西安交通大学电子与信息工程学院导师教师师资介绍简介-王进军

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

本站小编 Free考研考试/2021-06-26

欢迎来到王进军教授的学校主页 - 王进军基本信息

姓名：
王进军

任职：
教授，博士生导师

学位：
博士

单位：
西安交通大学电信学院自动化科学与

技术系

方向：
模式识别、机器学习、机器视觉、多

媒体计算

地址：
西安交通大学曲江校区西四楼307室

电话：

传真：

邮箱：
查看邮箱

推荐链接
类别/站点
西安交通大学
西安交通大学电信学院
西安交通大学研究生院
西安交通大学人工智能与机器人研究所

站点计数器

新闻
论文"Hierarchical and Interactive Refinement Network..."被期刊TIP录用
2020-09-21

论文"Hierarchical U-shape Attention Network for Salient Object Detection"被期刊TIP录用
2020-07-06

论文"Meta Corrupted Pixels Mining for Medical Image Segmentation"被MICCAI 2020录用
2020-06-22

论文"Discriminative Feature Learning with Foreground Attention for Person Re-identification"被期刊TIP录用
2019-03-20

论文"Semi-Supervised Person Re-Identification using Multi-View Clustering"被期刊PR录用
2018-11-16

“跨摄像头指定行人追踪”比赛成功夺冠
2018-08-30

更多新闻>>

个人简介
王进军教授2008年在新加坡南洋理工大学获得计算机工程博士学位。自2006年到2013年，他先后在美国硅谷的NEC研究院、美国Epson研发院等担任研究员和高级研究员。2013年2月，王进军教授加入西安交通大学电信学院自动化科学与技术系人工智能与机器人研究所。
王进军教授是多媒体计算与模式识别领域非常活跃的国际****。他在多模态体育视频复杂场景分析、图像特征向量优化、图像分辨率增强、时间序列信号分析等研究方向上提出了多项创新的理论方法与关键技术方案，成为许多后续研究的理论扩充及比较对象。王进军教授编写英文著作1部，在国际知名学术期刊IEEE T-MM和顶级国际会议CVPR、IJCAI、ACM MM等上发表学术论文70余篇，代表性论文被他引7000多次，单篇最高他引超过1800次。王进军教授已获授权美国发明专利14项，中国发明专利3项。王进军教授获得过2项NEC公司奖和1项微软亚洲奖，其所在团队在图像视频领域最具影响力的国际比赛TRECVID Event Detection（2009）和PASCAL VOC（2009）中获得冠军。
王进军教授的研究方向主要包括：模式识别、计算机视觉、多媒体计算和机器学习。在计算机视觉方向，王进军教授提出的图像特征表达算法，被广泛的引用并运用于解决图像分类、人物动作识别、图像超分辨率等问题。这些问题是对图像或视频数据进行检索/匹配/语义理解/增强等实际应用中的关键问题。在多媒体计算方面，王进军教授是国际上早期从事视频/音频/文本多模态进行体育视频检索的****之一。他和团队开发了实时体育视频检索技术，与ESPN（美国）、新加坡电信（新加坡）、NEC（中国）、Intel（中国）等企业有长期深入的学术及商业合作。在机器学习方面，王进军教授提出了多种基于图论模型的结构数据学习算法，用于解决图像超分辨率、人物动作序列识别、人物表情识别、驾驶安全度预测、机械手动作模仿等问题。王进军教授曾组织过Pattern Recognition期刊专题，主办过ICIP、ICME、MMM、PCM等会议专题，担任过ICIP、ICPR、ICME、ICIMCS等会议的专题主席或公共关系主席，并长期担任T-MM、T-IP、T-CSVT、CVIU等期刊以及ACM MM、ACM CIVR、ICME、3DTV等会议的审稿人。
Google对王进军教授的评价：scholar.google.com/citations
实验室对王进军教授的介绍：http://www.aiar.xjtu.edu.cn/yanjiusuochengyuan.htm

个人经历
教育
新加坡南洋理工大学

2008年5月
新加坡南洋理工大学计算机工程学院，工学博士（PhD）

华中科技大学

2003年7月
华中科技大学电信系通讯与信息系统专业，工学硕士

2000年7月
华中科技大学电信系通信工程专业，工学学士

工作
西安交通大学

2014年6月博士生导师

2013年2月
教授，西安交通大学电信学院自动化科学与技术系人工智能与机器人研究所

Epson Research and Development Inc.

2010年
高级研究员（Senior Research Scientist）

Akiira Media System

2009年
高级研究员（Senior Research Scientist）

NEC Laboratories America Inc.

2006年
研究员（Research Scientist）

荣誉
2019年获得“第一届中国研究生人工智能创新大赛”全国三等奖
2018年获得“全国研究生智慧城市技术与创意设计大赛”优秀指导教师（跨摄像头重识别分项冠军）
2014年博康杯“全国研究生智慧城市技术与创意设计大赛”优秀指导教师（视频分析技术项目多项冠亚军）
Pascal VOC 2009国际图像类别挑战竞赛。以精度超过第二名5%的绝对优势取得图像分类方向冠军（http://www.comp.leeds.ac.uk/me/VOC2009/prelimreszhong中Classification Results）
TRECVID 2009视频检索领域的权威国际评测。获得事件检测方向冠军（www-nlpir.nist.gov/projects/tvpubs/tv9.slides/tv9.ed.slides.pdf）
NEC美国研发院2009年Seed project 奖：“Intelligent Content Augmentation”（NEC美国研发院每年颁发给最具有创新性的团队之一）
NEC美国研发院2007年Seed project 奖：The Beauty project”（NEC美国研发院每年颁发给最具有创新性的团队之一）
Microsoft Research Asia Fellowship奖2005。（2005年全新加坡两名得奖者之一，新加坡南洋理工大学唯一获奖者，被南洋理工大学评价为“具有潜力成为未来的学术带头人”）

