pengyuxin

彭宇新 教授  [English]

彭宇新,北京大学二级教授、博士生导师、863首席专家,中国人工智能产业创新联盟专家委员会主任委员,中国工程院“人工智能2.0”规划专家委员会专家,北京大学信息与工程科学部教学指导委员会委员,北京大学计算机研究所学术委员会委员、多媒体信息处理研究室负责人。主要研究方向是:跨媒体分析与推理;图像视频理解与检索;机器学习与人工智能。2003年7月毕业于北京大学信息科学技术学院计算机应用技术专业,获理学博士学位。2003年8月-2004年11月在香港城市大学计算机科学系做访问学者。2006年入选教育部新世纪优秀人才支持计划和北京市科技新星计划(终期优秀),2007年获北京大学正大奖教金优秀奖,2008年获北京大学宝钢奖教金优秀奖,2010年获北京大学方正奖教金优秀奖,2011年获教育部科技进步二等奖(排名第三)、北京大学王选青年学者奖,2016年获北京市科学技术一等奖(排名第一),2017年获北京大学教学优秀奖。

主讲北京大学信息学院研究生必修课"数字图像处理",主持了863、国家自然科学基金、博士点基金(博导类)、发改委专项、北京市自然科学基金等20多个项目,其中2006-2008年主持的第一个国家自然科学基金项目结题获特优。在IJCV, TIP, TCSVT, TMM, PR等国际期刊和CVPR, ICCV, ACM-MM, IJCAI, AAAI等国际会议上发表论文上百篇。在国际评测上,6次参加由美国国家标准技术局NIST举办的国际比赛TRECVID,均获得第一名,参赛队伍包括斯坦福大学、卡内基梅隆大学、哥伦比亚大学、牛津大学等,具体成绩如下:2009年参加TRECVID视频语义特征提取比赛和视频搜索比赛获得4项第一名,2012年参加TRECVID视频搜索比赛的全部4项评测均获得第一名,2014年参加TRECVID视频搜索比赛获交互式搜索第一名;2015、2016、2017年参加TRECVID视频搜索比赛的全部2项评测——计算机自动搜索和交互式搜索,均获得第一名。在国内评测上,2014年参加了由中央网信办、科技部、国家自然科学基金委联合举办的第一届特定音视频分析系统评测资格大赛,参赛队伍包括北大、清华、中科大、国科大、国防科大、复旦、北邮、西安交大、中科院自动化所、计算所等30家单位,因为评测的优异表现,我们受中央网信办邀请提供关键技术和系统进行实际应用,也成为受公安部重大项目办邀请进行互联网图像视频分析与识别应用的唯一入选队伍。申请35项发明专利,已获16项专利授权,主持研发的互联网图像视频分析与识别系统已经应用于公安部、国家新闻出版广电总局、西藏网信办、中国教育电视台等单位。

中国图象图形学学会理事,北京图象图形学学会副秘书长,CCF、中国电子学会、中国人工智能学会高级会员,担任中国工程院院刊《Frontiers of Information Technology & Electronic Engineering》、《计算机研究与发展》等副编,《计算机研究与发展》“深度学习”专辑特邀编委,IScIDE委员会副主任委员,CCF专委工作委员会、CCF多媒体技术专业委员会、中国图象图形学学会多媒体专业委员会等委员。担任国家自然科学基金、北京市自然科学基金、博士后基金、公安部、司法部等项目的评审专家。担任人工智能顶级国际会议AAAI 2016、IJCAI 2015及国际会议ICIP 2017等领域主席,ACM-MM, IJCAI, AAAI, NIPS, ICME, ICIP, ICPR, ICMR, VCIP, PCM等十多个重要国际会议的程序委员会委员。



