基本信息

唐胜  男  研究员 博士生导师  中国科学院计算技术研究所
电子邮件: ts@ict.ac.cn
通信地址: 北京市海淀区科学院南路6号:中国科学院计算技术研究所前瞻研究室
邮政编码: 100190

研究领域

计算机视觉与深度学习、模式识别、多媒体内容分析与检索

教育背景

2001-09--2006-03   中国科学院计算技术研究所   工学博士
1998-09--2001-07   湘潭大学   工学硕士
1989-10--1993-06   湘潭大学   工学学士
学历
1. 2001年09月–2006年3月,中科院计算所博士研究生,计算机应用技术专业,获工学博士学位;
2. 1998年09月–2001年6月,湘潭大学计算机科学系硕士研究生,获工学硕士学位;
3. 1989年10月–1993年6月,湘潭大学机械工程系本科生,获工学学士学位。
学位
2006年3月,于中科院计算所博士毕业,计算机应用技术专业,获工学博士学位
出国学习工作
1. 2009年2月-2010年2月:国家公派访问学者,访问新加坡国大学一年,主要研究视频检索与事件检测。
2. 2006年7月-2006年8月:2006年应Prof Chua Tat-Seng邀请,访问了新加坡国立大学计算机学院,参加并完成了国际视频检索权威评测TRECVID。回国后,带领小组参加TRECVID,并在2007年和2008年连续两年取得了优异成绩,参加TRECVID 2008 并做大会报告(http://www-nlpir.nist.gov/projects/tvpubs/tv.pubs.org.html)。2007年联合新加坡国立大学研发的交互式视频检索系统VisionGo,在国际图像视频检索会议CIVR2007中获视频检索现场评测最佳系统奖(http://www.videolympics.org/)

工作经历

   
工作简历
2021-09~现在, 中国科学院计算技术研究所, 研究员
2018-12~现在, 中国科学院计算技术研究所, 博士生导师
2009-02~现在, 中国科学院计算技术研究所, 硕士生导师
2008-03~2021-09,中国科学院计算技术研究所, 副研究员
2006-03~2008-03,中国科学院计算技术研究所, 助理研究员
1993-06~1998-09,湘潭大学, 助理工程师、工程师

专利与奖励

   
奖励信息
(1) 开放环境下数字伪造内容检测关键技术与服务平台建设, 一等奖, 省级, 2020
(2) 互联网视频流的高通量计算理论与方法(2019年国家自然科学二等奖), 二等奖, 国家级, 2019
(3) 互联网视频的高效流式计算理论与方法(中国电子学会科学技术奖), 一等奖, 其他, 2018
(4) 视觉大数据检索与智能分析关键技术及应用(中国电子学会科学技术奖), 一等奖, 其他, 2017
(5) 2016年ImageNet大规模视觉识别挑战赛(ILSVRC 2016),图像目标检测(DET)任务全球第四(国内第三),视频目标检测(VID)任务全球第三(国内第二),语义分割任务全球第三(国内第一),应邀做大会报告, , 专项, 2016
(6) 2015年ImageNet大规模视觉识别挑战赛(ILSVRC 2015),分类定位(LOC)任务第四(国内第二),目标检测(DET)任务全球第五(国内第一), , 专项, 2015
(7) 大规模网络视频处理与内容分析关键技术及应用(北京市科学技术奖), 一等奖, 省级, 2014
(8) 大规模网络视频内容分析关键技术及应用(2012年首届中国计算机学会科学技术奖), , 其他, 2012
(9) 面向体育训练的三维人体运动模拟与视频分析系统(北京市科学技术奖), 一等奖, 省级, 2006
专利成果
[1] 唐胜, 伍天意, 李锦涛. 基于上下文信息指导的场景分割方法和系统. CN: CN109657538B, 2021-04-27.
[2] 唐胜, 伍天意, 李锦涛. 基于克罗内克卷积的场景分割方法和系统. CN: CN109670506B, 2021-04-06.
[3] 唐胜, 张蕊, 李锦涛. 基于特征图恢复的场景分割方法和系统. CN: CN109034198B, 2020-12-11.
[4] 刘春阳, 张旭, 陈志鹏, 唐胜, 王鹏, 张翔宇, 张丽, 万大千, 张勇东. 特定人物丑化图片识别方法及系统. CN: CN111832622A, 2020-10-27.
[5] 刘春阳, 张旭, 陈志鹏, 唐胜, 王鹏, 张翔宇, 张丽, 曹智, 张勇东. 基于稠密多路卷积网络的图片分类方法与系统. CN: CN111832621A, 2020-10-27.
[6] 唐胜, 李瑜, 李锦涛, 曹娟, 张勇东. 一种长尾目标检测方法与系统. CN: CN111832406A, 2020-10-27.
[7] 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. CN: CN107564007B, 2020-09-11.
[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. CN: CN107918782B, 2020-01-21.
[9] 唐胜, 伍天意, 李锦涛, 张勇东. 基于一致性特征的场景分割方法和系统. CN: CN110472493A, 2019-11-19.
[10] 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. CN: CN110443818A, 2019-11-12.
[11] 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. 中国: CN107564013A, 2018.01.09.
[12] 唐胜, 肖俊斌, 李锦涛. 一种基于目标检测的视觉目标检索方法与系统. 中国: CN107515895A, 2017.12.26.
[13] 张勇东, 曹阳, 高科, 唐胜. 一种基于颜色对比度的局部区域检测子提取方法及系统. 中国: CN104881669A, 2015-09-02.
[14] 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. 中国: CN104036012A, 2014-09-10.
[15] 唐胜, 韩淇, 张勇东, 李锦涛. 一种基于集成学习的模式训练和识别方法. 中国: CN102521599A, 2012-06-27.
[16] 谢呈, 刘毅志, 唐胜, 张勇东, 李锦涛. 色情检测模型建立方法和色情检测方法. 中国: CN101819638A, 2010-09-01.
[17] 刘安安, 李锦涛, 张勇东, 唐胜, 宋砚. 一种多模态融合的采访镜头检测方法. 中国: CN101316327B, 2010-05-26.
[18] 唐胜, 钱跃良, 林守勋, 李锦涛. 乱笔顺库建立方法及联机手写汉字识别评测系统. 中国: CN1317664, 2007-05-23.
[19] 钱跃良, 唐胜, 李锦涛, 褚诚缘, 谢萦. 个人数字助理远程通信系统及流量控制方法. 中国: CN1393784, 2003-01-29.

