唐胜  研究员  

研究方向:

所属部门:前瞻研究实验室

导师类别:博导计算机应用技术

联系方式:ts@ict.ac.cn

个人网页:http://people.ucas.ac.cn/~shengtang

简       历:

  20063月博士毕业于中国科学院计算技术研究所(简称计算所)后留所工作,20083月起先后任副研究员和研究员、硕士生导师和博士生导师,中国计算机学会和中国图象图形学会多媒体专委会委员。在国家973863、国家重点研发计划项目、国家自然科学基金等项目的支持下,带领团队长期从事多媒体内容分析与检索、计算机视觉与模式识别研究,相关论文发表于多媒体、计算机视觉和人工智能的国际顶级会议ICCVCVPRECCVACM MultimediaAAAIIJCAIMICCAI和国际顶级期刊IEEE T-PAMIT-IP等。研发的多项图像视频分析、检索与识别系统已经在国家相关部门获得大规模应用,部署在全国多地,应用效果显著。主持2014年全国首届特定音视频检索识别挑战赛视频评测;带领团队在美国NIST举办的视频检索国际评测TRECVID2008和国际著名的ImageNet大规模视觉识别挑战赛(ILSVRC 2016)中取得优异成绩,并受邀做大会报告。荣获中国计算机学会科学技术奖1项、中国电子学会科学技术奖一等奖2项、北京市科学技术奖一等奖3项、国家自然科学二等奖1项。

主要论著:

期刊文章(CCF A类期刊4篇,CCF B类期刊7篇,*表示通讯作者):

[1] Sheng Tang,Yan-Tao Zheng,Yu Wang and Tat-Seng Chua,“Sparse Ensemble Learning for Concept Detection”,IEEE Transactions on Multimedia,14(1):43-54,Feb. 2012. (CCF B类多媒体国际期刊)

[2] Sheng Tang,Yu Li,Lixi Deng,Yong-Dong Zhang;“Object Localization Based on Proposal Fusion”,IEEE Transactions on Multimedia,19(9):2105-2116,September 2017. (CCF B类多媒体国际期刊)

[3] Rui Zhang,Sheng Tang*,Yongdong Zhang*,Jintao Li,Shuicheng Yan,"Perspective-adaptive Convolutions for Scene Parsing",IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),42(4):909 – 924,April,2020. (CCF A类人工智能著名国际顶级期刊)

[4] Tianyi Wu,Sheng Tang*,Rui Zhang,Juan Cao,Yong-Dong Zhang;“CGNet: A Light-weight Context Guided Network for Semantic Segmentation”,IEEE Transactions on Image Processing,30(1):1169-1179,2021. (CCF A类图像处理国际顶级期刊)

[5] Yu Li,Sheng Tang*,Rui Zhang,Yongdong Zhang,Jintao Li,Shuicheng Yan,“Asymmetric GAN for Unpaired Image-to-image Translation”,IEEE Transactions on Image Processing,28(12):5881-5896,December,2019. (CCF A类图像处理国际顶级期刊)

[6] Yu Li,Sheng Tang*,Min Lin,Yongdong Zhang,Jintao Li,Shuicheng Yan,"Implicit Negative Sub-categorization and Sink Diversion for Object Detection",IEEE Transactions on Image Processing,27(4):1561-1574,April,2018.(CCF A类图像处理国际顶级期刊)

[7] Linghui Li,Sheng Tang*,Lixi Deng,Yongdong Zhang and Qi Tian;“GLA: Global-local Attention for Image Description”,IEEE Transactions on Multimedia,20(3):726-737,March,2018. (CCF B类多媒体国际期刊)

[8] YongDong Zhang,Yu Wang,Sheng Tang*,Steven C. H. Hoi,JinTao Li;“FSpH: Fitted Spectral Hashing Exploring Entropy Maximizing Criterion for Efficient Retrieval”,Computer Vision and Image Understanding (CVIU),Computer Vision and Image Understanding (CVIU),124: 3-11,2014. (CCF B类国际著名期刊)

[9] Wu Liu,Yongdong Zhang, Sheng Tang,Jinhui Tang,Richang Hong and Jintao Li;"Accurate Estimation of Human Body Orientation From RGB-D Sensors,"IEEE Transactions on Cybernetics,vol.43,no.5,pp.1442-1452,Oct. 2013. (CCF B类国际期刊)

[10] Hongtao Xie,Ke Gao,Yongdong Zhang,Sheng Tang,Jintao Li,and Yizhi Liu;“Efficient Feature Detection and Effective Post-Verification for Large Scale Near-Duplicate Image Search”,IEEE Transactions on Multimedia,13(6):1319-1332,Dec. 2011. (CCF B类多媒体国际期刊)