研究方向

  • 跨媒体分析与推理
  • 图像视频理解与检索
  • 机器学习与人工智能

主要科研项目


  1. 国家自然科学基金面上项目:视觉注意力驱动的图像视频分类与检索研究,项目负责人,2018年1月-2021年12月。
  2. 国家自然科学基金重点项目:混杂数据的模式识别及敏感内容挖掘理论与方法,第二完成人,2016年1月-2020年12月。
  3. 国家科技支撑计划:专题负责人,2015年4月-2017年12月。
  4. 国家863计划项目:面向政府管理的大数据内容理解与智能服务,首席专家,2014年1月-2016年12月。
  5. 国家自然科学基金面上项目:基于内容的跨媒体检索研究,项目负责人,2014年1月-2017年12月。
  6. 博士点基金(博导类):基于统一表示和相似性计算的跨媒体检索研究,项目负责人,2013年1月-2015年12月。
  7. 863重点专项课题4:课题负责人,2012年1月-2014年12月。
  8. 863重点专项课题1:参与,2012年1月-2014年12月。
  9. 国家科技支撑计划:监控视频语义感知和服务系统研发及应用示范,参与,2012年1月-2014年12月。
  10. 国家发改委专项:基于内容识别的网络视音频系统产业化,项目负责人,2010年7月-2012年7月。
  11. 国家自然科学基金面上项目:视频概念标注方法及其在视频语义检索中的应用,项目负责人,2011年1月-2013年12月。
  12. 国家自然科学基金面上项目:机器学习中模型选择问题的研究及其在图像理解中的应用,项目负责人,2009年1月-2011年12月。
  13. 国家自然科学基金青年基金项目:基于多媒体特征的视频语义片断检索关键技术的研究,项目负责人,2006年1月-2008年12月,结题评价:特优(约前5%)。
  14. 国家242项目,项目负责人,2006年11月-2008年5月。
  15. 北京市科技新星计划,项目负责人,2006年9月-2009年9月。
  16. 教育部新世纪优秀人才支持计划:视频内容的语义分析和检索,项目负责人,2007年1月-2009年12月。
  17. 北京市自然科学基金:基于概念的视频检索关键技术的研究,项目负责人,2012年1月-2014年12月。
  18. 北京市自然科学基金:新闻视频语义检索关键技术的研究,项目负责人,2008年1月-2010年12月。
  19. 中国教育电视台应用项目:国家教育新媒体平台的内容安全审查平台,项目负责人,2011年8月-2012年8月。
  20. 企业项目:图片和视频文字识别技术的研究,项目负责人,2007年6月-2008年12月。
  21. 企业项目:Web有害图像和视频的识别技术研究,项目负责人,2008年12月-2010年12月。
  22. 国家发改委项目:新一代宽带流媒体增值业务支撑平台研发及产业化,参加,2008年4月-2010年4月。