合作情况

   
项目协作单位
1. Prof. Chua Tat-Seng: School of Computing, National University of Singapore, http://www.comp.nus.edu.sg/~chuats/ 

2. Dr Yan-Tao ZHENG: Institute for Infocomm Research (I2R), Singapore, http://www1.i2r.a-star.edu.sg/~yzheng/

指导学生

已指导学生

韩淇  硕士研究生  081203-计算机应用技术  

徐作新  硕士研究生  081203-计算机应用技术  

张雅琳  硕士研究生  081203-计算机应用技术  

曹智  硕士研究生  081203-计算机应用技术  

陈慧  硕士研究生  081203-计算机应用技术  

曹阳  硕士研究生  081203-计算机应用技术  

肖俊斌  硕士研究生  081203-计算机应用技术  

秦欢  硕士研究生  081203-计算机应用技术  

伍天意  硕士研究生  081201-计算机系统结构  

张亭亭  硕士研究生  081203-计算机应用技术  

张睿  硕士研究生  081203-计算机应用技术  

张葭琦  硕士研究生  081203-计算机应用技术  

现指导学生

巩力铜  硕士研究生  081203-计算机应用技术  

柯芷莹  硕士研究生  081203-计算机应用技术  

王志浩  硕士研究生  081203-计算机应用技术  

周晨鸣  博士研究生  081203-计算机应用技术  

房海鹏  硕士研究生  081203-计算机应用技术  

张瑞泽  博士研究生  081203-计算机应用技术  

陈凌子  硕士研究生  085400-电子信息  

出版信息

   
发表论文
[1] Zijie Yang, Lingxi Xie, Wei Zhou, Xinyue Huo, Longhui Wei, Jian Lu, Qi Tian, Sheng Tang. VoxSeP: semi-positive voxels assist self-supervised 3D medical segmentation. Multimedia System[J]. 2023, 29(1): 33-48, https://link.springer.com/article/10.1007/s00530-022-00977-9.
[2] Tianyun Yang, Danding Wang, Fan Tang, Xinying Zhao, Juan Cao, Sheng Tang. Progressive Open Space Expansion for Open-Set Model Attribution. IEEE Conference on Computer Vision and Pattern Recognition(CCF A类计算机视觉国际顶级会议)null. 2023, https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Progressive_Open_Space_Expansion_for_Open-Set_Model_Attribution_CVPR_2023_paper.pdf.
[3] Litong Gong, Ruize Zhang, Sheng Tang, Juan Cao. Temporal Correlation-Diversity Representations for Video-Based Person Re-Identification. The 5th Chinese Conference on Pattern Recognition and Computer Visionnull. 2022, https://link.springer.com/chapter/10.1007/978-3-031-18907-4_8.
[4] Zijie Yang, Lingxi Xie, Xinyue Huo, Sheng Tang, Qi Tian, Yongdong Zhang. Finding the Host from the Lesion by Iteratively Mining the Registration Graph.. ACM Multimedia(CCF A类多媒体领域国际顶级会议,通讯作者)null. 2022, https://dl.acm.org/doi/pdf/10.1145/3503161.3548192.
[5] Tianyi Wu, Sheng Tang, Rui Zhang, Guodong Guo. Consensus Feature Network for Scene Parsing. IEEE Transactions on Multimedia(CCF B类多媒体领域国际顶刊,通讯作者)[J]. 2022, 24: 3208-3217, https://ieeexplore.ieee.org/document/9473001.
[6] Lixi Deng, Jingjing Chen, ChongWah Ngo, Qianru Sun, Sheng Tang, Yongdong Zhang, TatSeng Chua. Mixed Dish Recognition With Contextual Relation and Domain Alignment. IEEE Transactions on Multimedia(CCF B类多媒体领域国际顶刊)[J]. 2022, 24: 2034-2045, http://dx.doi.org/10.1109/TMM.2021.3075037.
[7] Linghui Li, Yongdong Zhang, Sheng Tang, Lingxi Xie, Xiaoyong Li, Qi Tian. Adaptive Spatial Location with Balanced Loss for Video Captioning. IEEE Transactions on Circuits and Systems for Video Technology(CCF B类视频处理顶刊)[J]. 2022, 32(1): 17-30, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9298810.
[8] Litong Gong, Sheng Tang, Juan Cao. Domain Balanced Sampling and Iterative Search for Product Identification. In Proceedings of the ACM Multimedia Workshop on Multimodal Product Identification in Livestreaming and WAB Challenge(WAB ’21)null. 2021, https://dl.acm.org/doi/10.1145/3475956.3484483.
[9] Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Yongdong Zhang. CGNet: A Light-Weight Context Guided Network for Semantic Segmentation. IEEE Transactions on Image Processing(CCF A类图像处理国际顶刊,通讯作者)[J]. 2021, 30: 1169-1179, [10] Jiaqi Zhang, Sheng Tang, Xu Zhang, Yu Li, Rui Zhang. Ahff-Net: Adaptive Hierarchical Feature Fusion Network For Image Inpainting. 2020 International Conference on Image Processing[J]. 2020, 478-482, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9191344.
