• 王文敏

  • 职称:教授
  • 电话:0755-26035700
  • Email:wangwm@pkusz.edu.cn
研究方向:1)计算机视觉;2)多媒体检索;3)人工智能与机器学习。

导师与研究领域、方向:

    1989年3月取得哈工大计算机工学博士学位。攻读博士学位期间曾在《计算机学报》等核心期刊和国际会议发表论文多篇,并获得设立不久、为数不多的1989年度国家自然科学基金青年科学基金。博士毕业后历任哈尔滨理工大学大副教授,哈工大科技开发总公司软件部部长等。

    1992年出国,在国外的十八年间,历任世界500强及日美知名上市公司研究和开发部门的主任研究员、主干研究员、中国区总工、公司唯一最高级资深工程师、开发本部总经理等。主持和参与多个国外重要产品及项目的研究开发。

    2009年底应邀回国,被聘为北京大学深圳研究生院教授,北京大学数字视频编解码国家工程实验室广州研发中心副主任。2011年6月被聘为华南理工大学研究员(教授),2012年3月被任命为北京大学信息工程学院常务副院长(主持工作),2013年9月至2016年3月任北京大学信息工程学院院长。

    回国后主持和参与国家、省、市科技开发项目多项,近几年发表国际重要期刊和会议论文数十篇、申报发明专利数十项。曾获得部、省级科学技术奖4项。担任多个国际期刊及国际会议的审稿人。2014年成为深圳市海外高层次人才团队暨“图像与视频处理研究”孔雀团队核心成员。

    主讲研究生课程:“人工智能”、 “面向对象分析与设计”。

主要科研项目:

1.深圳市海外高层次人才团队(孔雀团队)引进项目,“新一代网络视频处理技术研发”,2014年-2019年,团队核心成员;

2.国家自然科学基金项目,“基于轻量模型的立体视频转换生成与编码技术研究”,2014年-2017年,主要研究人员;

3.深圳市基础研究计划重大培育项目,“互联网3D视频内容生成、编码和云分发关键技术研究”,2012年-2014年,项目负责人。

4.广州市重大科技专项,“AVS 3D云媒体终端软件平台研发及产业化”,2011年-2013年,项目总负责人;

5.省部产学研结合项目,“3D云媒体平台和云终端的研发与产业化”,2011年-2012年,主要研究人员;

6.国家科技支撑计划项目,“基于AVS的3D电视实时编码系统研制与应用示范”,2010年-2012年,主要研究人员;

7.广东省重大科技专项,“AVS高清实时编码器研发及产业化”,2010年-2012年,项目总负责人。

代表性论文:

[1]. Jinzhuo Wang, Wenmin Wang, Ronggang Wang, Wen Gao. Beyond Monte Carlo Tree Search: Playing Go with Deep Alternative Neural Network and Long-Term Evaluation, Association for the Advance of Artificial Intelligence (AAAI), 2017. San Francisco, USA.

[2]. Jinzhuo Wang, Wenmin Wang, Xiongtao Chen, Ronggang Wang, Wen Gao. Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition, Advances in neural information processing systems (NIPS), 2016. Barcelona, Spain.

[3]. Zhenglin Tan, Wenmin Wang, Yifeng Jiang, Ronggang Wang. A Simple but Efficient Way to Combine VLAD with Locality-constrained Linear Coding, IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016. Chengdu, China.

[4]. Ruonan Zhang, Wenmin Wang. An Advanced Local Offset Matching Strategy for Object Proposal Matching, IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016. Chengdu, China.

[5]. Peilei Dong, Wenmin Wang. Better Region Proposals for Pedestrian Detection with R-CNN, IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016. Chengdu, China.

[6]. Ruonan Zhang, Wenmin Wang and Ronggang Wang. An MCMC-based Prior Sub-hypergraph Matching in Presence of Outliers, International Conference on Pattern Recognition (ICPR), 2016. Cancun, Mexico.

[7]. Zhihao Li, Wenmin Wang, Nannan Li, Jinzhuo Wang. Tube ConvNets: Better Exploiting Motion for Action Recognition, IEEE International Conference on Image Processing (ICIP), 2016, pp.3056-3060. Phoenix, USA.

[8]. Ruonan Zhang, Wenmin Wang, Ronggang Wang. A k-Nearest-Neighbor-Pooling Method for Graph Matching, IEEE International Conference on Multimedia and Expo (ICME), 2016. Seattle, USA.

[9]. Mengdi Fan, Wenmin Wang, Ronggang Wang. Coupled Feature Mapping and Correlation Mining for Cross-media. IEEE International Conference on Multimedia and Expo (ICME), 2016. Seattle, USA.

[10].Mingmin Zhen, Wenmin Wang and Ronggang Wang. Regional Subspace Projection Coding for Image Retrieval, accepted as long paper for oral representation in ACM International Conference on Multimedia Retrieval (ICMR), 2016. New York, USA.

[11].Jinzhuo Wang, Wenmin Wang, Ronggang Wang and Wen Gao. CSPS: An adaptive pooling method for Image Classification, accepted for publication in IEEE Transaction on Multimedia (TMM), 2016, 18(6):pp.1000-1010.

[12].Mingmin Zhen, Wenmin Wang and Ronggang Wang. Improving VLAD with Regional PCA Whitening, IEEE International Conference on Visual Communications and Image Processing (VCIP), 2015. Singapore.