国际权威评测


  1. 2016年参加TRECVID 2016,在Instance Search比赛(简称INS)的全部2大评测中,又获得全部2项第一名的好成绩。TRECVID 2016 Instance Search比赛的参赛队包括日本国立情报学研究所(NII)、阿姆斯特丹大学、北京大学、清华大学、北京邮电大学等国内外著名大学、研究所和企业研究院。国家基金委官方网站报道  (external link)国家基金委微信公众号报道  (external link)北大新闻报道 (external link)
  2. 2015年参加TRECVID 2015,在Instance Search比赛(简称INS)的全部2大评测中,又获得全部2项第一名的好成绩。TRECVID 2015 Instance Search比赛的参赛队包括加利福尼亚大学、阿姆斯特丹大学、日本国立情报学研究所(NII)、北京大学、清华大学、北京邮电大学等国内著名大学、研究所和企业研究院。
  3. 2014年参加TRECVID 2014,在Instance Search比赛(简称INS)的交互式搜索任务中获得第一的好成绩。TRECVID 2014 Instance Search比赛的参赛队包括IBM Watson研究中心、阿姆斯特丹大学、日本国立情报学研究所(NII)、北京大学、清华大学、北京邮电大学等国内著名大学、研究所和企业研究院。
  4. 2012年参加TRECVID 2012,在Known-Item Search(简称KIS)比赛和Instance Search(简称INS)比赛的全部4大评测中,又获得全部4项第一名。TRECVID 2012 Known-Item Search比赛和Instance Search比赛的参赛队伍包括斯坦福大学、哥伦比亚大学、IBM Watson研究中心、加州大学圣塔芭芭拉分校、阿姆斯特丹大学、日本国立情报学研究所(NII)、北京大学、清华大学、北京邮电大学、天津大学等国内外著名大学、研究所和企业研究院,最终27个队伍提交了118个参赛结果。北大新闻报道 (external link)
  5. 2009年,本研究室在彭宇新老师的带领下,参加了由美国国家标准技术局NIST组织实施的视频检索领域的权威国际评测TRECVID,在高层特征提取任务和搜索任务的6项评测中,共获得4项第一和2项第二的好成绩。TRECVID2009中参加高层特征提取任务的有42个研究机构,参加搜索任务的有19个研究机构,我们的结果处于卡内基梅隆大学、牛津大学、IBM Watson研究中心等国际著名大学和研究机构之前。北大新闻报道 (external link)