[11] Junbin Xiao, Sheng Tang. Joint Learning of Binary Classifiers and Pairwise Label Correlations for Multi-label Image Classification. Third International Conference on Multimedia Processing and Retrieval (MIPR 2020)[J]. 2020, 25-30, http://dx.doi.org/10.1109/MIPR49039.2020.00013.
[12] Junbin Xiao, Xindi Shang, Xun Yang, Sheng Tang, TatSeng Chua. Visual Relation Grounding in Videos. European Conference on Computer Vision(CCF B类计算机视觉国际顶级会议)null. 2020, http://arxiv.org/abs/2007.08814.
[13] 陈辰, 唐胜, 李锦涛. 动态生成掩膜弱监督语义分割. 中国图象图形学报[J]. 2020, 25(6): 1190-1200, http://lib.cqvip.com/Qikan/Article/Detail?id=7102356812.
[14] Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng. Overcoming Classifier 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,通讯作者)null. 2020, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9156611.
[15] Yun Song, Dengyong Zhang, Qiang Tang, Sheng Tang, Kun Yang. Local and nonlocal constraints for compressed sensing video and multi-view image recovery. Neurocomputing[J]. 2020, 406: 34-48, http://dx.doi.org/10.1016/j.neucom.2020.04.072.
[16] Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng. The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation. European Conference on Computer Vision(CCF B类计算机视觉国际顶级会议)null. 2020, http://arxiv.org/abs/2007.11978.
[17] 邓旭冉, 李灵慧, 唐胜, 张勇东. 图像内容自动描述技术综述. 信息安全研究[J]. 2019, 5(11): 988-992, http://lib.cqvip.com/Qikan/Article/Detail?id=7100184177.
[18] Deng, Lixi, Tang, Sheng, Fu, Huazhu, Wang, Bin, Zhang, Yongdong, Shen, D, Liu, T, Peters, TM, Staib, LH, Essert, C, Zhou, S, Yap, PT, Khan, A. Spatiotemporal Breast Mass Detection Network (MD-Net) in 4D DCE-MRI Images. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019(CCF B类医学图像期刊)[J]. 2019, 11767: 271-279, [19] Sheng Tang. Boundary Perception Guidance: A Scribble-Supervised Semantic Segmentation Approach. The 28th International Joint Conference on Artificial Intelligence (IJCAI-2019), August 10-16, 2019, Macao, China (CCF A类人工智能国际顶级会议长文,通讯作者). 2019, [20] Li, Yu, Tang, Sheng, Zhang, Rui, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Asymmetric GAN for Unpaired Image-to-Image Translation. IEEE Transactions on Image Processing(CCF A类图像处理国际顶刊,通讯作者)[J]. 2019, 28(12): 5881-5896, http://doi.org/10.1109/TIP.2019.2922854.
[21] Wu Tianyi, Tang Sheng, Zhang Rui, Guo Guodong, Zhang Yongdong. Consensus Feature Network for Scene Parsing. 2019, http://arxiv.org/abs/1907.12411.
[22] Sheng Tang. Mixed-dish Recognition with Contextual Relation Network. ACM Multimedia 2019, Nice, France, 21-25 October, 2019. (CCF A类国际顶级会议长文). 2019, [23] Deng, Lixi, Chen, Jingjing, Sun, Qianru, He, Xiangnan, Tang, Sheng, Ming, Zhaoyan, Zhang, Yongdong, Chua, TatSeng, ACM. Mixed-dish Recognition with Contextual Relation Networks. PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)null. 2019, 112-120, http://dx.doi.org/10.1145/3343031.3351147.
[24] Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Jintao Li. Tree-Structured Kronecker Convolutional Network for Semantic Segmentation. IEEE ICME 2019[J]. 2019, 940-945, [25] Zhang, Rui, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Perspective-Adaptive Convolutions for Scene Parsing. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2019, 42(4): 909-924, http://dx.doi.org/10.1109/TPAMI.2018.2890637.
[26] Wang, Bin, Tang, Sheng, Xiao, JunBin, Yan, QuanFeng, Zhang, YongDong. Detection and tracking based tubelet generation for video object detection. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION[J]. 2019, 58: 102-111, http://dx.doi.org/10.1016/j.jvcir.2018.11.014.
[27] Li, Yu, Tang, Sheng, Zhang, Rui, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Asymmetric GAN for Unpaired Image-to-Image Translation. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(12): 5881-5896, http://dx.doi.org/10.1109/TIP.2019.2922854.
