Multimedia analysis: Focusing on visual categorization and cross-media Analysis

Machine learning: Focusing on Kernel Learning, Deep Learning~and Correlation Learning

Web data mining: Social media data mining and retrieval, e.g., social behavior analysis and social identity linkage

​2019:

Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Dechao Meng, Qingming Huang. Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding. ICCV, 2019. Code

Yiling Wu, Shuhui Wang, Guoli Song, Qingming Huang. Learning Fragment Self-Attention Embeddings for Image-Text Matching. ACM Multimedia, pp. 2088-2096, 2019. (oral)  Code

Xuejing Liu, Liang Li, Shuhui Wang, Zhengjun Zha, Li Su, Qingming Huang. Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding. ACM Multimedia, pp. 539-547, 2019. (oral)

Shijie Yang, Liang Li, Shuhui Wang, Dechao Meng, Qingming Huang and Qi Tian. Structured Stochastic Recurrent Network for Linguistic Video Prediction. ACM Multimedia, pp. 21-29, 2019. (oral)

Shuhui Wang, Liang Li, Chenxue Yang, Qingming Huang. Regularized Topic-aware Latent Influence Propagation in Dynamic Relational Networks. GeoInformatica, 23(3): 329-352, 2019. Paper

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, 21(11): pp. 2916-2929, 2019.

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, vol. 28, no. 9, pp. 4299-4312, 2019. Code

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

2018:

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.

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

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%)

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

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

2017:

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

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

2016:

Yan Hua, Shuhui Wang, Siyuan Liu, Anni Cai and Qingming Huang. Cross-modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation. To appear on IEEE Transactions on Multimedia (TMM), 2016.

Lingyang Chu, Yanyan Zhang, Guorong Li, Shuhui Wang, Weigang Zhang, Qingming Huang. Effective multi-modality fusion framework for cross-media topic detection. IEEE Transactions on Circuit System and Video Technologies(TCSVT), vol. 26, no. 3, pp. 556 - 569, 2016.

2015:

Guoli Song, Shuhui Wang, Qingming Huang and Qi Tian. Similarity Gaussian Process Latent Variable Model for Multi-Modal Data Analysis. IEEE International Conference on Computer Vision (ICCV), 2015.

Lingyang Chu, Shuhui Wang, Siyuan Liu, Qingming Huang and Jian Pei. ALID: Scalable dominant cluster Detection. The 41st International Conference on Very Large Data Bases (VLDB), vol. 8, No. 8, 2015, Hawaii, USA.(full version available at: http://arxiv.org/abs/1411.0064)

Siyuan Liu, Shuhui Wang and Feida Zhu. Structured Learning from Heterogeneous Behavior for Social Identity Linkage. IEEE Transactions on Knowledge Discovery and Engineering (TKDE), vol 27, no. 7, pp. 2005-2019, 2015. 

Shuhui Wang, Fuzhen Zhuang, Shuqiang Jiang, Qingming Huang and Qi Tian. Cluster-Sensitive Structured Correlation Analysis for Web Cross Modality Retrieval. Neurocomputing, 168:747-760, 2015. (doi:10.1016/j.neucom.2015.05.049).

Shuhui Wang, Yiling Wu and Qingming Huang. Improving Cross-Modal Correlation Learning by Hyperlinks. ICME, 2015.

Jiaming Zhang, Shuhui Wang and Qingming Huang. Location-Based Parallel Tag Completion for Geo-tagged Social Photo Retrieval. International Conference on Multimedia Retrieval (ICMR), 2015.

Jun Huang, Guorong Li, Shuhui Wang, Weigang Zhang and Qingming Huang. Group Sensitive Classifier Chains for Multi-Label Classification. ICME, 2015.

Zhe Xue, Guorong Li, Shuhui Wang, Chunjie Zhang, Weigang Zhang and Qingming Huang. GOMES: A Group-Aware Multi-View Fusion Approach towards Real-World Image Clustering. ICME, 2015.

