王树徽  研究员  

研究员

研究方向:跨媒体推理与交互;图像视频理解;开放域视觉学习

所属部门:智能信息处理重点实验室

导师类别:博导计算机应用技术

联系方式:wangshuhui@ict.ac.cn

个人网页:https://vipl.ict.ac.cn/view_people.php?url=&id=62

简       历:

2020年09月 — 至今:中国科学院计算技术研究所,研究员 

2015年09月 — 2020年09月:中国科学院计算技术研究所,副研究员

2014年10月 — 2015年09月:中国科学院计算技术研究所,助理研究员

2012年08月 — 2014年10月:中国科学院计算技术研究所,博士后

2006年09月 — 2012年07月:中国科学院计算技术研究所,硕博连读(工学博士)

2002年09月 — 2006年07月:清华大学,电子工程系,本科(工学学士)

个人主页:https://vipl.ict.ac.cn/view_people.php?url=&id=62 

国科大个人主页:http://people.ucas.edu.cn/~wangshuhui 

主要论著:

期刊文章:

[1] Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian. Harmonized Multimodal Learning with Gaussian Process Latent Variable Models. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted.

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

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

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

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

[6] 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.

[7] 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.

[8] 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.

 

会议文章:

[1] Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, Qi Tian. Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations. CVPR, 2020. (Oral)

[2] Jun Wei, Shuhui Wang, Qingming Huang. F3Net: Fusion, Feedback and Focus for Salient Object Detection. AAAI, 2020. (Oral)

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

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

[5] 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)

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

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

[8] Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian: Similarity Gaussian Process Latent Variable Model for Multi-modal Data Analysis. ICCV, 4050-4058, 2015.

[9] 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.

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

 

专利:

[1] 国家发明专利:一种基于树结构的图像分类方法及其系统。第一发明人,已授权。

[2] 国家发明专利:一种基于密集子图的视觉词典生成方法及其系统。第四发明人,已授权。

[3] 国家发明专利:基于多模态信息融合与图聚类的跨媒体话题检测方法。第五发明人,已授权

科研项目:

[1] 国家重点研发项目(科技创新2030-新一代人工智能重大项目)子课题:跨媒体分析推理引擎;

[2] 国家自然科学基金面上项目:异构大数据的对象建模及跨域分析技术研究,主持;

[3] 973计划课题:跨媒体语义学习与内容理解,技术骨干;

获奖及荣誉:

担任ACM Multimedia 2019/2020领域主席,ICIMCS、PCM等领域重要会议出版主席,曾获2012年CCF科学技术奖、中科院院长奖等。