[28] Li, Linghui, Tang, Sheng, Guo, Junbo, Wang, Rui, Lyu, Bo, Tian, Qi, Zhang, Yongdong, IEEE. Image Captioning Based on Adaptive Balancing Loss. 2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM)null. 2018, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000630423400010.
[29] Sheng Tang. High Sensitivity with Tiny Candidates for Pulmonary Nodule Detection. International Conference On Medical Image Computing and Computer Assisted Intervention (MICCAI 2018), September 16-20, 2018, Granada, Spain. (Proventional Accept without Rebuttal, 医疗影像处理国际顶级会议长文,通讯作者). 2018, [30] Li, Linghui, Tang, Sheng, Zhang, Yongdong, Deng, Lixi, Tian, Qi. GLA: Global-Local Attention for Image Description. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2018, 20(3): 726-737, http://dx.doi.org/10.1109/TMM.2017.2751140.
[31] Zhang Rui, Tang Sheng, Liu Luoqi, Zhang, Yongdong, Li Jintao, Yan, Shuicheng. High Resolution Feature Recovering for Accelerating Urban Scene Parsing. The 27th International Joint Conference on Artificial Intelligence (IJCAI-2018), Stockholm, Sweden, July 13-19, 2018(CCF A类人工智能国际顶级会议长文, 通讯作者)[J]. 2018, [32] Zhang, Rui, Tang, Sheng, Li, Yu, Guo, Junbo, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng, ACM. Style Separation and Synthesis via Generative Adversarial Networks. PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18)null. 2018, 183-191, http://dx.doi.org/10.1145/3240508.3240524.
[33] Li, Yu, Tang, Sheng, Lin, Min, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Implicit Negative Sub-Categorization and Sink Diversion for Object Detection. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2018, 27(4): 1561-1574, http://dx.doi.org/10.1109/TIP.2017.2779270.
[34] Ding, Xiaohan, Ding, Guiguang, Han, Jungong, Tang, Sheng, AAAI. Auto-Balanced Filter Pruning for Efficient Convolutional Neural Networks. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2018, 6797-6804, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485488906108.
[35] Guo, Yuchen, Ding, Guiguang, Han, Jungong, Tang, Sheng, AAAI. Zero-Shot Learning with Attribute Selection. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2018, 6870-6877, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485488906117.
[36] Sheng Tang. Learning and Thinking Strategy for Training Sequence Generation Models. British Machine Vision Conference (BMVC) 2018,Newcastle, UK, September 3-6, 2018.(计算机视觉领域著名国际会议,通讯作者). 2018, [37] 王斌, 刘洋, 唐胜, 郭俊波. 融合多模型和帧间信息的行人检测算法. 计算机辅助设计与图形学学报[J]. 2017, 29(3): 444-449, http://lib.cqvip.com/Qikan/Article/Detail?id=7000133743.
[38] Tang, Sheng, Li, Yu, Deng, Lixi, Zhang, Yongdong. Object Localization Based on Proposal Fusion. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2017, 19(9): 2105-2116, http://dx.doi.org/10.1109/TMM.2017.2729786.
[39] Wan, Ji, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Wu, Pengcheng, Hoi, Steven C H. HDIdx: High-dimensional indexing for efficient approximate nearest neighbor search. NEUROCOMPUTING[J]. 2017, 237: 401-404, http://dx.doi.org/10.1016/j.neucom.2015.11.104.
[40] Zhang, Rui, Tang, Sheng, Liu, Wu, Zhang, Yongdong, Li, Jintao. Multi-modal tag localization for mobile video search. MULTIMEDIA SYSTEMS[J]. 2017, 23(6): 713-724, http://dx.doi.org/10.1007/s00530-016-0506-9.
[41] Zhang, Rui, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng, IEEE. Scale-adaptive Convolutions for Scene Parsing. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)null. 2017, 2050-2058, [42] Li Linghui, Tang Sheng, Deng Lixi, Zhang Yongdong, Tian Qi, AAAI. Image Caption with Global-Local Attention. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCEnull. 2017, 4133-4139, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485630704026.
[43] 贾佳, 唐胜, 谢洪涛, 肖俊斌. 移动视觉搜索综述. 计算机辅助设计与图形学学报[J]. 2017, 29(6): 1007-1021, http://lib.cqvip.com/Qikan/Article/Detail?id=7000217496.