主要论文

2018:
  1. Yuxin Peng, Yunzhen Zhao, and Junchao Zhang, "Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification", 2018.【arXiv】 (external link)
  2. Junjie Zhao and Yuxin Peng, "Cost-sensitive Deep Metric Learning for Fine-Grained Image Classification", 24th International Conference on MultiMedia Modeling (MMM), Bangkok, Thailand, Feb. 5-8, 2018.
  3. Yuxin Yuan and Yuxin Peng, "Recursive Pyramid Network with Joint Attention for Cross-media Retrieval", 24th International Conference on Multimedia Modeling(MMM), Bangkok, Thailand, Feb. 5-8, 2018.
  4. Jian Zhang, Yuxin Peng, and Mingkuan Yuan, "Unsupervised Generative Adversarial Cross-modal Hashing", 32th AAAI Conference on Artificial Intelligence (AAAI), New Orleans, Louisiana, USA, Feb. 2–7, 2018.【pdf】【arXiv】 (external link)
2017:
  1. Jinwei Qi, Xin Huang, and Yuxin Peng, "Cross-media Similarity Metric Learning with Unified Deep Networks", Multimedia Tools and Applications (MTAP), Vol. 76, No. 23, pp. 25109-25127, Dec. 2017.(EI)【pdf】【arXiv】 (external link)
  2. Yuxin Peng, Xiangteng He, and Junjie Zhao, "Object-Part Attention Model for Fine-grained Image Classification", IEEE Transactions on Image Processing (TIP), 2017.(Accepted)【pdf】【arXiv】 (external link)
  3. Yuxin Peng, Xin Huang, Jinwei Qi, Junchao Zhang, Junjie Zhao, Mingkuan Yuan, Yunkan Zhuo, Jingze Chi, and Yuxin Yuan, "PKU_ICST at TRECVID 2017: Instance Search Task", TRECVID, Gaithersburg, MD, USA, Nov. 13-15, 2017.【pdf】
  4. Jian Zhang and Yuxin Peng, "SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017.(EI) (Accepted)【pdf】【arXiv】 (external link)
  5. Yuxin Peng, Jinwei Qi, and Yuxin Yuan, "CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning", 2017.【pdf】【arXiv】 (external link)
  6. Xiangteng He and Yuxin Peng, "Visual-textual Attention Driven Fine-grained Representation Learning", 2017.【arXiv】 (external link)
  7. Yuxin Peng, Jinwei Qi, and Yuxin Yuan, "Modality-specific Cross-modal Similarity Measurement with Recurrent Attention Network", 2017.【pdf】【arXiv】 (external link)
  8. Xin Huang, Yuxin Peng, and Mingkuan Yuan, "MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval", 2017.【arXiv】 (external link)
  9. Yuxin Peng, Jinwei Qi, Xin Huang, and Yuxin Yuan, "CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network", IEEE Transactions on Multimedia (TMM), 2017.(EI)(Accepted)【pdf】【arXiv】 (external link)
  10. Jingze Chi, Xin Huang, and Yuxin Peng, "Zero-Shot Cross-media Retrieval with External Knowledge", 9th International Conference on Internet Multimedia Computing and Service (ICIMCS), Tsingtao, China, Aug. 23-25, 2017.(Accepted)【pdf】
  11. Xin Huang, Zhaoda Ye, and Yuxin Peng, "Attention-sharing Correlation Learning for Cross-media Retrieval", 9th International Conference on Image and Graphics (ICIG), Shanghai, China, Sep. 13-15, 2017.(Accepted)【pdf】
  12. Mingkuan Yuan, Xin Huang, and Yuxin Peng, "Cross-media Residual Correlation Learning", Applied Informatics, Vol. 4, No. 1, pp. 1-9, Oct. 2017.【pdf】
  13. Xiangteng He, Yuxin Peng and Junjie Zhao, "Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN", 25th ACM Multimedia Conference (ACM MM), Mountain View, CA, USA, Oct. 23-27, 2017.(Accepted)【arXiv】 (external link)
  14. Junjie Zhao, Yuxin Peng and Xiangteng He, "Attribute Hierarchy based Multi-task Learning for Fine-grained Image Classification", China National Conference on Multimedia (ChinaMM), Nanjing, Jiangsu, China, Sep. 15-17, 2017.(Accepted)【pdf】
  15. Yuxin Peng, Xin Huang, and Yunzhen Zhao, "An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017.(EI)【pdf】【arXiv】 (external link)
  16. Xin Huang, Yuxin Peng, and Mingkuan Yuan, "Cross-modal Common Representation Learning by Hybrid Transfer Network", 26th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1893-1900, Melbourne, Australia, Aug. 19-25, 2017.(EI)【pdf】【arXiv】 (external link)【source code】 (external link)