论文专利 - 王进军论文与专利
Patent
Jinjun Wang, Wei Xu, Yihong Gong, “REAL-TIME DRIVING DANGER LEVEL PREDICTION”, US patentUS**
Jinjun Wang, Shenghuo Zhu, Yihong Gong, "MONITORING DRIVING SAFETY USING SEMLSUPERVISED SEQUENTIAL LEARNING", US patentUS**
Jinjun Wang, Fengjun Lv, Kai Yu, "LOCALITY-CONSTRAINED LINEAR CODING SYSTEMS AND METHODS FOR IMAGE CLASSIFICATION", US patentUS**
Jinjun Wang, Shenghuo Zhu, Yihong Gong,"SYSTEMS AND METHODS FOR RESOLUTION-INVARIANT IMAGE REPRESENTATION", US patentUS**
Xi Zhou, Jinjun Wang, Fengjun Lv, Kai Yu, "FAST IMAGE PARSING BY GRAPH ADAPTIVE DYNAMIC PROGRAMMING (GADP) PERFORMING CLASSIFICATION, DETECTION, AND SEGMENTATION SIMULTANEOUSLY" US patentUS**
Jinjun Wang, Jing Xiao, "SMALL VEIN IMAGE RECOGNITION AND AUTHORIZATION USING CONSTRAINED GEOMETRICAL MATCHING AND WEIGHTED VOTING UNDER GENERIC TREE MODEL", US patentUS**
Jinjun Wang, Jing Xiao,"EMBEDDED OPTICAL FLOW FEATURES", US patentUS**
Jinjun Wang, Jing Xiao,"CONTINUOUS LINEAR DYNAMIC SYSTEMS", US patentUS**
Jinjun Wang, Jing Xiao,"CONFIDENCE BASED VEIN IMAGE RECOGNITION AND AUTHENTICATION", US patentUS**
Jinjun Wang, Jing Xiao,"POINT SET MATCHING WITH OUTLIER DETECTION", US patentUS**
Jinjun Wang, Jing Xiao,"SPARSE CODING BASED SUPERPIXEL REPRESENTATION WITH HIERARCHICAL CODEBOOK CONSTRUCTION AND INDEXING", US patentUS**
Jinjun Wang, Jing Xiao, Yuanyuan Ding,"COMPUTER VISION METHODS AND SYSTEMS TO RECOGNIZE AND LOCATE AN OBJECT OR OBJECTS IN ONE OR MORE IMAGES", US patentUS**
Jinjun Wang, Jing Xiao,"SUBSTRUCTURE AND BOUNDARY MODELING FOR CONTINUOUS ACTION RECOGNITION", US patentUS**
龚怡宏, 王进军, 张顺, 王泽伦, "一种迭代更新轨迹模型的多目标跟踪方法", 中国专利,CN 4
张世周, 王进军, 龚怡宏, 石伟伟, "基于归一化非负稀疏编码器的图像快速特征表示方法", 中国专利 CN 9(pending)
龚怡宏, 石伟伟, 王进军, 张世周, ""基于线性判别分析准则的改进卷积神经网络性能的方法", 中国专利 CN 9(pending)
王进军, 张世周, 龚怡宏, 石伟伟, "基于多线索归一化非负稀疏编码器的图像快速特征表示方法", 中国专利 CN 7(pending)
王进军, 石伟伟, 龚怡宏, 张世周, "基于码书块稀疏的非负稀疏编码的图像特征提取方法", 中国专利 CN 20**(pending)
石伟伟, 王进军, 龚怡宏, 张世周, "基于结构相似度的非负稀疏编码的图像分类方法", 中国专利 CN 2(pending)
龚怡宏, 张世周, 王进军, 石伟伟, "基于L21范数的提升卷积神经网络泛化能力的方法", 中国专利 CN 4(pending)
Edited book
Jinjun Wang, Jian Cheng, Shuqiang Jiang, “Computer Vision for Multimedia Applications: Methods and Solutions”, 1^nd Edition, published by IGI Global, DOI: 10.4018/978-1-60960-024-2, ISBN13: 42, ISBN10: X, EISBN13: 66, October, 2010. 354 pages
Book chapter
Jinjun Wang, Yihong Gong, "Female Facial Beauty Attribute Recognition and Editing", "Human-Centered Social Media Analytics", ISBN: 978-3-319-05490-2, Springer, 2014
Jinjun Wang, “Multi-Scale Exemplary Based Image Super-Resolution with Graph Generalization”, "Graph-?Based Methods in Computer Vision", ISBN13: 16, IGI Global, 2011.
Jinjun Wang, Yihong Gong, “Image and Video Super Resolution Techniques”, Encyclopedia of Multimedia, 2nd Edition (Book chapter), ISBN: 978-0-387-78415-1, pp 309-318, 2010
Journal
Sanping Zhou, Jinjun Wang*, Le Wang, Jimuyang Zhang, Fei Wang, Dong Huang, Nanning Zheng, "Hierarchical and Interactive Refinement Network for Edge-Preserving Salient Object Detection", IEEE Transactions on Image Processing, September 2020
Sanping Zhou, Jinjun Wang, Jimuyang Zhang, Le Wang, Dong Huang, Shaoyi Du, Nanning Zheng, "Hierarchical U-shape Attention Network for Salient Object Detection", IEEE Transactions on Image Processing, July 2020
Xiaomeng Xin, Jinjun Wang*, Ruji Xie, Sanping Zhou, Wenli Huang, NanningZheng, "Semi-supervised person re-identification using multi-view clustering", Pattern Recognition, Volume 88, Pages 285-297, April 2019
Sanping Zhou, Jinjun Wang*, Deyu Meng, Xiaomeng Xin, Nanning Zheng, "Deep self-paced learning for person re-identification", Pattern Recognition, Pages 739-751, Volume 76, April 2018
Jiayun Wang, Sanping Zhou, Jinjun Wang*, Qiqi Hou, "Deep ranking model by large adaptive margin learning for person re-identification", Pattern Recognition, Volume 74, Pages 241-252, February 2018
Qiqi Hou, Jinjun Wang*, Ruibin Bai, Sanping Zhou, Yihong Gong, "Face alignment recurrent network", Pattern Recognition, Volume 74, Pages 448-458, February 2018
De Cheng, Yihong Gong,Jinjun Wang, Nanning Zheng, “Balanced Mixture of Deformable Part Models with Automatic Part Configurations”, IEEE Trans. on Circuits and Systems for Video Technology, Volume: 27, Issue: 9, Page(s): 1962-1973, Sept. 2017
Sanping Zhou, Jinjun Wang*, Rui Shi, Qiqi Hou, Yihong Gong, Nanning Zheng, "Large Margin Learning in Set to Set Similarity Comparison for Person Re-identi?cation", IEEE Trans. Multimedia, Vol. 18, Pages 1-11, Aug. 2017
Weiwei Shi, Yihong Gong, Xiaoyu Tao,Jinjun Wang, Nanning Zheng. "Improving CNN Performance Accuracies with Min-Max Objective". IEEE Trans. on Neural Networks and Learning Systems, Volume: PP, Issue: 99, Page(s): 1-14, June 2017
Shizhou Zhang,Jinjun Wang*, Xiaoyu Tao, Yihong Gong and Nanning Zheng, “Constructing Deep Sparse coding Network for Image classification”. Pattern Recognition, Vol. 64, Pages 130-140, April 2017
Yudong Liang,Jinjun Wang*, Yihong Gong and Nanning Zheng, “Incorporating Image Priors with Deeonvolutional Neural Networks for Image Super-Resolution”, Neurocomputing, Volume 194, Pages 340-347, June 2016
Sanping Zhou,Jinjun Wang*,Shun Zhang,Yudong Liang,Yihong Gong, “Active contour model based on local and global intensity information for medical image segmentation”, Neurocomputing, Volume 186, Pages 107-118, April 2016
Huaizu Jiang,Jinjun Wang*, Yihong Gong, Na Rong, Zhenhua Chai, Nanning Zheng, "Online Multi-Target Tracking With Unified Handling of Complex Scenarios", IEEE Transactions on Image Processing, Volume: 24, Issue: 11, Nov. 2015
W. Lin, Y. Zhang, J.Lu, B. Zhou, J. Wang, Y. Zhou, "Summarizing Surveillance Videos with Localpatch-learning-based Abnormality Detection, Blob Sequence Optimization, and Type-based Synopsis,"Neurocompting, Volume 155, Pages 84-98, May 2015
Jinjun Wang, Jing Xiao, Weiyao Lin and Chuanfei Luo, "Discriminative and Generative Vocabulary Tree With Application to Vein Image Authentication and Recognition", Image and Vision Computing, Volume 34, Pages 51-62, February 2015
De Cheng,Jinjun Wang*, Xing Wei, Yihong Gong, “Training Mixture of Weighted SVM for Object Detection Using EM Algorithm”, Nurocomputing, Volume 149, Part B, 3,Pages 473-482,February 2015
Shun Zhang,Jinjun Wang*, Zelun Wang, Yihong Gong and Yuehu Liu, “Multi-Target Tracking by Learning Local-to-Global Trajectory Models”, Pattern Recognition,vol. 48, issue 2, pp 580–590, 2015
Shizhou Zhang,Jinjun Wang*, Yihong Gong, Shun Zhang, Xinzi Zhang, Xuguang Lan, “Image Parsing by Loopy Dynamic Programming”, Neurocomputing, Volume 145, Pages 240-249, December 2014
Jinjun Wang, Yihong Gong, “Discovering Image Semantics in Codebook Derivative Space", IEEE Trans. on Multimedia, vol.14, issue.4, pp 986-994, August 2012
Jinjun Wang, Shenghuo Zhu, “Resolution-invariant coding for continuous image super resolution", Neurocomputing,vol. 82, pp 21-28, April 2012
Jinjun Wang, Wei Xu, Yihong Gong, “Real-time Driving Danger-Level Prediction”. Engineering Applications of Artificial Intelligence, vol. 23, issue 8,pp 1247–1254,December 2010
Jinjun Wang, Shenghuo Zhu, Yihong Gong, “Resolution Enhancement based on Learning the Sparse Association of Image Patches”. Pattern Recognition Letter, vol 31, issue 1, pp 1-10, 2010.
Jinjun Wang, Shenghuo Zhu, Yihong Gong, “Driving Safety Monitoring using Semi-Supervised Learning on Time Series Data”. IEEE Trans. on Intelligent Transportation Sys., vol 10, no. 3, pp728-737, 2010
Feng Liu, Jinjun Wang, Shenghuo Zhu, Michael Gleicher, Yihong Gong, “Visual-Quality Optimizing Super Resolution”, Computer Graphics Forum, vol 0 (1981), no 0, pp 1–14, 2008.
Changsheng Xu, Jinjun Wang, Hanqing Lu, Yifan Zhang, “A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video”, IEEE Trans. on Multimedia,vol. 10,no. 3,pp. 421-436, 2008
Jinjun Wang, Changsheng Xu, Engsiong Chng, Qi Tian and Hanqing Lu, “Automatic Composition of Broadcast Soccer Video”, ACM MultiMedia System Journal, 2008
Jinjun Wang, Engsiong Chng, Changsheng Xu, Hanqing Lu and Qi Tian, “Generation of Personalized Music Sports Video using Multimodal Cues”, IEEE Trans. on Multimedia, vol. 9, issue 3, pp 576-588, April 2007.
Benxiong Huang and Jinjun Wang, “Echo canceller based on improved PNLMS and quick correlation DTD algorithms”, Journal of Huazhong University of Science and Technology (Nature Science Edition), vol 32, no 6, pp 4-6, 2004
Conference
Jixin Wang, Sanping Zhou, Chaowei Fang, Le Wang, Jinjun Wang, "Meta Corrupted Pixels Mining for Medical Image Segmentation",MICCAI 2020
Ye Deng, Jinjun Wang, Xi’an Jiaotong University, China, "Image Inpainting using Parallel Network", ICIP 2020
Mengliu Li, Han Xu, Jinjun Wang, Wenpeng Li, Yongli Sun, "Temporal Aggregation with Clip-level Attention for Video-based Person Re-identification" , WACV 2020
Ruibin Bai, Jinjun Wang, Sanping Zhou, "Continuous Action Recognition and Segmentation in Untrimmed Videos", ICPR 2018
Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong, Nanning Zheng, "Point to Set Similarity Based Deep Feature Learning for Person Re-Identification", CVPR, 2017