[44] Zhang Rui, Tang Sheng, Li Min, Li Jintao, Yan Shuicheng. 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,通讯作者)[J]. 2017, [45] Sheng Tang. Category Aggregation Among Region Proposals for Object Detection. Advances in Multimedia Information Processing - PCM 2016 - 17th Pacific-Rim Conference on Multimedia, Pages: 210-220, Xi'an, China, September 15-16, 2016(CCF C类国际会议,通讯作者). 2016, [46] Gao, Xingyu, Chen, Zhenyu, Tang, Sheng, Zhang, Yongdong, Li, Jintao. Adaptive weighted imbalance learning with application to abnormal activity recognition. NEUROCOMPUTING[J]. 2016, 173: 1927-1935, http://dx.doi.org/10.1016/j.neucom.2015.09.064.
[47] Sheng Tang. Scalable Logo Recognition based on Compact Sparse Dictionary for Mobile Device. THE 17TH IEEE INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), (TOP 10% PAPER AWARD). 2015, [48] Sheng Tang. A Sparse Ensemble Learning System For Efficient Semantic Indexing. ACM International Conference on Multimedia Retrieval (ICMR), June 23-26. 2015, [49] Tang Sheng, Chen Hui, Lv Ke, Zhang YongDong, IEEE. Large Visual Words for Large Scale Image Classification. 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2015, 1170-1174, [50] Tang, Sheng, Zhang, YongDong, Xu, ZuoXin, Li, HaoJie, Zheng, YanTao, Li, JinTao. An efficient concept detection system via sparse ensemble learning. NEUROCOMPUTING[J]. 2015, 169: 124-133, http://dx.doi.org/10.1016/j.neucom.2014.09.100.
[51] Liang, Feidie, Tang, Sheng, Zhang, Yongdong, Xu, Zuoxin, Li, Jintao. Pedestrian detection based on sparse coding and transfer learning. MACHINE VISION AND APPLICATIONS[J]. 2014, 25(7): 1697-1709, http://dx.doi.org/10.1007/s00138-013-0549-2.
[52] Zhang, YongDong, Wang, Yu, Tang, Sheng, Hoi, Steven C H, Li, JinTao. FSpH: Fitted spectral hashing for efficient similarity search. COMPUTER VISION AND IMAGE UNDERSTANDING[J]. 2014, 124: 3-11, http://dx.doi.org/10.1016/j.cviu.2014.01.011.
[53] Sheng Tang. A Representative Local Region Detector Based On Color-Contrast-MSER. ACM International Conference on Multimedia Retrieval (ICMR). 2014, [54] Wang, Yu, Tang, Sheng, Zheng, YanTao, Zhang, YongDong, Li, JinTao. Semi-supervised learning via sparse model. NEUROCOMPUTING[J]. 2014, 131: 124-131, http://dx.doi.org/10.1016/j.neucom.2013.10.033.
[55] 唐胜, 高科, 顾晓光, 颜成钢, 张勇东. 高通量视频内容分析技术. 工程研究:跨学科视野中的工程[J]. 2014, 6(3): 294-306, http://lib.cqvip.com/Qikan/Article/Detail?id=662341424.
[56] Yizhi Liu, Ying Yang, Hongtao Xie, Sheng Tang. Fusing audio vocabulary with visual features for pornographic video detection. FUTURE GENERATION COMPUTER SYSTEMS. 2014, 69-76, http://dx.doi.org/10.1016/j.future.2012.08.012.
[57] Zhang Yongdong, Wang Yu, Tang, Sheng, Steven C.H. Hoi, Li Jintao. FSpH: Fitted spectral hashing for efficient similarity search. Computer Vision and Image Understanding (CVIU), 124: 3-11[J]. 2014, [58] Wang, Yu, Tang, Sheng, Zhang, YongDong, Li, JinTao, Wang, Dong. Representative selection based on sparse modeling. NEUROCOMPUTING[J]. 2014, 139: 423-431, http://dx.doi.org/10.1016/j.neucom.2014.02.013.
[59] Sheng Tang. Ensemble Learning with LDA Topic Models for Visual Concept Detection. Multimedia - A Multidisciplinary Approach to Complex Issues , Ioannis Karydis (Ed.), ISBN: 978-953-51-0216-8, InTech - Open Access Publisher, chapter 9, pages: 175-200. 2013, [60] Wan, Ji, Tang, Sheng, Zhang, Yongdong, Huang, Lei, Li, Jintao, IEEE. DATA DRIVEN MULTI-INDEX HASHING. 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)null. 2013, 2670-2673, [61] Xie, Hongtao, Zhang, Yongdong, Gao, Ke, Tang, Sheng, Xu, Kefu, Guo, Li, Li, Jintao. Robust common visual pattern discovery using graph matching. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION[J]. 2013, 24(5): 635-646, http://dx.doi.org/10.1016/j.jvcir.2013.04.012.
