zhang, Jintao Li; “Multi-modality Tag Localization for Mobile Video Search Multimedia Systems”, Multimedia Systems, accepted on February 14th, 2016.
  4. Yong-Dong Zhang, Yu Wang, Sheng Tang, Steven C. H. Hoi, Jin-Tao Li, “FSpH: Fitted spectral hashing for efficient similarity search”, Computer Vision and Image Understanding (CVIU), 124: 3-11, 2014 (Corresponding Author).
  5. Yu Wang, Sheng Tang, Yan-Tao Zheng, Yongdong Zhang, Jintao Li, “Semi-supervised earning via Sparse Model”, Neurocomputing, 131: 124-131, 2014.
  6. Yu Wang, Sheng Tang, Yongdong Zhang, Jintao Li, Dong Wang, “Representative selection based on sparse modeling”, Neurocomputing, 139: 423-431, 2014.
  7. Feidie Liang, Sheng Tang, Yongdong Zhang, Zuoxin Xu, Jintao Li, “Pedestrian Detection based on Sparse Coding and Transfer Learning”, Machine Vision and Applications, 25(7): 1697-1709,2014.
  8. Wu Liu, Yongdong Zhang, Sheng Tang, et al, “Accurate Estimation of Human Body Orientation From RGB-D Sensors”, IEEE Transactions on Cybernetics , 43(5): 1442 - 1452, 2013.
  9. Lei Huang, Sheng Tang, Yongdong Zhang, Shiguo Lian, Shouxun Lin, “Robust Human Body Segmentation based on Part Appearance and Spatial Constraint”, Neurocomputing, 118:191-202, October 2013.
  10. Shaoxi Xu, Sheng Tang, Yongdong Zhang, Jintao Li, Yan-Tao Zheng, “Exploring Multi-Modality Structure for Cross Domain Adaptation in Video Concept Annotation”, Neurocomputing, Volume 95, Number 15, Pages 11-21, October 2012. [PDF]
  11. Yan Song, Sheng Tang, Yan-Tao Zheng, Tat-Seng Chua, Yongdong Zhang, Shouxun Lin, “Exploring Probabilistic Localized Video Representation for Human Action Recognition”, Multimedia Tools and Applications, Volume 58, Number 3, Pages 663-685, June, 2012. [PDF]
  12. Hongtao Xie, Ke Gao, Yongdong Zhang, Sheng Tang, Jintao Li, Yizhi Liu, “Efficient Feature Detection and Effective Post-Verification for Large Scale Near-Duplicate Image Search”, IEEE Transactions on Multimedia, Volume: 13 Issue: 6, pages: 1319-1332, Dec. 2011. [PDF]
  13. Yan Song, Yan-Tao Zheng, Sheng Tang, Xiangdong Zhou, Yongdong Zhang, Shouxun Lin, Tat-Seng Chua, “Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos”, IEEE Transactions on Circuits and Systems for Video Technology, Volume: 21, Issue: 9, pages: 1193-1202, 2011. [PDF]
  14. Guangda Li, Haojie Li, Zhaoyan Ming, Richang Hong, Sheng Tang, Chua, Tat-Seng; “Answering over Community-Contributed Web Videos”, IEEE Multimedia, Volume: 17 Issue: 4, pages: 46 – 57, Oct.-Dec. 2010.
  15. Juan Cao, Tian Xia, Jin-Tao Li, Yong-Dong Zhang, Sheng Tang, “A Density-based Method for Adaptive LDA Model Selection”; Neurocomputing, 72(7-9):1775-1781, 2009.
  16. Xuefeng Pan, Jintao Li, Yongdong Zhang, Sheng Tang, Lejun Yu, Tian Xia; “Spatiotemporal Video Copy Detection Based on Visual Perception Analyses”; Chinese Journal of Computers. Vol.32, No.1, Pages: 107-114, 2009.
  17. Juan Cao, Jin-Tao Li, Yong-Dong Zhang, Sheng Tang, “The optimal condition of LDA model for video retrieval”; Chinese Journal of Computers. Vol.31, No.10, Pages: 1780-1787, 2008.
  18. Xuefeng Pan, Jintao Li, Yongdong Zhang, Sheng Tang, Lejun Yu; “Format-Independent Motion Content Description Based on Spatiotemporal Visual Sensitivity”; IEEE Transactions on Consumer Electronics; Vol.53, No.2, Pages:769-774, 2007.
  19. Yong-Dong Zhang, Sheng Tang, and Jin-Tao Li, “Secure and Incidental Distortion Tolerant Digital Signature for Image Authentication”, Journal of Computer Science and Technology, Vol.22, No.4, Pages: 618-625, 2007.