De Cheng, Yihong Gong, Sanping Zhou,Jinjun Wang, Nanning Zheng, “Person Re-Identification by Multi-Channel Parts-BaseNN with Improved Triplet Loss Function” CVPR, 2016
Shun Zhang, Yihong Gong, Jia-Bin Huang, Jongwoo Lim, Jinjun Wang, Narendra Ahuja, Ming-Hsuan Yang, “Tracking Persons-of-Interest via Adaptive Discriminative Features”, ECCV, 2016
Yudong Liang, Jinjun Wang, Xingyu Wan, Yihong Gong, Nanning Zheng, “Image Quality Assessment Using Similar Scene as Reference”, ECCV, 2016
Shizhou Zhang, Yihong Gong, Jinjun Wang, “Improving DCNN Performance with Sparsategory-Selective Objective Function”, IJCAI, 2016
Shun Zhang, Yihong Gong, Jinjun Wang, “Deep Metric Learning with Improved Triplet Loss for Faclustering in Videos”, PCM, 2016
Weiwei Shi, Yihong Gong, and Jinjun Wang, “Integrating Supervised Laplacian Objective witNN for Object Recognition”, PCM, 2016
Sanping Zhou, Jinjun Wang, Yihong Gong, “Deep Ranking Model for Person Re-identification with Pairwise Similaritomparison”, PCM, 2016
Xiaoyu Tao, Yihong Gong, Jinjun Wang, “A DeeNN with Focused Attention Objective for Integrated Object Recognition and Localization”, PCM, 2016
Yudong Liang, Jinjun Wang, Ze Yang, Yihong Gong and Nanning Zhen, “Learning qualitative and quantitative image quality assessment”, PCM, 2016
Shizhouzhang, yihong gong, jinjun wang and nanning zheng, “A Biologically Inspired DeeNN Model”, PCM, 2016
Ruibin Bai, Qiqi Hou, Jinjun Wang, and Yihong Gong, “Facial Animation Based on 2D Shape Regression”, PCM, 2016
Shi W., Gong Y., Wang J., “ImprovinNN Performance with Min-Max Objective, Proceedings of the Twenty-Fifth International Joinonference on Artificial Intelligence” ，IJCAI, 2016
De Cheng, Jinjun Wang, Xing Wei,Nan Liu, Shizhou Zhang, Yihong Gong, Nanning Zheng,“Cascade object detection with complementary features and algorithms”,IEEE Conference on Semantic Computation, 2015
Nan Liu,Jinjun Wang,Yihong Gong,“Deep Self-Organizing Map for Visual Classification”，International Joint Conference on Neural Networks, 2015.
Qiqi Hou, Jinjun Wang, Lele Cheng, Yihong Gong，“Facial Landmark Detection Via Cascade Multi-Channel Convolutional Neural Network”, ICIP, 2015.
Lele Cheng, Jinjun Wang, Yihong Gong, Qiqi Hou, “Robust Deep Auto-encoder for Occluded Face Recognition”, ACM Multimedia Conference,2015.
Zhang Shizhou, Wang Jinjun, Liang Yudong, Gong Yihong and Nanning Zheng,“Multi-cue Normalized Non-Negative Sparse Encoder for image classification”, International Conference on Multimedia & Expo, 2015.
Shi Dahu, Zhang Shun, Wang Jinjun, Gong Yihong, “Detection and Association based Multi-target Tracking in Surveillance Video”, IEEE International Conference on Multimedia Big Data (BigMM), 2015.
Shun Zhang, Jinjun Wang, Yihong Gong, Shizhou Zhang, “Free Hand Gesture with “Touchable” Virtual Interface forHuman-3DTV Interface” 3DTV-CON, 2015.
Yudong Liang, Jinjun Wang ,Shizhou Zhang , Yihong Gong, “Incorporating Image Degeneration Modeling With Multitask Learningfor Imagesuper-Resolution”, ICIP, 2015.
Qiqi Hou, Lunxin Mou,Jinjun Wang, Yihong Gong,“Virtual Face Transplant in Video”, IWVCC,2015.
Weiwei Shi, Jinjun Wang, Yihong Gong, “Sparse Coding Based on Group-Sparsity Dictionary for Image Classification”, IWVCC, 2015.
Lele Cheng, Xiaoyu Tao, Jinjun Wang, Yihong Gong ,“Double-Channel Deep Denoising Auto-Encoder for Facial Expression Recognition”, IWVCC，2015.
Xinzi Zhang,Jinjun Wang, Yihong Gong, Shizhou Zhang, Shun Zhang, et al, "Low Computation Face Verification using Class Center Analysis”, in Proc. of International Conference on Pattern Recognition 2014 (ICPR'14)
Yudong Liang, Jinjun Wang, Shizhou Zhang, Yihong Gong, Learning Visual Co-Occurrence with Auto-Encoder for Image Super-Resolution, In Proceeding of APSIPA 2014
Yang Zhou, Weiyao Lin, Hang Su, Jianxin Wu, Jinjun Wang, Yu Zhou, "Representing and Recognizing Motion Trajectories: A Tube and Droplet Approach", in Proc. of ACM Multimedia 2014 (ACM MM'14), Orlando, FL, USA, 2014
Jinjun Wang, Jing Xiao, "Human behavior segmentation and recognition using Continuous Linear Dynamic System", IEEE Conference on Application of Computer Vision (WACV'13), Tampa, USA, 2013
Jinjun Wang, Jing Xiao, "Discriminative and generative vocabulary tree for vein image recognition", in Proc. of International Conference on Pattern Recognition 2012 (ICPR’ 12), Tsukuba, Japan, 2012
Zhaowen Wang, Jinjun Wang, Jing Xiao, Thomas Huang, “Substructure and Boundary Modeling for Continuous Action Recognition”, IEEE Conference on Computer Vision and Pattern Recognition 2012 (CVPR’ 12), Rhode Island, USA, 2012
Min-hsuan Tsai，Jinjun Wang, Tong Zhang, Yihong Gong, Thomas Huang, “Learning the image semantic at Large-Scale”, in Proc. of IEEE Conference on Image Processing (ICIP’11), Brussels, Belgium, 2011
Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, “Locality-constrained Linear Coding for Image Classification”, in Proc. of IEEE Conference on Computer Vision and Pattern Recognition 2010 (CVPR’ 10), San Francisco, USA, 2010
Jinjun Wang, Shenghuo Zhu, Yihong Gong, “Resolution-Invariant Image Representation and Its Applications”, in Proc. of IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR’ 09), Florida, USA, 2009
Jinjun Wang, Shenghuo Zhu, Yihong Gong, “Resolution-Invariant Image Representation For Content-Based Zooming”, in Proc. of IEEE International Conference on Multimedia Expo 2009 (ICME’ 09), Cancun, Mexico, 2009
Jinjun Wang, Yihong Gong, “Normalizing Multi-Subject Variation For Drivers’ Emotion Recognition”, in Proc. of IEEE International Conference on Multimedia Expo 2009 (ICME’ 09), Cancun, Mexico, 2009
Jinjun Wang, Yihong Gong, “Recognition of multiple drivers' emotional state”, in Proc. of International Conference on Pattern Recognition 2008 (ICPR’ 08), Florida, USA, 2008
Jinjun Wang, Yihong Gong, “Fast Image Super-Resolution Using Connected Component Enhancement”, in Proc. of IEEE International Conference on Multimedia Expo 2008 (ICME’ 08), Hannover, Germany, 2008
Feng Liu, Jinjun Wang, Shenghuo Zhu, Michael Gleicher, Yihong Gong, “Noisy video super-resolution” , in Proc. of ACM Multimedia 2008 (ACM MM’08), Vancouver, Canada, 2008
Jinjun Wang, Wei Xu, Shenghuo Zhu, Yihong Gong, “Efficient Video Object Segmentation by Graph-Cut”, in Proc. of IEEE International Conference on Multimedia Expo 2007 (ICME’ 07), Beijing, China, July 2007
Jinjun Wang, Changsheng Xu and Engsiong Chng, “Automatic Sports Video Genre Classification using Pseudo-2D-HMM”, in Proc. of International Conference on Pattern Recognition 2006 (ICPR’06), Hong Kong, China, August, 2006
Changsheng Xu, Jinjun Wang, Kongwah Wan, Yiqun Li and Linyu Duan, “Live Sports Event Detection Based on Broadcast Video and Web-casting Text", in Proc. of ACM Multimedia 2006 (ACM MM'06), pp221-230, Santa Barbara, USA, October, 2006
Jinjun Wang, Engsiong Chng, Changsheng Xu, Hanqing Lu and Xiaofeng Tong, “Identify Sports Video Shots With ‘Happy’ or ‘Sad’ Emotions”, in Proc. of IEEE International Conference on Multimedia And Expo 2006 (ICME’06), Toronto, Canada, July, 2006
Jinjun Wang, Engsiong Chng and Changsheng Xu, “Fully and Semi-Automatic Music Sports Video Composition”, in Proc. of IEEE International Conference on Multimedia And Expo 2006 (ICME’ 06), Toronto, Canada, July, 2006
Changsheng Xu, Jinjun Wang, Qi Tian and Hanqing Lu, “Sports Video Personalization for Consumer Products”, in Proc. of IEEE International Conference on Consumer Electronics 2006 (ICCE’06) Las Vegas, USA, 2006.
Jinjun Wang, Changsheng Xu, Engsiong Chng, Linyu Duan, Kongwah Wan and Qi Tian, “Automatic Generation of Personalized Music Sports Video”, in Proc. of ACM Multimedia 2005 (ACM MM'05), pp 735-744, Singapore, 2005
Xiaofeng Tong, Linyu Duan, Changsheng Xu, Hanqing Lu, Jinjun Wang and Jesse J. Jin, “Periodicity Detection of Local Motion”, in Proc. of IEEE International Conference on Multimedia And Expo 2005 (ICME’ 05), Amsterdam, Netherlands, July, 2005
Jinjun Wang, Engsiong Chng and Changsheng Xu, “Soccer Replay Detection using Scene Transition Structure Analysis”, in Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing 2005 (ICASSP’ 05), vol. 2, pp. 433-436 Pennsylvania, USA, March 2005
Kongwah Wan, Jinjun Wang, Changsheng Xu and Qi Tian, “Automatic Sports Highlights Extraction with Content Augmentation”, in Proc. of IEEE Pacific-Rim Conference on Multimedia 2004 (PCM’ 04), vol. 3332, pp. 19-26. Tokyo, Japan, Dec. 2004
Jinjun Wang, Changsheng Xu, Engsiong Chng, Kongwah Wah and Qi Tian, “Automatic Replay Generation for Soccer Video Broadcasting”, in Proc. of ACM Multimedia 2004 (ACM MM'04), pp 32-39, New York, USA, 2004
Jinjun Wang, Changsheng Xu, Engsiong Chng, Xinguo Yu and Qi Tian, “Event Detection Based on Non-Broadcast Sports Video”, in Proc. of IEEE International Conference on Image Processing 2004 (ICIP’ 04), pp. 1637-1640, Singapore, 2004
Jinjun Wang, Changsheng Xu, Engsiong Chng and Qi Tian, “Sports Highlight Detection from Keyword Sequences using HMM”, in Proc. of IEEE International Conference on Multimedia And Expo 2004 (ICME’04), Taipei, China, June 2004