  17. Xiangteng He and Yuxin Peng, "Fine-grained Image Classification via Combining Vision and Language", 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5994-6002, Honolulu, Hawaii, USA, Jul. 21-26, 2017.【pdf】【arXiv】 (external link)
  18. Xin Huang and Yuxin Peng, "Cross-modal Deep Metric Learning with Multi-task Regularization", 18th IEEE International Conference on Multimedia and Expo (ICME), pp. 943-948, Hong Kong, Jul. 10-14, 2017.(EI)【pdf】【arXiv】 (external link)
  19. Yunzhen Zhao and Yuxin Peng, "Saliency-guided Video Classification Via Adaptively Weighted Learning", 18th IEEE International Conference on Multimedia and Expo (ICME), pp. 847-852, Hong Kong, Jul. 10-14, 2017.(Oral)(EI)【pdf】【arXiv】 (external link)
  20. Yuxin Peng, Wenwu Zhu, Yao Zhao, Changsheng Xu, Qingming Huang, Hanqing Lu, Qinghua Zheng, Tiejun Huang, and Wen Gao, "Cross-media analysis and reasoning: advances and directions", Frontiers of Information Technology & Electronic Engineering (FITEE), Vol. 18, No. 1, pp. 44-57, Jan. 2017.(SCI,EI)【pdf】
  21. Chao Zhu and Yuxin Peng, "Discriminative Latent Semantic Feature Learning for Pedestrian Detection", Neurocomputing, Vol. 238, pp. 126-138, May. 2017.(SCI, EI)【pdf】
  22. Panpan Tang and Yuxin Peng, "Exploiting Distinctive Topological Constraint of Local Feature Matching for Logo Image Recognition", Neurocomputing, Vol. 236, pp. 113-122, May. 2017.(SCI, EI)【pdf】
  23. Lei Huang and Yuxin Peng, "Cross-media Retrieval by Exploiting Fine-Grained Correlation at Entity Level", Neurocomputing, Vol. 236, pp. 123-133, May. 2017.(SCI, EI)【pdf】
  24. Xiangteng He and Yuxin Peng, "Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-grained Image Classification", 31th AAAI Conference on Artificial Intelligence (AAAI), pp. 4075-4081, San Francisco, California, USA, Feb. 4–9, 2017.(EI)【pdf】
2016:
  1. Yuxin Peng, Xin Huang, and Jinwei Qi, Junjie Zhao, Junchao Zhang, Yunzhen Zhao, Yuxin Yuan, Xiangteng He, and Jian Zhang, "PKU-ICST at TRECVID 2016: Instance Search Task", TRECVID, Gaithersburg, MD, USA, Nov. 14-16, 2016.【pdf】
  2. Jian Zhang and Yuxin Peng, "Query-adaptive Image Retrieval by Deep Weighted Hashing", 2016, arXiv:1612.02541.【pdf】【arXiv】 (external link)
  3. Jinwei Qi, Xin Huang, and Yuxin Peng, "Cross-media Retrieval by Multimodal Representation Fusion with Deep Networks", 13th International Forum of Digital TV and Wireless Multimedia Communication (IFTC), pp. 218-227, Shanghai, China, Nov. 9-10, 2016.(Oral)(EI)【pdf】
  4. Yuxin Peng, Xin Huang, and Jinwei Qi, "Cross-media Shared Representation by Hierarchical Learning with Multiple Deep Networks", 25th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3846-3853 , New York City, New York, USA, Jul. 9-15, 2016.(Oral)(EI)【pdf】【source code】
  5. Yuxin Peng, Xiaohua Zhai, Yunzhen Zhao, and Xin Huang, "Semi-Supervised Cross-Media Feature Learning with Unified Patch Graph Regularization", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 26, No. 3, pp. 583-596 , Mar. 2016.(SCI, EI)【pdf】【source code】
  6. Chao Zhu and Yuxin Peng, "Group Cost-Sensitive Boosting for Multi-Resolution Pedestrian Detection", 30th AAAI Conference on Artificial Intelligence (AAAI), pp. 3676-3682 , Phoenix, Arizona, USA, Feb. 12–17, 2016.(Oral)(EI)【pdf】
  7. Panpan Tang and Yuxin Peng, "Logo Recognition via Improved Topological Constraint", 22nd International Conference on MultiMedia Modeling (MMM), pp. 150-161, Miami, Florida, USA, Jan. 4-6, 2016.(Oral)(EI)【pdf】
  8. Lei Huang and Yuxin Peng, "Cross-Media Retrieval via Semantic Entity Projection", 22nd International Conference on MultiMedia Modeling (MMM), pp. 276-288, Miami, Florida, USA, Jan. 4-6, 2016.(Oral)(EI)【pdf】
2015:
