多年从事图像分析、目标检测与识别、智能视频分析、生物特征识别、计算机视觉和模式识别等方面研究工作。以目标检测和识别、目标跟踪、行为分析为基础，构建对于国家安全和公共安全有重大需求的智能视频分析系统。近年来，研究团队获得了包括863、国家自然科学基金、教育部博士点基金等多个国家项目支持，并取得出色成果。

王生进教授团队在行人再识别（Person ReID）研究领域具有国际领先的研究成果，学术论文覆盖计算机视觉、人工智能顶级期刊（TPAMI、TIP）、顶级国际会议（ICCV、CVPR、ECCV）。MIT Technology Review给予高度评价。同时，团队贡献了Person ReID研究领域3个大型公开图像数据集，Market-1501，iLID-VID及视频数据集MARS。其中iLID-VID下载超过3700次。SVDNet方法论文被评选为ICCV2017 spotlight，RPP方法刷新国际最高水平。相关技术开始在安防领域展开试用。在两个典型行人序列数据集上，所开发的新方法准确率分别比现有最好方法提高了5.7%和16.3%，在平安城市视频监控应用领域具有良好潜力，国际权威期刊IEEE PAMI发表了这项成果。

2018年，学术论文“Attend and Align: Improving Deep Representations with Feature Alignment Layer for Person Retrieval”获得2018年国际模式识别大会（ICPR2018）最佳学术论文奖。

作为起草人之一，制定中华人民共和国公共安全行业标准《安全防范系统生物特征识别应用术语》和国家标准《安全防范视频监控数字视音频编解码技术要求（SVAC）》。

1.国家支撑计划项目、2003CB314904、多源信息关联整合与共享联动技术与系统研发、子课题主持。

2.国家863计划项目、2012AA011004、海量不确定异构数据的集成管理与分析技术、子课题主持。

3.国家自然科学基金项目，61071135、重现的行人目标数据关联和深度跟踪理论及方法研究、主持。

4.教育部博士点基金项目、20090002110077、基于在线特征学习的人形表象数据关联方法及其应用研究、主持。

5.国家863计划项目、2006AA01Z115、基于人类视觉感知和认知机理的视频图像模式识别和机器学习、主持。

中国图象图形学会视频监控与安全专委会主任

北京图象图形学会副理事长

全国安防标委会人体生物特征识别应用分技术委员会委员

公安部安全防范技术与风险评估公安部重点实验室学术委员会委员

自动化学会国防大数据分会副主任委员

危爆品扫描探测国家工程实验室副主任

[1]Yun Lei, Xiaoqing Ding, and Shengjin Wang. Visual Tracker Using Sequential Bayesian Learning: Discriminative, Generative and Hybrid, IEEE Trans. on Systems, Man And Cybernetics-Part B, Vol.38, No.6, pp.1578-1591, December, 2008。SCI 378GZ

[2]Yali Li, Shengjin Wang, Xiaoqing Ding, Eye/eyes tracking based on a unified deformable template and particle filtering, Pattern Recognition Letters, Volume: 31, Issue: 11, pp.1377-1387, AUG 2010 . SCI: 000279834800018, or SCI: IDS Number: 624QO。SCI 624QO

[3]Yali Li, Shengjin Wang, and Xiaoqing Ding, Person-Independent Head Pose Estimation Based On Random Forrest Regression. In Proceedings of International Conference on Image Processing (ICIP2010), pp.1521-1524, September 26-29, 2010, Hong Kong. EI 20110213575002, Inspec 11690716

[4]Gu Junxia, Ding Xiaoqing, Wang Shengjin, Wu Youshou. Action and gait recognition from recovered 3D human joints. IEEE Transactions on Systems, Man, and Cybernetics, Part B，Vol.40, No.4, pp.1021-1033, August, 2010 （SCI源刊). SCI 656PJ

[5]Liang Zheng, Shengjin Wang. Visual phraselet: refining spatial constraints for large scale image search. IEEE Signal Processing Letters, Vol. 20, No. 4, pp. 391-394, April, 2013.