科研工作简介 - 王进军主要研究项目
跨摄像头行人再识别
Point to Set Similarity Based Deep Feature Learning for Person Re-identification Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong, Nanning Zheng
CVPR, 2017
Person re-identification (Re-ID) remains a challenging problem due to significant appearance changes caused by variations in view angle, background clutter, illumination condition and mutual occlusion. To address these issues, conventional methods usually focus on proposing robust feature representation or learning metric transformation based on pairwise similarity, using Fisher-type criterion. The recent development in deep learning based approaches address the two processes in a joint fashion and have achieved promising progress. One of the key issues for deep learning based person Re-ID is the selection of proper similarity comparison criteria, and the performance of learned features using existing criterion based on pairwise similarity is still limited, because only P2P distances are mostly considered. In this paper, we present a novel person Re-ID method based on P2S similarity comparison. The P2S metric can jointly minimize the intra-class distance and maximize the inter-class distance, while back-propagating the gradient to optimize parameters of the deep model. By utilizing our proposed P2S metric, the learned deep model can effectively distinguish different persons by learning discriminative and stable feature representations. Comprehensive experimental evaluations on 3DPeS, CUHK01, PRID2011 and Market1501 datasets demonstrate the advantages of our method over the state-of-the-art approaches.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
跨镜头多人脸跟踪
Tracking Persons-of-Interestvia Adaptive Discriminative FeaturesShun Zhang, Yihong Gong, Jia-Bin Huang, Jongwoo Lim, Jinjun Wang, Narendra Ahuja and Ming-Hsuan Yang
ECCV, 2016
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up. Low level features used in existing multi-target tracking methods are not effective for identifying faces with such large appearance variations. In this paper, we tackle this problem by learning discriminative, video-specific face features using convolutional neural networks (CNNs). Unlike existing CNN-based approaches that are only trained on large-scale face image datasets offline, we further adapt the pre-trained face CNN to specific videos using automatically discovered training samples from tracklets. Our network directly optimizes the embedding space so that the Euclidean distances correspond to a measure of semantic face similarity. This is technically realized by minimizing an improved triplet loss function. With the learned discriminative features, we apply the Hungarian algorithm to link tracklets within each shot and the hierarchical clustering algorithm to link tracklets across multiple shots to form final trajectories. We extensively evaluate the proposed algorithm on a set of TV sitcoms and music videos and demonstrate significant performance improvement over existing techniques.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
深度特征学习
Improving DCNN Performance with Sparse Category-Selective Objective Function Shizhou Zhang, Yihong Gong, JinjunWang
IJCAI, 2016
we choose to learn useful cues fromobject recognition mechanisms of the human visualcortex, and propose a DCNN performance improvementmethod without the need for increasingthe network complexity. Inspired by the categoryselectiveproperty of the neuron population in theIT layer of the human visual cortex, we enforcethe neuron responses at the top DCNN layer to becategory selective. To achieve this, we proposethe Sparse Category-Selective Objective Function(SCSOF) to modulate the neuron outputs of thetop DCNN layer. The proposed method is genericand can be applied to any DCNN models. As experimentalresults show, when applying the proposedmethod to the “Quick” model and NINmodels, image classification performances are remarkablyimproved on four widely used benchmarkdatasets: CIFAR-10, CIFAR-100, MNISTand SVHN, which demonstrate the effectiveness ofthe presented method.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
多目标跟踪
Multi-target tracking by learnin glocal-to-global trajectory models Shun Zhang, Jinjun Wang, Zelun Wang, Yihong Gong and Yuehu Liu
Pattern Recognition, 2014
The multi-target tracking problem is challenging when there exist occlusions, tracking failures of the detector and severe interferences between detections. In this paper, we propose a novel detection based tracking method that links detections into tracklets and further forms long trajectories. Unlike many previous hierarchical frameworks which split the data association into two separate optimization problems (linking detections locally and linking tracklets globally), we introduce a unified algorithm that can automatically relearn the trajectory models from the local and global information for finding the joint optimal assignment. In each temporal window, the trajectory models are initialized by the local information to link those easy-to-connect detections into a set of tracklets. Then the trajectory models are updated by the reliable tracklets and reused to link separated tracklets into long trajectories. We iteratively update the trajectory models by more information from more frames until the result converges. The iterative process gradually improves the accuracy of the trajectory models, which in turn improves the target ID inferences for all detections by the MRF model. Experiment results revealed that our proposed method achieved state-of-the-art multi-target tracking performance.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
图像特征表达
Locality-constrained Linear Coding for Image Classification Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, Thomas Huang and Yihong Gong
Proc.of IEEE Conference on Computer Vision and Pattern Recognition 2010
The traditional SPM approach based on bag-of-features (BoF) must use nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM. LLC utilizes the locality constraints to project each descriptor into its local-coordinate system, and the projected coordinates are integrated by max pooling to generate the final representation. With linear classifier, the proposed approach performs remarkably better than the traditional nonlinear SPM, achieving state-of-the-art performance on several benchmarks.
Compared with the sparse coding strategy [22], the objective function used by LCC has an analytical solution, bearing much lower computational complexity of O(M + M) with M the size of codebook. In addition, the paper proposes an approximated LCC method by first performing a K-nearest-neighbor search and then solving a constrained least square fitting problem, further reducing the computational complexity to O(M+K). Hence even with very large codebooks, our system can still process multiple frames per second. This efficiency significantly adds to the practical values of LLC for real applications.
[pdf]