[62] Huang, Lei, Tang, Sheng, Zhang, Yongdong, Lian, Shiguo, Lin, Shouxun. Robust human body segmentation based on part appearance and spatial constraint. NEUROCOMPUTING[J]. 2013, 118: 191-202, http://dx.doi.org/10.1016/j.neucom.2013.03.003.
[63] Liu, Wu, Zhang, Yongdong, Tang, Sheng, Tang, Jinhui, Hong, Richang, Li, Jintao. Accurate Estimation of Human Body Orientation From RGB-D Sensors. IEEE TRANSACTIONS ON CYBERNETICS[J]. 2013, 43(5): 1442-1452, http://dx.doi.org/10.1109/TCYB.2013.2272636.
[64] Sheng Tang. Fast Pedestrian Detection Based on Sliding Window Filtering. Advances in Multimedia Information Processing – PCM 2012 , pp: 811-822, Singapore. 2012, [65] Tang, Sheng, Zheng, YanTao, Wang, Yu, Chua, TatSeng. Sparse Ensemble Learning for Concept Detection. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2012, 14(1): 43-54, https://www.webofscience.com/wos/woscc/full-record/WOS:000302701100005.
[66] Song, Yan, Tang, Sheng, Zheng, YanTao, Chua, TatSeng, Zhang, Yongdong, Lin, Shouxun. Exploring probabilistic localized video representation for human action recognition. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2012, 58(3): 663-685, http://dx.doi.org/10.1007/s11042-011-0748-7.
[67] Xu, Shaoxi, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Zheng, YanTao. Exploring multi-modality structure for cross domain adaptation in video concept annotation. NEUROCOMPUTING[J]. 2012, 95: 11-21, http://dx.doi.org/10.1016/j.neucom.2011.05.041.
[68] 刘毅志, 唐胜, 王向东, 林守勋, 张勇东. 融合音频单词与视觉特征的成人视频检测. 中国图象图形学报[J]. 2012, 17(7): 791-797, http://lib.cqvip.com/Qikan/Article/Detail?id=42507363.
[69] Xie, Hongtao, Gao, Ke, Zhang, Yongdong, Tang, Sheng, Li, Jintao, Liu, Yizhi. Efficient Feature Detection and Effective Post-Verification for Large Scale Near-Duplicate Image Search. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2011, 13(6): 1319-1332, https://www.webofscience.com/wos/woscc/full-record/WOS:000297343400012.
[70] 刘毅志, 杨颖, 唐胜, 林守勋. 基于视觉注意模型VAMAI的敏感图像检测方法. 中国图象图形学报[J]. 2011, 16(7): 1226-1233, http://lib.cqvip.com/Qikan/Article/Detail?id=38416929.
[71] Song, Yan, Zheng, YanTao, Tang, Sheng, Zhou, Xiangdong, Zhang, Yongdong, Lin, Shouxun, Chua, TatSeng. Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2011, 21(9): 1193-1202, http://dx.doi.org/10.1109/TCSVT.2011.2130230.
[72] Song, Yan, Tang, Sheng, Zheng, YanTao, Chua, TatSeng, Zhang, Yongdong, Lin, Shouxun, IEEE. A DISTRIBUTION BASED VIDEO REPRESENTATION FOR HUMAN ACTION RECOGNITION. 2010 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2010)null. 2010, 772-777, [73] 吴潇, 李锦涛, 唐胜, 郭俊波. 基于时空轨迹行为特征的视频拷贝检测方法. 计算机研究与发展[J]. 2010, 1871-1877, http://lib.cqvip.com/Qikan/Article/Detail?id=35890458.
[74] 刘安安, 李锦涛, 张勇东, 唐胜, 杨兆选, 吴佳鹏. 新闻视频结构化浏览与标注系统. 计算机工程[J]. 2009, 35(1): 33-35, http://lib.cqvip.com/Qikan/Article/Detail?id=29310569.
[75] 唐胜, 余乐军, 潘雪峰, 李锦涛, 张勇东, 夏添. 基于视觉感知的时空联合视频拷贝检测方法. 计算机学报[J]. 2009, 107-114, http://lib.cqvip.com/Qikan/Article/Detail?id=29336460.
[76] Sheng Tang. PornProbe: an LDA-SVM based Pornography Detection System. ACM Multimedia 2009. 2009, [77] Cao, Juan, Xia, Tian, Li, Jintao, Zhang, Yongdong, Tang, Sheng. A density-based method for adaptive LDA model selection. NEUROCOMPUTING[J]. 2009, 72(7-9): 1775-1781, http://www.corc.org.cn/handle/1471x/2401132.
[78] 杨旌, 唐胜, NEO. 结合全局轮廓变形的改进Snake算法. 湘潭大学自然科学学报[J]. 2008, 30(1): 135-140, http://lib.cqvip.com/Qikan/Article/Detail?id=26957257.
[79] 曹娟, 张勇东, 李锦涛, 唐胜. 一种基于密度的自适应最优LDA模型选择方法. 计算机学报[J]. 2008, 31(10): 1780-1787, http://lib.cqvip.com/Qikan/Article/Detail?id=28494700.