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

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

2014:

Shuhui Wang, Zhenjun Wang, Shuqiang Jiang, Qingming Huang.Cross media Topic Analytics Based on Synergetic Content and User Behavior Modeling. ICME, 2014.(oral)

Yan (Tina) Hua, Shuhui Wang, Siyuan Liu, Qingming Huang, Anni Cai. TINA: Cross-modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation. ICDM, 2014. (Regular paper)

Yan (Tina) Hua, Shuhui Wang, Zhicheng Zhao, Qingming Huang and Anni Cai. Cross Modal Metric Learning with Multi-level Semantic Relevance. In ICIP, 2014.

Li Shen, Gang Sun, Shuhui Wang, Enhua Wu and Qingming Huang. Sharing Model with Multi-level Feature Representations. In ICIP, 2014.

Lingyang Chu, Shuhui Wang, Yanyan Zhang, Shuqiang Jiang, Qingming Huang. Graph-Density-Based Visual Word Vocabulary for Image Retrieval. ICME, 2014.

Siyuan Liu, Shuhui Wang, Jinbo Zhang, Feida Zhu, Ramayya Krishnan. HYDRA: Large-scale Social Identity Linkage via Heterogeneous Behavior Modeling. The 41st ACM SIGMOD International Conference on Management of Data. 2014.Snowbird. USA.

Siyuan Liu, Shuhui Wang, and Ramayya  Krishnan. Persistent Community Detection in Dynamic Social Networks. In PAKDD, 2014.

Xinhang Song, Shuqiang Jiang, Shuhui Wang, Liang Li, Qingming Huang. Polysemious Visual Representation Based on Feature Aggregation for Large Scale Image Applications. Multimedia Tools and Application, 74(2):595-611, 2014.

Siyuan Liu, Shuhui Wang, Ce Liu and Ramayya Krishnan. Understanding Taxi Drivers’ Routing Choices from Spatial and Social Traces. Frontier of Computer Science, 2014.

2013:

Chunjie Zhang, Shuhui Wang, Qingming Huang, Jing Liu, Chao Liang, Qi Tian. Image Classification Using Spatial Pyramid Robust Sparse Coding. Pattern Recognition Letters, 34(9): 1046-1052, 2013.

Gang Sun, Shuhui Wang, Xuehui Liu, Qingming Huang, Yanyun Chen, Enhua Wu: Accurate and efficient cross-domain visual matching leveraging multiple feature representations. The Visual Computer 29(6-8): 565-575, 2013. (Acceptance rate: 10%)

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

Chunjie Zhang, Shuhui Wang, Qingming Huang, Jing Liu, Chao Liang, Qi Tian. Laplacian Affine Sparse Coding with tilt and orientation consistency for Image Classification. Journal of Visual Communication and Image Representation, 24(7): 786-793, 2013.

Siyuan  Liu, Shuhui  Wang, Kasthuri  JEYARAJAH, archan  Misra, Ramayya  Krishnan. TODMIS: Mining Communities from Trajectories. ACM CIKM, 2013. (full paper, acceptance rate:17%)

Chunjie Zhang, Yifan Zhang, Shuhui Wang, Junbiao Pang, Chao Liang, Qingming Huang, Qi Tian. Undo the Codebook Bias by Linear Transformation for Visual Applications. ACM Multimedia, 2013.

Chunjie Zhang, Shuhui Wang, Chao Liang, Jing Liu, Qingming Huang, Haojie Li, Qi Tian. Beyond Bag of Words: Image Representation in Sub-semantic Space. ACM Multimedia, 2013.

Xin  Jin, Fuzhen  Zhuang, Shuhui  Wang, Qing He and Zhongzhi Shi. Shared Structure Learning for Multiple Tasks with Multiple Views. ECMLPKDD, 2013. (Regular paper)

Li Shen, Shuhui Wang, Gang Sun, Shuqiang Jiang, Qingming Huang. Multi-Level Discriminative Dictionary Learning towards Hierarchical Visual Categorization. CVPR, 2013.

Wei Xiong, Shuhui Wang, Chunjie Zhang, Qingming Huang. WIKI-CMR: A Web Cross Modality database for Studying and Evaluation of Cross Modality Retrival Methods. ICME, 2013.