Discovering Image Semantics inCodebook Derivative Space Jinjun Wang and Yihong Gong
IEEETrans. on Multimedia，vol.14, issue.4,pp 986-994, August 2012
The sparse coding based approaches for image recognition have recently shown improved performance than traditional bag-of-features technique. Due to high dimensionality of the image descriptor space, existing systems usually require very large codebook size to minimize coding error in order to get satisfactory accuracy. While most research efforts try to address the problem by constructing a relatively smaller codebook with stronger discriminative power, in this paper, we introduce an alternative solution by enhancing the quality of coding. Particularly, we apply the idea similar to Fisher kernel to the coding framework, where we use the image-dependent codebook derivative to represent the image. The proposed idea is generic across multiple coding criteria, and in this paper, it is applied to enhance the Locality-constraint Linear Coding (LLC). Experiments show that, the extracted new feature, called “LLC+”, achieved significantly improved accuracy on several challenging datasets even with a small codebook of 1/20 the reported size used by LLC. This obviously adds to LLC+ the modeling accuracy, processing speed and codebook training advantages.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
图像与视频超分辨率
Resolution-Invariant Image Representation and Its Applications Jinjun Wang, Shenghuo Zhu, Yihong Gong
Proc. of IEEE Conference on Computer Vision and PatternRecognition 2009
We present a Resolution-Invariant Image Representation (RIIR) framework in this paper. The RIIR framework includes the methods of building a set of multi-resolution bases from training images, estimating the optimal sparse resolution-invariant representation of any image, and reconstructing the missing patches of any resolution level. As the proposed RIIR framework has many potential resolution enhancement applications, we discuss three novel image magnification applications in this paper. In the first application, we apply the RIIR framework to perform Multi-Scale Image Magnification where we also introduced a training strategy to built a compact RIIR set. In the second application, the RIIR framework is extended to conduct Continuous Image Scaling where a new base at any resolution level can be generated using existing RIIR set on the fly. In the third application, we further apply the RIIR framework onto Content-Base Automatic Zooming applications. The experimental results show that in all these applications, our RIIR based method outperforms existing methods in various aspects.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
人物动作识别
Substructure and Boundary Modeling for Continuous Action Recognition Zhaowen Wang, Jinjun Wang*, Jing Xiao, Kai-Hsiang Lin and Thomas Huang
Proc. of IEEE Conference on Computer Vision and Pattern Recognition 2012
This work introduces a probabilistic graphical model for continuous action recognition with two novel components: substructure transition model and discriminative boundary model. The first component encodes the sparse and global temporal transition prior between action primitives in state-space model to handle the large spatialtemporal variations within an action class. The second component enforces the action duration constraint in a discriminative way to locate the transition boundaries between actions more accurately. The two components are integrated into a unified graphical structure to enable effective training and inference. Our comprehensive experimental results on both public and in-house datasets show that, with the capability to incorporate additional information that had not been explicitly or efficiently modeled by previous methods, our proposed algorithm achieved significantly improved performance for continuous action recognition.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
基于内容的视频检索与自动编辑
A Novel Framework for Semantic Annotation andPersonalized Retrieval of Sports Video Changsheng Xu, Jinjun Wang, Hanqing Lu and Yifan Zhang
IEEE Trans. on Multimedia; vol. 10, issue. 3,pp 421-436, 2008
In this paper, we propose a novel automatic approach for personalized music sports video generation. Two research challenges are addressed, specifically the semantic sports video content extraction and the automatic music video composition. For the first challenge, we propose to use multimodal (audio, video, and text) feature analysis and alignment to detect the semantics of events in broadcast sports video. For the second challenge, we introduce the video-centric and music-centric music video composition schemes and proposed a dynamic-programming based algorithm to perform fully or semi-automatic generation of personalized music sports video. The experimental results and user evaluations are promising and show that our system’s generated music sports video is comparable to professionally generated ones. Our proposed system greatly facilitates the music sports video editing task for both professionals and amateurs.
[pdf]