[80] Liu Anan, Tang Sheng, Zhang Yongdong, Song Yan, Li Jintao, Yang Zhaoxuan, IEEE. A Hierarchical Framework for Movie Content Analysis: Let Computers Watch Films like Humans. 2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3null. 2008, 683-+, [81] 唐胜. TRECVID 2008高级语义概念提取(MCG-ICT-CAS). Proc. TRECVID Workshop 2008. 2008, [82] Yang Ying, Lin Shouxun, Zhang Yongdong, Tang Sheng, IEEE. A statistical framework for replay detection in soccer video. PROCEEDINGS OF 2008 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-10null. 2008, 3538-3541, [83] 杨颖, 林守勋, 张勇东, 唐胜. 基于动态规划融合多模态的足球视频事件分析. 计算机辅助设计与图形学学报[J]. 2008, 20(8): 1056-1063, http://lib.cqvip.com/Qikan/Article/Detail?id=27954679.
[84] Song Yan, Liu Anan, Pang Lin, Lin Shouxun, Zhang Yongdong, Tang Sheng, Lee R. A novel image text extraction method based on k-means clustering. 7TH IEEE/ACIS INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE IN CONJUNCTION WITH 2ND IEEE/ACIS INTERNATIONAL WORKSHOP ON E-ACTIVITY, PROCEEDINGSnull. 2008, 185-190, http://dx.doi.org/10.1109/ICIS.2008.31.
[85] Gao, Ke, Lin, Shouxun, Zhang, Yongdong, Tang, Sheng, Shi, Z, MercierLaurent, E, Leake, D. Object-based Image Retrieval with Attention Analysis and Spatial Re-ranking. INTELLIGENT INFORMATION PROCESSING IVnull. 2008, 118-+, [86] 高科, 林守勋, 张勇东, 唐胜. 基于空间上下文的目标图像检索. 计算机辅助设计与图形学学报[J]. 2008, 20(11): 1452-1458, http://lib.cqvip.com/Qikan/Article/Detail?id=28720504.
[87] Yang Ying, Lin Shouxun, Zhang Yongdong, Tang Sheng, Yagi Y, Kang SB, Kweon IS, Zha H. Statistical framework for shot segmentation and classification in sports video. COMPUTER VISION - ACCV 2007, PT II, PROCEEDINGSnull. 2007, 4844: 106-115, [88] Cao Juan, Li Jintao, Zhang Yongdong, Tang Sheng. LDA-based retrieval framework for semantic news video retrieval. ICSC 2007: INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING, PROCEEDINGSnull. 2007, 155-+, http://dx.doi.org/10.1109/ICSC.2007.26.
[89] 唐胜. TRECVID 2007高级语义概念提取(MCG-ICT-CAS). Proc. TRECVID Workshop 2007. 2007, [90] Yang Ying, Lin Shouxun, Zhang Yongdong, Tang Sheng, IEEE. Highlights extraction in soccer videos based on goal-mouth detection. 2007 9TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOLS 1-3null. 2007, 356-359, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000259439900090.
[91] Zhang, YongDong, Tang, Sheng, Li, JinTao. Secure and incidental distortion tolerant digital signature for image authentication. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY[J]. 2007, 22(4): 618-625, http://lib.cqvip.com/Qikan/Article/Detail?id=24958766.
[92] 周建新, 高科, 李锦涛, 张勇东, 唐胜. 图像检索中一种有效的SVM相关反馈算法. 计算机辅助设计与图形学学报[J]. 2007, 19(4): 535-540, http://lib.cqvip.com/Qikan/Article/Detail?id=24260726.
[93] Liu Anan, Li Jintao, Zhang Yongdong, Tang Sheng, Song Yan, Yang Zhaoxuan, IEEE. Human attention model for action movie analysis. 2007 2ND INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND APPLICATIONS, VOLS 1 AND 2null. 2007, 204-+, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000253450200039.
[94] Sheng Tang. SSF Fingerprint for Image Authentication: An Incidental Distortion Resistant Scheme. Proc. ACM Multimedia 2005. 2005, [95] Tang, S, Li, JT, Zhang, YD, Gervasi, O, Gavrilova, ML, Kumar, V, Lagana, A, Lee, HP, Mun, Y, Taniar, D, Tan, CJK. Compact and robust image hashing. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2005, PT 2[J]. 2005, 3481: 547-556, http://www.corc.org.cn/handle/1471x/2377647.
[96] Tang, S, Li, JT, Zhang, YD, Marques, JS, PerezdelaBlanca, N, Pina, P. Compact and robust fingerprints using DCT coefficients of key blocks. PATTERN RECOGNITION AND IMAGE ANALYSIS, PT 2, PROCEEDINGS[J]. 2005, 3523: 521-528, http://www.corc.org.cn/handle/1471x/2377933.
[97] 刘宏, 李锦涛, 崔国勤, 唐胜. 基于SVM和纹理的笔迹鉴别方法. 计算机辅助设计与图形学学报[J]. 2003, 15(12): 1479-1484, http://lib.cqvip.com/Qikan/Article/Detail?id=8814257.
[98] 李锦涛, 唐胜, 周经野, 钱跃良. 一种基于模拟退火的自适应算法. 计算机工程与应用[J]. 2002, 38(18): 43-46, http://lib.cqvip.com/Qikan/Article/Detail?id=6895888.