[11] Yan Song,Yan-Tao Zheng,Sheng Tang,Xiangdong Zhou,Yongdong Zhang,Shouxun Lin,and Tat-Seng Chua;“Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos”,IEEE Transactions on Circuits and Systems for Video Technology,21(9):1193-1202,Sept.2011. (CCF B类国际期刊)

会议文章(国际顶级会议长文14篇,其中CCF A类会议10篇, *表示通讯作者):

[12] Rui Zhang,Sheng Tang*,YongDong Zhang,Jintao Li,Shuicheng Yan;“Scale-adaptive Convolutions for Scene Parsing”,The 2017 IEEE International Conference on Computer Vision (ICCV) 2017,Pages: 2050-2058,Venice,Italy,October 22-29,2017. (CCF A类计算机视觉国际顶级会议长文)

[13] Yu Li,Tao Wang,Bingyi Kang,Sheng Tang*,Chunfeng Wang,Jintao Li,Jiashi Feng;“Overcoming Classi?er Imbalance for Long-tail Object Detection with Balanced Group Softmax”;IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020),Seattle,Washington,USA. June 16-18,2020. (CCF A类计算机视觉国际顶级会议长文,Oral)

[14] Junbin Xiao,Xindi Shang,Xun Yang,Sheng Tang,Tat-seng Chua;“Visual Relation Grounding in Videos”;16th European Conference on Computer Vision (ECCV'20),23-28 August 2020. (CCF B类计算机视觉国际顶级会议长文,Spotlight)

[15] Tao Wang,Yu Li,Bingyi Kang,Junnan Li,Jun Hao Liew,Sheng Tang,Steven Hoi,Jiashi Feng;“The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation”;16th European Conference on Computer Vision (ECCV'20),23-28 August 2020. (CCF B类计算机视觉国际顶级会议长文)

[16] Bin Wang,Guojun Qi,Sheng Tang*,Tianzhu Zhang,Yunchao Wei,Linghui Li,Yongdong Zhang;“Boundary Perception Guidance: A Scribble-Supervised Semantic Segmentation Approach”,The 28th International Joint Conference on Artificial Intelligence (IJCAI 2019),Pages: 3663-3669,August 10-16,2019,Macao,China (CCF A类人工智能国际顶级会议长文).

[17] Rui Zhang,Sheng Tang*,Luoqi Liu,Yongdong Zhang,Jintao Li,Shuicheng Yan;“High Resolution Feature Recovering for Accelerating Urban Scene Parsing”,The 27th International Joint Conference on Artificial Intelligence (IJCAI 2018),Pages: 1156-1162,Stockholm,Sweden,July 13-19,2018(CCF A类人工智能国际顶级会议长文)

[18] Rui Zhang,Sheng Tang*,Min Lin,Jintao Li,Shuicheng Yan;“Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions”,The 26th International Joint Conference on Artificial Intelligence (IJCAI 2017),Pages:3427-3433,Melbourne,Australia,August 19-25,2017(CCF A类人工智能国际顶级会议长文)

[19] Yuchen Guo,Guiguang Ding,Jungong Han,Sheng Tang;“Zero-shot Learning with Attribute Selection”,The 32th AAAI Conference on Artificial Intelligence (AAAI 2018),February 2-7,2018,New Orleans,USA. (CCF A类人工智能国际顶级会议长文)

[20] Xiaohan Ding,Guiguang Ding,Jungong Han,Sheng Tang;“Auto-balanced Filter Pruning for Efficient Convolutional Neural Networks”,The 32th AAAI Conference on Artificial Intelligence (AAAI 2018),February 2 - 7,2018,New Orleans,USA. (CCF A类人工智能国际顶级会议长文)

[21] Linghui Li,Sheng Tang*,Lixi Deng,Yongdong Zhang,Qi Tian;“Image Caption with Global-Local Attention”,The 31th AAAI Conference on Artificial Intelligence (AAAI 2017),Pages: 4133-4139,San Francisco,California USA,February 4–9,2017 (CCF A类人工智能国际顶级会议长文)

[22] Lixi Deng,Jingjing Chen,Qianru Sun,Xiangnan He,Sheng Tang,Zhaoyan Ming,Yongdong Zhang,Tat Seng Chua;“Mixed-dish Recognition with Contextual Relation Network”,ACM Multimedia 2019,Pages: 112-120,Nice,France,21-25 October,2019. (CCF A类多媒体国际顶级会议长文)

[23] Rui Zhang,Sheng Tang*,Yu Li,Junbo Guo,Yongdong Zhang,Jintao Li,Shuicheng Yan;“Style Separation and Synthesis via Generative Adversarial Networks”,ACM Multimedia 2018,Pages: 183-191,Oct.22-26,2018,Seoul,Korea. (CCF A类多媒体国际顶级会议长文).