-Selected Conference Papers


  1. Rui Zhang, Sheng Tang, Min Lin, Jintao Li, Shuicheng Yan; “Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions”, The 26th International Joint Conference on Artificial Intelligence (IJCAI-2017), Melbourne, Australia, August 19-25, 2017.(Corresponding Author, CCF A class international top conference, full paper)
  2. Linghui Li, Sheng Tang, Lixi Deng, Yongdong Zhang and Qi Tian; “Image Caption with Global-Local Attention”, The 31th AAAI Conference on Artificial Intelligence (AAAI-2017), Pages: 4133-4139, San Francisco, California USA, February 4–9, 2017.(Corresponding Author, CCF A class international top conference, full paper) [PDF]
  3. Sheng Tang, Yong Dong Zhang, Hui Chen, “Scalable Logo Recognition based on Compact Sparse Dictionary for Mobile Device”, The 17th IEEE International Workshop on Multimedia Signal Processing (MMSP 2015), Shamen, China, October 19-21, 2015. (Top 10% Paper Award
  4. Sheng Tang, Hui Chen, Ke Lv, Yong Dong Zhang, “Large Visual Words for Large Scale Image Classification”, IEEE International Conference on Image Processing (ICIP 2015), Quebec City, Canada, Sep. 27-30, 2015.
  5. Sheng Tang, Hui Chen, Yu Li, Jun-Bin Xiao and Jin-Tao Li, “A Sparse Ensemble Learning System For Efficient Semantic Indexing”, ACM International Conference on Multimedia Retrieval (ICMR 2015), Shanghai, China, June 23-26, 2015.
  6. Yang Cao, Ke Gao, Sheng Tang, Yongdong Zhang, “A Representative Local Region Detector Based On Color-Contrast-MSER”, ACM International Conference on Multimedia Retrieval (ICMR 2014), Glasgow, Scotland, April, 2014.
  7. Yu Wang, Sheng Tang, Yongdong Zhang, Jintao Li, et al, “Fitted Spectral Hashing”, ACM Multimedia: 645-648, 2013.
  8. Ji Wan, Sheng Tang, Yongdong Zhang, Lei Huang, Jintao Li, “Data Driven Multi-Index Hashing”, International Conference on Image Processing (ICIP), 2013 (Accepted).
  9. Yu Wang, Sheng Tang, Feidie Liang, YaLin Zhang, and Jintao Li, “Beyond Kmedoids: Sparse Model Based Medoids Algorithm for Representative Selection”, 19th International Conference on Multimedia Modeling (MMM) (2), pp: 239-250, 2013.
  10. Feidie Liang, Sheng Tang, Yu Wang, Qi Han, and Jintao Li, “A Sparse Coding based Transfer Learning Framework for Pedestrian Detection”, 19th International Conference on Multimedia Modeling (MMM) (2), pp: 272-282, 2013.
  11. Feidie Liang, Dong Wang, Yang Liu, Youcheng Jiang, Sheng Tang, “Fast Pedestrian Detection Based on Sliding Window Filtering", Advances in Multimedia Information Processing – PCM 2012 , pp: 811-822, Singapore, 2012.
  12. Shao-Xi Xu, Jing Yang, Sheng Tang, Yong-Dong Zhang, “A pseudo relevance feedback based cross domain video concept detection”, The Third International Conference on Internet Multimedia Computing and Service (ACM ICIMCS 2011), pp: 21-25, 2011.
  13. Yan Song, Sheng Tang, Yan-Tao Zheng, Tat-Seng Chua, Yongdong Zhang, Shouxun Lin, “A Distribution Based Video Representation For Human Action Recognition”, Proc. of IEEE International Conference on Multimedia and Expo 2010, pp: 772-777, Singapore, 2010.
  14. Shaoxi Xu, Sheng Tang, Yongdong Zhang, and Jintao Li, “Mulit-Modality Transfer based on Multi-Graph Optimization for Domain Adaptive Video Concept Annotation”, Proc. of the Pacific-Rim Symposium on Image and Video Technology, Singapore, 2010. (Student Travel Grant Award)
  15. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang,etal; “PornProbe: an LDA-SVM based Pornography Detection System”; ACM Multimedia 2009, Beijing, China, Oct.19-24, 2009. [PDF] [Demo]
  16. Tat-Seng Chua, Sheng Tang, Remi Trichet, Hung Khoon Tan, Yan Song; “MovieBase: A Movie Database for Event Detection and Behavioral Analysis”, ACM Multimedia 2009 Workshop on Web-Scale Multimedia Corpus, Beijing, China, Oct.23, 2009.
