Visual Information Processing and Learning
Visual Information Processing and Learning
Shuhui Wang

Associate Professor

Research area: Multimedia analysis、Computer vision、Machine Learning、Data Mining

Shuhui Wang received the B.S. degree in electronic engineering from Tsinghua University, Beijing, China, in 2006, and the Ph.D. degree from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, in 2012. He is currently an Associate Professor with the Institute of Computing Technology, Chinese Academy of Sciences. He is also with the Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences. His research interests include semantic image analysis, image and video retrieval and large-scale Web multimedia data mining. Dr. Wang has published over 70 papers on prestigious journals and conferences including IEEE-TIP, IEEE-TMM, IEEE-TKDE, IEEE-TCSVT, ACM-TKDD, ACM-TIST, and ACMMM, CVPR, ICCV, ECCV, SIGMOD, VLDB, ICDM, CIKM. 

Academic service
Conference services
  • Publication Chair, ACM International Conference on Internet Multimedia Computing and Service (ICIMCS'15), 17th-21th, Aug, 2015, Zhangjiajie, Hunan.
  • PC Co-Chair, 1st International Workshop on Mobility Analytics for Spatio-temporal and Social Data (MATES),VLDB'17, Sept. 1, 2017.
Educational experience
  • 2006.9 ~ 2012.7 Institute of Computing Technology Computer Science PHD
  • 2002.9 ~ 2006.7 Tsinghua University Electronic Engineering Bachelor in Eng.
Research content

1.   Multimodal reasoning and interaction

Focus on cross-modal representation learning, visual-linguistic retrieval, and interactive multimodal QA.

2.   Vision and Multimedia Understanding

Focus on visual learning on large number of categories, domain adaptation and multimodal semantic analytics.

3.   Heterogeneous multimedia big data analytics

Focus on recommendation systems, learning with noisy Web data and community discovery based on content and social context.

4.   Multimodal perception

Focus on knowledge/memory/language guided multimodal perception and representation, and human-like multimodal active perception.
Research project

1.   Research on object modeling and Cross-domain anlysis in heterogeneous big data

Project type: NSFC Project
Project time: 2017.01-2020.12
Project leader: Shuhui Wang
Book or Paper


1.   Siyuan Liu , Shuhui Wang, Qiang Qu. Trajectory Mining. Book chapter of Encyclopedia of GIS, Springer, ISBN: 978-3-319-23519-6 (Online), 2017. 【pdf】


Major Publication (Please see DBLP for full publication list):

1.  Shuhui Wang, Liang Li, Chenxue Yang, Qingming Huang. Regularized Topic-aware Latent Influence Propagation in Dynamic Relational Networks. GeoInformatica, accepted.

2. Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang, Qingming Huang, Qi Tian. SkeletonNet: A Hybrid Network with a Skeleton-Embedding Process for Multi-view Image Representation Learning. IEEE Transactions on Multimedia, accepted.

3. Yiling Wu, Shuhui Wang, Guoli Song, Qingming Huang. Online Asymmetric Metric Learning with Multi-Layer Similarity Aggregation for Cross-Modal Retrieval. IEEE Transaction on Image Processing , accepted. Code

4. Junbao Zhuo, Shuhui Wang, Shuhao Cui, Qingming Huang. Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization. In CVPR, 2019.  PaperCode

5. Zhe Xue, Guorong Li, Shuhui Wang, Weigang Zhang, Qingming Huang. Bilevel Multiview Latent Space Learning. IEEE Trans. Circuits Syst. Video Techn. 28(2): 327-341, 2018.

6. Yangyu Chen, Shuhui Wang, Weigang Zhang, Qingming Huang. Less is More: Picking Informative Frames for Video Captioning. ECCV, 2018. 

7. Shuhui Wang, Yangyu Chen, Junbao Zhuo, Qingming Huang, Qi Tian. Joint Global and Co-Attentive Representation Learning for Image-Sentence Retrieval. ACM Multimedia, 2018. (Oral, Acceptance rate: 8%)

8. Yiling Wu, Shuhui Wang, Qingming Huang. Learning Semantic Structure-preserved Embeddings for Cross-modal Retrieval. ACM Multimedia, 2018. 

9. Liang Li, Shuhui Wang, Shuqiang Jiang, Qingming Huang. Attentive Recurrent Neural Network for Weak-supervised Multi-label Image Classification. ACM Multimedia, 2018. 

10. Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian: Multimodal Similarity Gaussian Process Latent Variable Model. IEEE Trans. Image Processing 26(9): 4168-4181 (2017). Code

11. Jiaming Zhang, Shuhui Wang, Qingming Huang: Location-Based Parallel Tag Completion for Geo-Tagged Social Image Retrieval. ACM TIST 8(3): 38:1-38:21 (2017).

12. Siyuan Liu, Shuhui Wang: Trajectory Community Discovery and Recommendation by Multi-Source Diffusion Modeling. IEEE Trans. Knowl. Data Eng. 29(4): 898-911 (2017). 