[24] Lixi Deng,Sheng Tang*,Huazhu Fu,Bin Wang,Yongdong Zhang;“Spatiotemporal Breast Mass Detection Network (MD-Net) in 4D DCE-MRI Images”,International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2019),LNCS 11767,Pages: 271-279,Oct. 13-17,2019,Shenzhen,China. (医疗影像处理国际顶级会议长文)

[25] Bin Wang,Guo-Jun Qi,Sheng Tang*,Liheng Zhang,Lixi Deng,Yongdong Zhang;“Automated Pulmonary Nodule Detection: High Sensitivity with Few Candidates”,International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2018),LNCS 11071,Pages:759–767,September 16-20,2018,Granada,Spain. (医疗影像处理国际顶级会议长文)

授权专利:

[1] 唐胜、王斌、张勇东,一种基于涂鸦的弱监督语义分割方法与系统;授权日期:202197日,授权专利号:CN201910588880.1

[2] 唐胜、伍天意、李锦涛,基于上下文信息指导的场景分割方法与系统;授权日期:2021427日,授权专利号:CN201811309249.5

[3] 唐胜、伍天意、李锦涛,基于克罗内克卷积的场景分割方法与系统;授权日期:202146日,授权专利号:CN201811309245.7

[4] 唐胜、张蕊、李锦涛,基于特征图恢复的场景分割方法和系统.;授权日期:20201211日,授权专利号:CN201810664250.3

[5] 唐胜、张蕊、李锦涛,融合全局信息的场景分割修正方法与系统;授权日期:2020911日,授权专利号:CN201710650525.3

[6] 唐胜、张蕊、李锦涛,融合局部信息的场景分割修正方法与系统;授权日期:2020626日,授权专利号:CN201710650541.2

[7] 唐胜、肖俊斌、李锦涛,一种基于目标检测的大规模图像检索方法与系统;授权日期:202065日,授权专利号:CN201710574741.4

[8] 唐胜、李灵慧、张勇东、李锦涛,一种生成描述图像内容的自然语言的方法与系统;授权日期:2020121日,授权专利号:CN201711265210.3

[9] 唐胜、张勇东、李锦涛、徐作新;字典学习、视觉词袋特征提取方法及检索系统;授权日期:2017630日,授权专利号:CN201410287639.2

[10] 唐胜、李锦涛、张勇东、谢 呈;一种数字图像训练和检测方法;授权日:201336日,授权专利号:CN200910092710.0

科研项目:

[1] 国家自然科学基金面上项目,基于稀疏表示和深度学习的大规模目标检测(61572472)78.4万,2016/01-2019/12,项目负责人

[2] 国家自然科学基金面上项目,基于跨域迁移学习的网络视频检索技术研究(61173054)57万元,2012/01-2015/12,项目负责人

[3]国家自然科学基金面上项目,融合显式和隐含语义概念的视频检索技术研究(60873165)30万,2009/01-2011/12,项目负责人

[4] 北京市自然科学基金面上项目,基于稀疏表示的大规模移动视觉搜索技术研究(4152050)18万,2015/01-2017/12,项目负责人



获奖及荣誉:

科研获奖:

12019年国家自然科学奖二等奖,获奖项目为互联网视频流的高通量计算理论与方法

22020年北京市科技进步奖一等奖,获奖项目为开放环境下数字伪造内容检测关键技术与服务平台建设

32018年中国电子学会科学技术奖(自然科学类)一等奖,获奖项目为互联网视频的高效流式计算理论与方法

42017年中国电子学会科学技术奖(技术发明类)一等奖,获奖项目为视觉大数据检索与智能分析关键技术及应用

52014年北京市科学技术奖一等奖,获奖项目为大规模网络视频处理与内容分析关键技术及应用

62012年首届中国计算机学会科学技术奖,获奖项目为大规模网络视频内容分析关键技术及应用

72006年北京市科学技术奖一等奖,获奖项目为面向体育训练的三维人体运动模拟与视频分析系统

国际竞赛:

1ACM Multimedia 2021多模态商品识别挑战赛,冠军。

2ICCV 2019大规模长尾实例分割挑战赛,冠军。

32016年国际ImageNet大规模视觉识别挑战赛(ILSVRC),获视频目标检测和语义分割任务全球第三。