[6]Liang Zheng, Shengjin Wang, Ziqiong Liu, Qi Tian. Lp-norm IDF for large scale image search. IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013), pp. 1626-1633, June 23-28, 2013，Portland, OR, United states, EI 20134616982674

[7]Liang Zheng, Shengjin Wang, Ziqiong Liu, Qi Tian,Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval, CVPR2014, pp. 1963-1970, in Columbus, Ohio, USA, June, 2014

[8]Liang Zheng, Shengjin Wang, Ziqiong Liu, Qi Tian,Packing and Padding: Coupled Multi-index for Accurate Image Retrieval, CVPR2014, pp. 1947-1954, in Columbus, Ohio, USA, June, 2014

[9]Taiqing Wang, Shengjin Wang, Xiaoqing Ding，Detecting Human Action as Spatio-Temporal Tube of Maximum Mutual Information，IEEE Transactions on Circuits and Systems for Video Technology, pp.277-290, Vol.24, No.2, 2014, DOI:10.1109/TCSVT.2013.2276856 （SCI）

[10]Yuan LIN, Shengjin WANG, Pose-free Face Swapping Based on a Deformable 3D Shape Morphable Model, IEICE Transactions on Information and Systems, pp. 305-314,Vol.E97-D,No.2, Feb. 2014 (SCI)

[11]Liang Zheng, Shengjin Wang, and Qi Tian, Coupled Binary Embedding for Scalable Image Retrieval, IEEE Transactions on Image Processing, Vol 23, No. 8, pp. 3368-3380, June, 2014.

[12]Liang Zheng, Shengjin Wang, and Qi Tian, Lp-norm IDF for Scalable Image Retrieval, IEEE Transactions on Image Processing, Vol 23, No. 8, pp. 3604-3617, June, 2014.

[13]Ziqiong Liu, Shengjin Wang, Liang Zheng, Qi Tian, Visual Reranking with improved image graph, ICASSP2014(International Conference On Acoustics Speech and Signal Processing), IEEE catalog number: CFP14ICA-USB,pp.6939-6943,4-9 May 2014 in Florence, Italy. ISBN: 978-1-4799-2892-7

[14]Liang Zheng, Shengjin Wang, Peizhen Guo, Hanyue Liang, and Qi Tian, Tensor Index for Large Scale Image Retrieval, Multimedia Systems, Oct. 2014 (SCI源刊，影响因子0.443；EI收录，检索号：20144300116846)

[15]Zheng L, Wang S, Liu Z, Tian Q. Fast Image Retrieval: Query Pruning and Early Termination. IEEE Transactions on Multimedia, 2014, 17(5): 648-659. (SCI源刊，影响因子1.776)

[16]Taiqing Wang, Shaogang Gong, Shengjin Wang, Discriminative Video Matching for Person Re-Identication, European Conference on Computer Vision （ECCV2014）, September 8-12, 2014, pp.688-703, Zurich, Switzerland.

[17]Yali Li, Shengjin Wang, Qi Tian, Xiaoqing Ding, Learning Cascaded Shared-Boost Classifiers for Part-based Object Detection, IEEE Transactions on Image Processing, pp.1858-1871,Volume:23,No.4, 2014. DOI: 10.1109/ TIP.2014.2307432（SCI）

[18]Fei He and Shengjin Wang, Beyond χ2 Difference: Learning Optimal Metric for Boundary Detection, IEEE Signal Processing Letters, Vol 22, No. 1, pp. 40-44, Jan. 2015

[19]Jie Liu, Shengjin Wang, Salient Region Detection via Simple Local and Global Contrast Representation, Neurocomputing, Pages 435-443, Volume 147, 5 January 2015

[20]Xu Zhang, Fei He, Lu Tian, Shengjin Wang, Cognitive Pedestrian Detector: Adapting Detector to Specific Scene by Transferring Attributes, Neurocomputing, Pages 800-810, Volume 149, Part B, 3 February 2015

[21]Liang Zheng, Shengjin Wang, Lu Tian, Fei He, and Qi Tian, "Black Sheep Out: Query Adaptive Fusion for Image Search and Person Re-identification", International Conference on Computer Vision and Pattern Recognition (CVPR2015), pp. 1741-1750, in Boston, USA, June, 2015.