Xinhang Song, Shuqiang Jiang, Shuhui Wang, Jinhui Tang and Qingming Huang. Cross Concept Local Fisher Discriminant Analysis for Image Classification. Multimedia Modelling (MMM), 2013.

Yanyan Zhang, Guorong Li, Lingyang Chu, Shuhui Wang, Weigang Zhang, Qingming Huang. Cross-Media Topic Detection: A Multi-Modality Fusion Framework. ICME, 2013. (oral, Best paper candidate)

before 2013:

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

Shuhui Wang, Qingming Huang, Shuqiang Jiang, Qi Tian and Lei Qin. Nearest-Neighbor Method Using Multiple Neighborhood Similarities for Social Media Data Mining. NeuroComputing, 2012: 95(15), 105-116.

Shuhui Wang, Shuqiang Jiang, Qingming Huang and Qi Tian. Multi-feature Metric Learning with Knowledge Transfer among Semantics and Social Tagging. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2012.

Shuhui Wang, Shuqiang Jiang, Qingming Huang and Qi Tian. S³MKL: Scalable Semi-Supervised Multiple Kernel Learning for Image Data Mining. In ACM International Conference on Multimedia, 2010. (full paper, acceptance rate: 16%)

Shuhui Wang, Qingming Huang, Shuqiang Jiang and Qi Tian. Nearest-neighbor Classification Using Unlabeled Data for Real World Image Application. In ACM International Conference on Multimedia, 2010.

Shuhui Wang, Qingming Huang, Shuqiang Jiang and Qi Tian. Efficient L_p-norm Multiple Feature Metric Learning for Image Categorization. In ACM International Conference on Information and Knowledge Management (CIKM), 2011.

Shuhui Wang, Shuqiang Jiang, Qingming Huang and Qi Tian. Multiple Kernel Learning with High Order Kernels. In International Conference on Pattern Recognition (ICPR), 2010. (oral, acceptance rate 10%)

Shuhui Wang, Qingming Huang, Shuqiang Jiang, Lei Qin and Qi Tian. Visual ContextRank for Web Image Re-ranking. In Proceedings of 1st ACM workshop on Large Scale Multimedia Retrieval and Mining, 2009.

Shuhui Wang, Shuqiang Jiang, Qingming Huang and Wen Gao. Shot Classification for Action Movies Based on Motion Characteristics. In International Conference on Image Processing (ICIP), 2008.

Li Shen, Shuqiang Jiang, Shuhui Wang and Qingming Huang. Learning-to-Share Based on Finding Groups for Large Scale Image Classification. In Pacific-Rim Conference on Multimedia (PCM), 2011.

王树徽, 李乐, 章毓晋. 基于Gabor特征的线性降维人脸识别算法的实验比较。第十三届全国图象图形学学术会议论文集，2006，387-391.

已指导学生

辛永健  硕士研究生  085211-计算机技术  

于晟昊  硕士研究生  085211-计算机技术  

魏军  硕士研究生  081203-计算机应用技术  

崔书豪  硕士研究生  081203-计算机应用技术  

闫旭  硕士研究生  081203-计算机应用技术  

薛壮壮  硕士研究生  085211-计算机技术  

韩华侨  硕士研究生  085211-计算机技术  

邓文达  硕士研究生  085211-计算机技术  

魏浩  硕士研究生  085404-计算机技术  

现指导学生

孙隽姝  硕士研究生  081203-计算机应用技术  

蔡硕  硕士研究生  085404-计算机技术  

朱妍  硕士研究生  085410-人工智能  

黄克楠  硕士研究生  085410-人工智能  

李梦莲  硕士研究生  085410-人工智能  

何晓铭  硕士研究生  085410-人工智能  

申树藩  博士研究生  081200-计算机科学与技术  

朱纪龙  硕士研究生  085400-电子信息  

吴悦  博士研究生  081200-计算机科学与技术  

龚琳涵  硕士研究生  085410-人工智能  

裴正奇  硕士研究生  085410-人工智能  

许冰  硕士研究生  085410-人工智能  

徐亮  博士研究生  081200-计算机科学与技术  

刘金哲  博士研究生  081200-计算机科学与技术  

党添添  硕士研究生  081200-计算机科学与技术