Generation of Personalized Music Sports VideoUsing Multimodal Cues Jinjun Wang, Engsiong Chng, Changsheng Xu, Hanqinq Lu and Qi Tian
IEEE Trans. on Multimedia，vol.9, issue.3, pp 576-588, April 2007
The sparse coding based approaches for image recognition have recently shown improved performance than traditional bag-of-features technique. Due to high dimensionality of the image descriptor space, existing systems usually require very large codebook size to minimize coding error in order to get satisfactory accuracy. While most research efforts try to address the problem by constructing a relatively smaller codebook with stronger discriminative power, in this paper, we introduce an alternative solution by enhancing the quality of coding. Particularly, we apply the idea similar to Fisher kernel to the coding framework, where we use the image-dependent codebook derivative to represent the image. The proposed idea is generic across multiple coding criteria, and in this paper, it is applied to enhance the Locality-constraint Linear Coding (LLC). Experiments show that, the extracted new feature, called “LLC+”, achieved significantly improved accuracy on several challenging datasets even with a small codebook of 1/20 the reported size used by LLC. This obviously adds to LLC+ the modeling accuracy, processing speed and codebook training advantages.
[pdf]

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
智能汽车
Driving Safety Monitoring Using SemisupervisedLearning on Time Series Data Jinjun Wang, Shenghuo Zhu and Yihong Gong
IEEE Trans. on Intelligent Transportation Sys., vol. 11,issue 3, pp 728-737, Sept. 2010
This work introduces a dangerous-driving warning system that uses statistical modeling to predict driving risks. The major challenge of the research is how to discover the safe/dangerous driving patterns from a sparsely labeled training data set. This paper proposes a semisupervised learning method to utilize both the labeled and the unlabeled data, as well as their interdependence to build a proper danger-level function. In addition, the learned function adopts a continuous parametric form, which is more suitable in modeling the continuous safe/dangerous-driving state transitions in a practical dangerousdriving warning system. Our comprehensive experimental evaluations reveal that, in comparison with driving danger-levelestimation using classification-based methods, such as the hidden Markov model (HMM) or the conditional random field algorithm, the proposed method requires less training time and achieved higher prediction accuracy. Index Terms—Driving safety monitoring, functional safety, semisupervised learning.
[pdf]