[22]Lu Tian, Shengjin Wang, Person Re-identification as Image Retrieval Using Bag of Ensemble Colors, IEICE Transactions on Information and Systems, Vol.E98-D,No.1,pp. 180-188, Jan. 2015 (SCI)

[23]Yali Li, Shengjin Wang, Qi Tian, Xiaoqing Ding, A survey of recent advances in visual feature detection, Neurocomputing, Pages 736u2013751, Volume 149, Part B, 3 February 2015

[24]Yali Li, Shengjin Wang, Qi Tian, Xiaoqing Ding, Feature representation for statistical learning based object detection: a review, Pattern Recognition, pp.3542-3559, vol.48, 2015

[25]Yali Li, Shengjin Wang, Qi Tian, Xiaoqing Ding, A Boosting Approach to Exploit Instance Correlations for Multi-Instance Classification, IEEE Transactions on Neural Networks and Learning Systems, 2015 (Accepted)

[26]Taiqing Wang, Shaogang Gong, Xiatian Zhu,Shengjin Wang, Re-Identification by Discriminative Selection in Video Ranking, IEEE Transactions on Pattern Recognition and Machine Intelligence, 2015, submitted to PAMI 2014 (Now Major)

[27]Dong Li, Yali Li, Shengjin Wang, Selective Parts for Fine-Grained Recognition, In Proceedings of International Conference on Image Processing (ICIP2015), Quebec, Canada, Sept. 2015, will be published.

[28]Xu Zhang, Felix Xinnan Yu, Ruiqi Guo, Sanjiv Kumar, Shengjin Wang, Shih-Fu Chang, Fast Orthogonal Projection Based on Kronecker Product, ICCV2015, Santiago, Chile, Dec.2015, Accepted

[29] Ziqiong Liu, Shengjin Wang, Qi Tian, Fine-residual VLAD for image retrieval, Neurocomputing, 2015, Accepted

[30]Xu Zhang, Felix Xinnan Yu, Ruiqi Guo, Sanjiv Kumar, Shengjin Wang, Shih-Fu Chang, Fast Orthogonal Projection Based on Kronecker Product, ICCV2015, Santiago, Chile, Dec.2015, Accepted

[31] Ziqiong Liu, Shengjin Wang, Qi Tian, Fine-residual VLAD for image retrieval, Neurocomputing, 2015, Accepted

[32]Liang Zheng, Shengjin Wang, Liyue Shen, Lu Tian, Qi Tian, S Scalable Person Re-identification: A Benchmark, ICCV2015, Santiago, Chile, Dec.2015, Accepted

[33] Dong Li, Yali Li, Shengjin Wang, Discriminative Middle-Level Parts Mining for Object Detection, IEICE Transactions on Information and Systems, Vol.E98-D, No.11, pp.1950-1957, Jan. 2015 (SCI).

[34] Liang Zheng, Shengjin Wang, Jingdong Wang, and Qi Tian, "Accurate Image Search with Multi-Scale Contextual Evidences", International Journal of Computer Vision (IJCV), 2016:1-13, 2016.

[35] Hongchuan Liu, Yali Li, Hongma Liu, Shengjin Wang, Bagging Regularized Common Spatial Pattern With Hybrid Motor Imagery and Myoelectric Signal, ICASSP2016, May, 2016, shanghai, China.

[36] Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, Ming-Hsuan Yang, Weakly Supervised Object Localization with Progressive Domain Adaptation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR2016), Las Vegas, USA, June, 2016.

[37] Liang Zheng, Zhi Bie, Yifan Sun, Jingdong Wang, Chi Su, Shengjin Wang*,Qi Tian, MARS: A Video Benchmark for Large-Scale Person Re-Identification, ECCV2016, 17 September 2016.

[38] Dong Li, Shengjin Wang, Unsupervised Visual Representation Learning by Graph-based Consistent Constraints, ECCV2016.

[39] Li Yali, Liu Hongma, Wang Shengjin. Exploiting eeg channel correlations in p300 speller paradigm for brain-computer interface[J]. IEICE TRANSACTIONS on Information and Systems, 2016, 99(6): 1653-1662.（SCI源刊.影响因子0.411）

[40] Ziqiong Liu, Shengjin Wang, Qi Tian, Robust ImageGraph: Rank-Level Feature Fusion for Image Search, IEEE Transactions on Image Processing, pp. 3128-3141, Volume: 26, No.7, 2017.(SCI).