科研活动

   
科研项目
( 1 ) 伪造检测软件加速和优化算法研发, 负责人, 研究所自主部署, 2021-06--2023-05
( 2 ) 自监督视频深伪检测关键技术研究, 负责人, 中国科学院计划, 2021-05--2023-12
( 3 ) 中国科学院计算技术研究所—寺库AI 联合实验室项目:奢侈品智能鉴定, 参与, 境内委托项目, 2019-05--2022-05
( 4 ) 基于影像组学的前列腺肿瘤风险评估与手术导航研究(子课题), 负责人, 国家任务, 2019-01--2022-12
( 5 ) 实培计划:基于深度学习的特定目标检索技术研究, 负责人, 地方任务, 2019-01--2019-07
( 6 ) 融合多通道语境信息的类人智能感知机制与方法, 负责人, 国家任务, 2017-10--2021-09
( 7 ) 图像语义自动标注研究(腾讯公司), 负责人, 境内委托项目, 2017-05--2018-04
( 8 ) 基于多模态类脑强化学习的微视频内容理解技术研究, 参与, 地方任务, 2017-05--2018-12
( 9 ) 基于稀疏表示和深度学习的大规模目标检测(国家自科基金面上项目61572472), 负责人, 国家任务, 2016-01--2019-12
( 10 ) 基于稀疏表示的大规模移动视觉搜索技术研究(北京市自科基金面上项目4152050), 负责人, 地方任务, 2015-01--2017-12
( 11 ) 异构媒体数据的关联与挖掘研究(863), 参与, 国家任务, 2014-01--2016-12
参与会议
(1)Style Separation and Synthesis via Generative Adversarial Networks   2018 ACM多媒体大会(CCF A类国际顶级会议)   2018-10-22
(2)High Resolution Feature Recovering for Accelerating Urban Scene Parsing   第27届国际人工智能联合大会(IJCAI 2018,CCF A类国际顶级会议)   2018-07-13
(3)Scale-adaptive Convolutions for Scene Parsing   IEEE国际计算机视觉大会(CCF A类计算机视觉国际顶级会议)   Rui Zhang, Sheng Tang, YongDong Zhang, Jintao Li, Shuicheng Yan   2017-10-22
(4)Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions   第26届国际人工智能联合大会(IJCAI 2017,CCF A类国际顶级会议)   Rui Zhang,Sheng Tang, Min Lin, Jintao Li, Shuicheng Yan   2017-08-19
(5)Image Caption with Global-Local Attention   第31届国际人工智能大会(AAAI-2017,CCF A类国际顶级会议)   Linghui Li, Sheng Tang, Lixi Deng, Yongdong Zhang and Qi Tian   2017-02-06
(6)MCG-ICT-CAS Object Detection at ILSVRC 2016   2015年欧洲计算机视觉会议及ImageNet大规模视觉识别挑战赛   2016-10-09
(7)MCG-ICT-CAS's Investigation of Model Sparsity and Category Information on Object Classification, Localization and Detection at ILSVRC 2015   2015年国际计算机视觉会议及ImageNet大规模视觉识别挑战赛   唐胜   2015-12-17
(8)Large Visual Words for Large Scale Image Classification   2015年国际图像处理会议   唐胜   2015-09-27
(9)Fitted Spectral Hashing   2013 ACM多媒体大会(CCF A类国际顶级会议)   Yu Wang, Sheng Tang, YaLin Zhang, Jintao Li, et al,   2013-10-21
(10)SSF Fingerprint for Image Authentication: An Incidental Distortion Resistant Scheme   2005 ACM多媒体大会(CCF A类国际顶级会议)   2009-11-06
(11)PornProbe: an LDA-SVM based Pornography Detection System   2009 ACM多媒体大会(CCF A类国际顶级会议)   2009-10-21
(12)TRECVID 2008 Content-Based Copy Detection By MCG-ICT-CAS   2008年国际视频检索评测会议   2008-11-17
(13)Active learning approach to interactive spatio-temporal news video retrieval   2007年国际图像视频检索会议   2007-07-09