团队及成员 - 王进军团队总负责人

姓名：
郑南宁

主页：
http://www.xjtu.edu.cn/info/1729/197980.htm

团队成员
作者还未对该模块添加任何内容.

加入我们的科研团队 - 王进军Blank

姓名：
王进军

任职：
教授，博士生导师

学位：
博士

单位：
西安交通大学电信学院自动化科学与

技术系

方向：
模式识别、机器学习、机器视觉、多

多媒体计算

地址：
西安交通大学曲江校区西四楼307室

电话：

传真：

邮箱：
查看邮箱

招生/招聘信息
计划招收2018/19年博士研究生和硕士研究生各两名

博士毕业要求：
从事大规模统计学习和深度机器学习方面的研究，解决模式识别、计算机视觉和人工智能方面的科学问题
学习时间3至5年
发表CCF推荐A类期刊或会议论文两篇
联系电话：
邮箱：查看邮箱（抵制垃圾邮件）
欢迎学生报考！鼓励报考前和我联系，并通过与实验室学生交流，了解导师的指导风格和科研水平！
实验室团队页面：http://gr.xjtu.edu.cn/web/jinjun/members
实验室介绍：www.aiar.xjtu.edu.cn
西安交通大学研究生院招生信息：http://gs.xjtu.edu.cn/zhaos/
以下附导师简介：

王进军教授2008年在新加坡南洋理工大学获得计算机工程博士学位。自2006年到2013年，他先后在美国硅谷的NEC研究院、美国Epson研发院等担任研究员和高级研究员。2013年2月，王进军教授加入西安交通大学电信学院自动化科学与技术系人工智能与机器人研究所。
王进军教授是多媒体计算与模式识别领域非常活跃的国际****。他在多模态体育视频复杂场景分析、图像特征向量优化、图像分辨率增强、时间序列信号分析等研究方向上提出了多项创新的理论方法与关键技术方案，成为许多后续研究的理论扩充及比较对象。王进军教授编写英文著作1部，在国际知名学术期刊IEEE T-MM和顶级国际会议CVPR、IJCAI、ACM MM等上发表学术论文70余篇，代表性论文被他引5000多次，单篇最高他引超过1800次。王进军教授已获授权美国发明专利14项，中国发明专利3项。王进军教授获得过2项NEC公司奖和1项微软亚洲奖，其所在团队在图像视频领域最具影响力的国际比赛TRECVID Event Detection（2009）和PASCAL VOC（2009）中获得冠军。
王进军教授的研究方向主要包括：模式识别、计算机视觉、多媒体计算和机器学习。在计算机视觉方向，王进军教授提出的图像特征表达算法，被广泛的引用并运用于解决图像分类、人物动作识别、图像超分辨率等问题。这些问题是对图像或视频数据进行检索/匹配/语义理解/增强等实际应用中的关键问题。在多媒体计算方面，王进军教授是国际上早期从事视频/音频/文本多模态进行体育视频检索的****之一。他和团队开发了实时体育视频检索技术，与ESPN（美国）、新加坡电信（新加坡）、NEC（中国）、Intel（中国）等企业有长期深入的学术及商业合作。在机器学习方面，王进军教授提出了多种基于图论模型的结构数据学习算法，用于解决图像超分辨率、人物动作序列识别、人物表情识别、驾驶安全度预测、机械手动作模仿等问题。王进军教授曾组织过Pattern Recognition期刊专题，主办过ICIP、ICME、MMM、PCM等会议专题，担任过ICIP、ICPR、ICME、ICIMCS等会议的专题主席或公共关系主席，并长期担任T-MM、T-IP、T-CSVT、CVIU等期刊以及ACM MM、ACM CIVR、ICME、3DTV等会议的审稿人。