[13].Zi’ou Zheng, Wenmin Wang and Ronggang Wang. Weighted Transformable Spatial Pyramid and Scalable Query for Object Retrieval, IEEE International Conference on Visual Communications and Image Processing (VCIP), 2015. Singapore.

[14].Yang Zhao, Ronggang Wang, Wenmin Wang and Wen Gao. High Resolution Local Structure Constrained Image Upsampling. IEEE Transaction on Image Processing (TIP), 2015, 24(11): pp.4394-4407.

[15].Jinzhuo Wang, Wenmin Wang, Ronggang Wang and Wen Gao. Image Classification Using RBM to Encode Local Descriptors with Group Sparse Learning, IEEE International Conference on Image Processing (ICIP), 2015, pp.912-916. Quebec City, Canada.

[16].Jinzhuo Wang, Wenmin Wang, Ronggang and Wen Gao. A Compact Shot Representation for Video Semantic Indexing, IEEE International Conference on Image Processing (ICIP), 2015, pp.3265-3269. Quebec City, Canada.

[17].Mingmin Zhen, Wenmin Wang, Ronggang Wang. Improved Cluster Center Adaption for Image Classification, IEEE International Conference on Image Processing (ICIP), 2015, pp.3092-3095. Quebec City, Canada.

[18].Longfei Gao, Shengfu Dong, Wenmin Wang, Ronggang Wang and Wen Gao. A Novel Integer-Pixel Motion Estimation Algorithm based on Quadratic Prediction, IEEE International Conference on Image Processing (ICIP), 2015. Quebec City, Canada.

[19].Jinzhuo Wang, Wenmin Wang, Ronggang Wang and Wen Gao. Learning Class-Specific Pooling Sharp for Image Classification. IEEE International Conference on Multi Media & Expo (ICME), 2015. Torino, Italy.

[20].Yingli Wei, Wenmin Wang and Ronggang Wang. An Improved Averaging Combination Method for Image and Object Recognition. Workshop on Distributed and Cooperative Visual Recognition and Analysis (DCVRA), IEEE International Conference on Multi Media & Expo (ICME), 2015. Torino, Italy.

[21].Mingmin Zhen, Wenmin Wang and Ronggang Wang. Signature of Unique Angles Histograms for 3D Data Description. Workshop on Hot Topics in 3D Multimedia (Hot3D), IEEE International Conference on Multi Media & Expo (ICME), 2015. Torino, Italy.

[22].Ying Huang, Wenmin Wang and Rong Wang. Learning discriminative visual dictionary for natural scene categorization. IEEE 40th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015, pp.1329-1333. Brisbane, Australia.

[23].Longfei Gao, Shengfu Dong, Wenmin Wang and Wen Gao, Fast Intra Mode Decision Algorithm Based on Refinement in HEVC, IEEE International Symposium on Circuits and Systems (ISCAS), 2015, pp.517-520. Lisbon, Portugal.

[24].Yang Zhang, Yunqing Xia, Yi Liu and Wenmin Wang. Clustering Sentences with Density Peaks for Multi-document Summarization. The 2015 Annual Conference of the North American Chapter of the ACL (NAACL). 2015, pp.1262-1267. Denver, USA.

[25].Zhenyu Wang, Shengfu Dong, Ronggang Wang, Wenmin Wang and Wen Gao, Dynamic macroblock wavefront parallelism for parallel video coding. Journal of Visual Communication and Image Representation, 2015, 28, pp. 36-43.      

[26].Qinshui Chen, Wenmin Wang and Rong Wang. An approach to support stereoscopic 3D web. 29th Annual ACM Symposium on Applied Computing (SAC), 2014, pp. 981-984. Gyeongju, Korea.

[27].Zhongxin Liu, Wenmin Wang and Rong Wang, Incremental multi-manifold out-of-sample data prediction, in IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 2014, pp. 313-338. Warsaw, Poland.

[28].Jianbo Jiao, Ronggang Wang, Wenmin Wang, Shengfu Dong, Zhenyu Wang, and Wen Gao. Local stereo matching with improved matching cost and disparity refinement. IEEE Multimedia, 2014, 21(4): pp. 16-27.

[29].Wenmin Wang, Shengfu Dong, Ronggang Wang, Qinshui Cheng, Jianlong Zhang, Zhongxin Liu. Stereoscopic 3D Web: From idea to implementation, International Conference on Information Science, Electronics & Electrical Engineering (ISEEE), 2014, pp. 3:1440-1444. Sapporo, Japan.

[30].Zhongxin Liu, Wenmin Wang and RonggangWang, The design and implementation of stereoscopic 3D scalable vector graphics based on WebKit. 25th Stereoscopic Displays and Applications Conference XXV, SPIE, 2014, pp. 90111R:1-7. San Francisco, USA.

[31].Qinshui Chen, Wenmin Wang and Ronggang Wang, The rendering context for stereoscopic 3D web. 25th Stereoscopic Displays and Applications Conference XXV, SPIE, 2014, 90111P:1-7. San Francisco, USA. pp.

[32].Jianlong Zhang, Wenmin Wang, Ronggang Wang, et al. A rendering approach for stereoscopic web pages. Proc. SPIE 9011, Stereoscopic Displays and Applications XXV, SPIE, 2014, pp. 90111O:1-7. San Francisco, USA.