  17. Shaoxi Xu, Sheng Tang, Jintao Li, Yongdong Zhang, “Pseudo Relevance Feedback with Incremental Learning for High Level Feature Detection”, Proc. of IEEE International Conference on Multimedia and Expo, 2009.
  18. Sheng Tang, Jin-Tao Li, Ming Li, Cheng Xie, Yi-Zhi Liu, Kun Tao, Shao-Xi Xu; “TRECVID 2008 High-Level Feature Extraction By MCG-ICT-CAS”; Proc. TRECVID 2008 Workshop, Gaithesburg, USA , Nov 2008. (53 citations as shown by Google Scholar)
  19. Yongdong Zhang, Ke Gao, Sheng Tang, Xiao Wu, Xiaoyuan Cao, Huamin Ren,Yufen Wu, Jian Yang; “TRECVID 2008 Content-Based Copy Detection By MCG-ICT-CAS”; Proc. TRECVID 2008 Workshop, Gaithesburg, USA , Nov 2008. (Oral Presentation Slides on TRECVID 2008 Workshop)
  20. Lei Bao, Sheng Tang, Jintao Li, etal, “Document Clustering based on Spectral Clustering and Non-negative Matrix Factorization”, The 21th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA-AIE 2008), Lecture Notes in Computer Science, Volume: 5027, June 18-20, 2008, Poland.
  21. Anan Liu, Sheng Tang, Yongdong Zhang, et al., “A Hierarchical Framework for Movie Content Analysis: Let Computers Watch Films like Humans”, Proc. of the 3rd CVPR2008 Workshop on Semantic Learning Applications in Multimedia (SLAM2008), Anchorage, America, pp. 1-8, 2008.
  22. Sheng Tang, Yong-Dong Zhang, Jin-Tao Li, etal; “TRECVID 2007 High-Level Feature Extraction By MCG-ICT-CAS ”; Proc. TRECVID 2007 Workshop, Gaithesburg, USA , Nov 2007.
  23. Tat-Seng Chua, Sheng Tang, etal; “TRECVID 2007 Search Tasks by NUS-ICT”; Proc. TRECVID 2007 Workshop, Gaithesburg, USA , Nov 2007.
  24. Huan-Bo Luan, Shi-Yong Neo, Tat-Seng Chua, Yan-Tao Zheng, Sheng Tang, Yong-Dong Zhang, Jin-Tao Li; “Active Learning Approach to Interactive Spatio-temporal News Video Retrieval”, ACM International Conference on Image and Video Retrieval (CIVR) 2007, July 9-11, 2007, Amsterdam, The Netherlands. (VisionGo, Best Performance Award in the CIVR2007 Interactive Video Retrieval Competition -- VideOlympics)
  25. Sheng Tang, Yong-Dong Zhang, Jin-Tao Li, etal; “Rushes Exploitation 2006 By CAS MCG”; Proc. TRECVID 2006 Workshop, Gaithesburg, USA , Nov 13-14. 2006.
  26. Tat-Seng Chua, Shi-Yong Neo, Yantao Zheng, Hai-Kiat Goh, Sheng Tang, Yang Xiao and Ming Zhao, Sheng Gao, Xinglei Zhu, Lekha Chaisorn, Qibin Sun; “TRECVID 2006 by NUS-I2R”; Proc. TRECVID 2006 workshop, Gaithersburg, Maryland, November 2006.
  27. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang, “SSF Fingerprint for Image Authentication: An Incidental Distortion Resistant Scheme”, ACM Multimedia 2005, Singapore, November 6-11, 2005.
  28. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang, “Compact and Robust Image Hashing”, Lecture Notes in Computer Science, Volume 3481, Apr 2005, Pages 547 – 556.
  29. Sheng Tang, Jin-Tao Li, Yong-Dong Zhang, “Compact And Robust Fingerprints Using DCT Coefficients Of Key Blocks”, Lecture Notes in Computer Science, Volume 3523, May 2005, 521 – 528.

-Book Chapter


  1. Sheng Tang, Yan-Tao Zheng, Gang Cao, Yong-Dong Zhang and Jin-Tao Li; "Ensemble Learning with LDA Topic Models for Visual Concept Detection", in book: Multimedia - A Multidisciplinary Approach to Complex Issues (ISBN: 978-953-51-0216-8), InTech , chapter 9, pages: 175-200, March, 2012. [Online PDF]

-DemoSystem


    Please refer to for my 5 Demo Videos on Baidu Cloud Driver.
  1. Large Scale Image Classification Based on Sparse Ensemble Learning (our TMM 2012 Paper) with Convolution Neural Network (CNN) feature extraction (Test on the ILSVRC 2012 Validation dataset).
  2. Large Scale Image Retrieval tested on 14,207,868 ImageNet images.
  3. Large Scale Logo Recognition with 709 logo categories.
  4. Image Caption with Global-Local Attention Based on AAAI 2017 paper.
  5. PornProbe: an LDA-SVM based Pornography Detection System Based on our ACM Multimedia 2009 Paper.

Links