13. Yiling Wu, Shuhui Wang, Qingming Huang: Online Asymmetric Similarity Learning for Cross-Modal Retrieval. CVPR 2017: 3984-3993. 

14. Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang, Qingming Huang: A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning. CVPR 2017: 7053-7061.

15. Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian: Multimodal Gaussian Process Latent Variable Models with Harmonization. ICCV 2017: 5039-5047. Code

16. Junbao Zhuo, Shuhui Wang, Weigang Zhang, Qingming Huang: Deep Unsupervised Convolutional Domain Adaptation. ACM Multimedia 2017: 261-269. 

17. Weiqing Min, Shuqiang Jiang, Shuhui Wang, Jitao Sang, Shuhuan Mei: A Delicious Recipe Analysis Framework for Exploring Multi-Modal Recipes with Various Attributes. ACM Multimedia 2017: 402-410. 

18. Lingyang Chu, Yanyan Zhang, Guorong Li, Shuhui Wang, Weigang Zhang, Qingming Huang: Effective Multimodality Fusion Framework for Cross-Media Topic Detection. IEEE Trans. Circuits Syst. Video Techn. 26(3): 556-569 (2016).

19. Yan Hua, Shuhui Wang, Siyuan Liu, Anni Cai, Qingming Huang: Cross-Modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation. IEEE Trans. Multimedia 18(6): 1201-1216 (2016).

20. Shuhui Wang, Fuzhen Zhuang, Shuqiang Jiang, Qingming Huang, Qi Tian: Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval. Neurocomputing 168: 747-760 (2015).

21. Lingyang Chu, Shuhui Wang, Siyuan Liu, Qingming Huang, Jian Pei: ALID: Scalable Dominant Cluster Detection. PVLDB 8(8): 826-837 (2015). 

22. Li Shen, Gang Sun, Qingming Huang, Shuhui Wang, Zhouchen Lin, Enhua Wu: Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification. IEEE Trans. Image Processing 24(10): 3109-3123 (2015). 

23. Siyuan Liu, Qiang Qu, Shuhui Wang: Rationality Analytics from Trajectories. TKDD 10(1): 10:1-10:22 (2015).

24. Siyuan Liu, Shuhui Wang, Feida Zhu: Structured Learning from Heterogeneous Behavior for Social Identity Linkage. IEEE Trans. Knowl. Data Eng. 27(7): 2005-2019 (2015). 

25. Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian: Similarity Gaussian Process Latent Variable Model for Multi-modal Data Analysis. ICCV 2015: 4050-4058. (CCF-A类会议)

26. Yan Hua, Shuhui Wang, Siyuan Liu, Qingming Huang, Anni Cai: TINA: Cross-Modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation. ICDM 2014: 190-199.

27. Siyuan Liu, Shuhui Wang, Feida Zhu, Jinbo Zhang, Ramayya Krishnan: HYDRA: large-scale social identity linkage via heterogeneous behavior modeling. SIGMOD Conference 2014: 51-62. 

28. Lingyang Chu, Shuqiang Jiang, Shuhui Wang, Yanyan Zhang, Qingming Huang: Robust Spatial Consistency Graph Model for Partial Duplicate Image Retrieval. IEEE Trans. Multimedia 15(8): 1982-1996 (2013).

29. Siyuan Liu, Shuhui Wang, Kasthuri Jayarajah, Archan Misra, Ramayya Krishnan: TODMIS: mining communities from trajectories. CIKM 2013: 2109-2118.

30. Li Shen, Shuhui Wang, Gang Sun, Shuqiang Jiang, Qingming Huang: Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization. CVPR 2013: 383-390. 

31. Shuhui Wang, Qingming Huang, Shuqiang Jiang, Qi Tian, Lei Qin: Nearest-neighbor method using multiple neighborhood similarities for social media data mining. Neurocomputing 95: 105-116 (2012).

32. Shuhui Wang, Qingming Huang, Shuqiang Jiang, Qi Tian: S3MKL: Scalable Semi-Supervised Multiple Kernel Learning for Real-World Image Applications. IEEE Trans. Multimedia 14(4): 1259-1274 (2012).

33. Shuhui Wang, Shuqiang Jiang, Qingming Huang, Qi Tian: Multi-feature metric learning with knowledge transfer among semantics and social tagging. CVPR 2012: 2240-2247. 

34. Shuhui Wang, Shuqiang Jiang, Qingming Huang, Qi Tian: S3MKL: scalable semi-supervised multiple kernel learning for image data mining. ACM Multimedia 2010: 163-172. 

Visual Information Processing and Learning
  • Address :No.6 Kexueyuan South Road
  • Zhongguancun,Haidian District
  • Beijing,China
  • Postcode :100190
  • Tel : (8610)62600514
  • Valse

  • Big Lecture of DL

Copyright @ Visual Information Processing and Learning 京ICP备05002829号 京公网安备1101080060