[41] Jingchun Cheng, Sifei Liu, Yi-Hsuan Tsai, Wei-Chih Hung, Shalini De Mello, Jinwei Gu, Jan Kautz, Shengjin Wang, Ming-Hsuan Yang, Learning to Segment Instances in Videos with Spatial Propagation Network, The 2017 DAVIS Challenge on Video Object Segmentation - CVPR 2017 Workshops. Win 6th Place Award.

[42] Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan,Shengjin Wang, Hongsheng Li, Xiaogang Wang, Orientation Invariant Feature Embedding and Spatial Temporal Re-ranking for Vehicle Re-identification, ICCV2017, Venice, Italy, Oct. 2017.

[43] Yifan Sun, Liang Zheng, Shengjin Wang, SVDNet for Pedestrian Retrieval, ICCV2017, Venice, Italy, Oct. 2017.

[44] Jingchun Cheng, Shengjin Wang, Ming-Hsuan Yang, SegFlow: Joint Learning for Video Object Segmentation and Optical Flow, ICCV2017, Venice, Italy, Oct. 2017.

[45] Dangdang Chen, Lanqing He, Shengming Yu, and Shengjin Wang. An Efficient and Accurate Face Verification Method Based on CNN Cascade Architeture. Proc of CAAI, 2017: 534-540.

[46] Shu Han, Chen Dangdang, Li Yali, Wang Shengjin. A highly accurate facial region network for unconstrained face detection[C]// Image Processing(ICIP), 2017 IEEE International Conference on. IEEE, 2017:665-669.

[47] Jingchun Cheng, Shengjin Wang, Ming-Hsuan Yang, Fast and Accurate Online Video Object Segmentation via Tracking Parts, CVPR2018, Jun 19, 2018 - Jun 21, 2018, Salt Lake City, USA

[48] Lingxiao Wang, Yali Li, Shengjin Wang, Feature Learning For One-Shot Face Recognition, ICIP2018, October 7-10, 2018, Athens, Greece.

[49] Qin Xu, Yifan Sun, Yali Li, Shengjin Wang, Improving Deep Representations with Feature Alignment Layer for Person Retrieval, ICPR2018, August 2018. (Best Paper Award)

[50] Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang and Ming-Hsuan Yang, Progressive Representation Adaptation for Weakly Supervised Object Localization, IEEE Trans PAMI, accepted in Jan. 2019.

[51] Yifan Sun, Liang Zheng, Shengjin Wang, Beyond Part Models: Person Retrieval with Refined Part Pooling, ECCV2018, September, 2018. Munich, Germany.

[52] Jianqiang Wang, Yali Li, Shengjin Wang, A Highly Accurate Feature Fusion Network For Vehicle Detection In Surveillance Scenarios, BMVC2018, September 3, Newcastle, UK.

[53] Xiudong Wang, Yali Li, Shaodi You, Hongdong Li, and Shengjin Wang, Unidirectional Representation Based Efficient Dictionary Learning, IEEE Transactions on Circuits and Systems for Video Technology, page(s): 1-16 Print ISSN: 1051-8215 Online ISSN: 1558-2205 Digital Object Identifier: 10.1109/TCSVT.2018.2886600

[54] Yuxuan Zhu, Yali Li, Shengjin Wang, Unsupervised Deep Hashing with Adaptive Feature Learning for Image Retrieval, IEEE Signal Processing Letters, IEEE Signal Processing Letters On page(s): 1--5 Print ISSN: 1070-9908 Online ISSN: 1558-2361 Digital Object Identifier: 10.1109/LSP.2019.2892233

[55] Zhongdao Wang, Shengjin Wang, Linkage Based Face Clustering via Graph Convolution Network, CVPR2019, accepted

[56] Yifan Sun, Qin Xu, Yali Li, Chi Zhang, Shengjin Wang*, Jian Sun, Learning Visibility-aware Part-level Features with Self-supervision for Partial Person Re-identification, CVPR2019, accepted

[57] Yue Zheng, Yali Li, Shengjin Wang, Intention Oriented Image Captions with Guiding Objects, CVPR2019, accepted