Google对王进军教授的评价：scholar.google.com/citations

计划招收科研专职人员若干名
从事计算机视觉和模式识别方面的原型系统开发和算法研究。
职位基本要求：
具有计算机、电信、自动控制等相关专业硕士学位
具有在计算机视觉、机器学习、模式识别、多媒体技术等相关方面的研发经验
熟练掌握以下一种或多种程序开发语言C/C++，Python，Java，Matlab
具有良好的编程能力，用于进行各种数学算法的实现、视频处理、数据分析等
具有团队合作精神
具备以下条件者优先：
具有可证明的科技论文写作能力（如发表过高质量的学术论文）
具有移动、视频、网站等开发能力
具有参与过相关项目的实际经验
联系电话：
邮箱：查看邮箱（抵制垃圾邮件）
本通知长期有效并会不定期更新！有意者欢迎将简历发送至我的邮箱进行初选。一经录用，薪酬从优，并可全面享受学校的各项福利待遇！
实验室团队页面：http://gr.xjtu.edu.cn/web/jinjun/members
实验室介绍：www.aiar.xjtu.edu.cn
以下附导师简介：
王进军教授2008年在新加坡南洋理工大学获得计算机工程博士学位。自2006年到2013年，他先后在美国硅谷的NEC研究院、美国Epson研发院等担任研究员和高级研究员。2013年2月，王进军教授加入西安交通大学电信学院自动化科学与技术系人工智能与机器人研究所。
王进军教授是多媒体计算与模式识别领域非常活跃的国际****。他在多模态体育视频复杂场景分析、图像特征向量优化、图像分辨率增强、时间序列信号分析等研究方向上提出了多项创新的理论方法与关键技术方案，成为许多后续研究的理论扩充及比较对象。王进军教授编写英文著作1部，在国际知名学术期刊IEEE T-MM和顶级国际会议CVPR、IJCAI、ACM MM等上发表学术论文70余篇，代表性论文被他引5000多次，单篇最高他引超过1800次。王进军教授已获授权美国发明专利14项，中国发明专利3项。王进军教授获得过2项NEC公司奖和1项微软亚洲奖，其所在团队在图像视频领域最具影响力的国际比赛TRECVID Event Detection（2009）和PASCAL VOC（2009）中获得冠军。
王进军教授的研究方向主要包括：模式识别、计算机视觉、多媒体计算和机器学习。在计算机视觉方向，王进军教授提出的图像特征表达算法，被广泛的引用并运用于解决图像分类、人物动作识别、图像超分辨率等问题。这些问题是对图像或视频数据进行检索/匹配/语义理解/增强等实际应用中的关键问题。在多媒体计算方面，王进军教授是国际上早期从事视频/音频/文本多模态进行体育视频检索的****之一。他和团队开发了实时体育视频检索技术，与ESPN（美国）、新加坡电信（新加坡）、NEC（中国）、Intel（中国）等企业有长期深入的学术及商业合作。在机器学习方面，王进军教授提出了多种基于图论模型的结构数据学习算法，用于解决图像超分辨率、人物动作序列识别、人物表情识别、驾驶安全度预测、机械手动作模仿等问题。王进军教授曾组织过Pattern Recognition期刊专题，主办过ICIP、ICME、MMM、PCM等会议专题，担任过ICIP、ICPR、ICME、ICIMCS等会议的专题主席或公共关系主席，并长期担任T-MM、T-IP、T-CSVT、CVIU等期刊以及ACM MM、ACM CIVR、ICME、3DTV等会议的审稿人。

English - 王进军(1.)Basic Information

Name:
Jinjun Wang, PhD

Title:
Full professor

Degree:
PhD

Dept.:
Xian Jiaotong University, School of

Electronicand Information,
Department of Automation

Area:
Pattern Recognition, Machine

Learning, Computer Vision,
MultimediaComputing etc

Address:
XJTU, Qujiang Campus, West 4

Building, Room 307

Tel:

Fax:

E-Mail
Hover to see

Biography
Prof. Jinjun Wang got his PhD from Nanyang Technological University, Singapore in 2008. From 2006 to 2013, Prof. Wang worked in Silicon Valley, USA for leading research institutes including NEC laboratories America, Inc. and Epson Research and Development, Inc. as research scientist and senior research scientist. In 2013, Prof. Wang joined Xian Jiaotong University, School of Electronic and Information, Department of automation, Institute of Artificial Intelligence and Robotics.
Prof. Wang is an active international researcher in pattern recognition and multimedia computing area. Many of his works are widely used, benchmarked and referenced. Prof. Wang's major contributions focus on content-based sports video analysis, image feature representation, super-resolution, time-series signal analysis and recognition. Prof. Wang has published one book and over 70 high quality academic papers in prestigious international journals and conferences, including IEEE Trans. Multimedia, IEEE Trans. Intelligence Transportation Systems, IEEE conference on Computer Vision and Pattern Recognition, ACM conference on Multimedia, etc. His works has been cited for over 5000 times, and the greatest number of citations for one single publication is above 1800 times. Prof. Wang has 14 US patents granted. Prof. Wang was the receiver of two NEC seed rewards and one Microsoft Asia Fellowship. As a key member, his team won the championship of TRECVID Event Detection (2009) and PASCAL VOC (2009).
Prof. Wang's area of interests includes pattern recognition, computer vision, multimedia computing and machine learning.See what's there on Google scholar about prof. Wang:scholar.google.com/citations

Experience
Education
Nanyang Technological University, Singapore

May 2008
PhD, School of Computer Engineering, Nanyang Technological University, Singapore

Huazhong University of Science and Technology

July 2003
M.E., Department of Electronic and Information,Huazhong University of Science and Technology

July 2000
B.E., Department of Electronic and Information,Huazhong University of Science and Technology

Work
Xian Jiaotong University

February 2013
Professor, Institute of Artificial Intelligence and Robotics, Department of Automation, School of Electronic and Information, Xian Jiaotong University

Epson Research and Development Inc.

August 2010
Senior Research Scientist

Akiira Media System

November 2009
Senior Research Scientist

NEC Laboratories America Inc.

November 2006
Research Scientist

Honor
Winner of Pascal VOC 2009, Image classification track (http://www.comp.leeds.ac.uk/me/VOC2009/prelimreszhong中Classification Results)

Winner of TRECVID 2009, Survellience event detection track (www-nlpir.nist.gov/projects/tvpubs/tv9.slides/tv9.ed.slides.pdf)
"Intelligent Content Augmentation”(2009) and “The Beauty project” (2007), NEC seed project rewards
Winner of Microsoft Research Asia Fellowship, 2005, Singapore