  1. Chao Zhu and Yuxin Peng, "A Boosted Multi-Task Model for Pedestrian Detection with Occlusion Handling", IEEE Transactions on Image Processing (TIP),Vol. 24, No. 12, pp. 5619-5629 , Dec. 2015.(SCI, EI)【pdf】
  2. Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, and Zheng Zhang, "The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification", 28th IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 842-850, Boston, MA, USA, Jun. 7-12, 2015.(EI)【pdf】
  3. Yuxin Peng, "Adaptive Sampling with Optimal Cost for Class-Imbalance Learning", 29th AAAI Conference on Artificial Intelligence (AAAI), pp. 2921-2927, Austin Texas, USA, Jan. 25-29, 2015.(EI)【pdf】
  4. Chao Zhu and Yuxin Peng, "A Boosted Multi-Task Model for Pedestrian Detection with Occlusion Handling", 29th AAAI Conference on Artificial Intelligence (AAAI), pp. 3878-3884, Austin Texas, USA, Jan. 25-29, 2015.(EI)【pdf】
  5. Yuxin Peng, Jian Zhang, Xin Huang, et, al., "PKU-ICST at TRECVID 2015:Instance Search Task", TRECVID, Gaithersburg, MD, USA, Nov. 16-18, 2015.【pdf】
2014:
  1. Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang, Yuxin Peng, and Zheng Zhang, "Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification", 22nd ACM Multimedia Conference (ACM MM), pp. 177-186, Orlando, Florida, USA, Nov. 3-7, 2014. (Full paper)(EI)【pdf】
  2. Wenxuan Xie, Yuxin Peng, and Jianguo Xiao, "Weakly-Supervised Image Parsing via Constructing Semantic Graphs and Hypergraphs", 22nd ACM Multimedia Conference (ACM MM), pp. 277-286, Orlando, Florida, USA, Nov. 3-7, 2014. (Full paper)(EI)【pdf】
  3. Wenxuan Xie, Zhiwu Lu, Yuxin Peng, and Jianguo Xiao, "Graph-based Multimodal Semi-supervised Image Classification", Neurocomputing, Vol. 138, pp. 167-179, Aug. 2014. (SCI, EI, IF_2014=2.005)【pdf】
  4. Wenxuan Xie, Yuxin Peng, and Jianguo Xiao, "Cross-View Feature Learning for Scalable Social Image Analysis", 28th AAAI Conference on Artificial Intelligence (AAAI), pp. 201-207, Quebec City, Quebec, Canada, Jul. 27-31, 2014. (EI)【pdf】
  5. Wenxuan Xie, Yuxin Peng, and Jianguo Xiao, "Semantic Graph Construction for Weakly-Supervised Image Parsing", 28th AAAI Conference on Artificial Intelligence (AAAI), pp. 2853-2859, Quebec City, Quebec, Canada, Jul. 27-31, 2014. (EI)【pdf】
  6. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "Learning Cross-Media Joint Representation with Sparse and Semisupervised Regularization", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 24, No. 6, pp. 965-978 , Jun. 2014. (SCI, EI, IF_2014=2.259)【pdf】【source code】
  7. Yuxin Peng, Jian Zhang, Panpan Tang, et, al., "PKU-ICST at TRECVID 2014:Instance Search Task", TRECVID, Orlando, Florida, USA, Nov. 10-12, 2014.【pdf】
2013:
  1. Ding Ma, Xiaohua Zhai, and Yuxin Peng, "Cross-Media Retrieval by Cluster-based Correlation Analysis", 20th International Conference on Image Processing (ICIP), pp. 3986-3990, Melbourne, Australia, Sep. 15-18, 2013. (EI, ISTP)【pdf】
  2. Wenxuan Xie, Zhiwu Lu, Yuxin Peng, and Jianguo Xiao, "Multimodal Semi-supervised Image Classification by Combining Tag Refinement, Graph-based Learning and Support Vector Regression", 20th International Conference on Image Processing (ICIP), pp. 4307-4311, Melbourne, Australia, Sep. 15-18, 2013. (EI, ISTP)【pdf】
  3. Zhiwu Lu and Yuxin Peng, "Learning Descriptive Visual Representation by Semantic Regularized Matrix Factorization", 23rd International Joint Conferences on Artificial Intelligence (IJCAI), pp. 1523-1529, Beijing, China, Aug. 3–9, 2013. (EI)【pdf】
  4. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "Heterogeneous Metric Learning with Joint Graph Regularization for Cross-Media Retrieval”, 27th AAAI Conference on Artificial Intelligence (AAAI), pp. 1198-1204, Bellevue, Washington, USA, Jul. 14-18, 2013. (EI) 【pdf】【source code】
  5. Zhiwu Lu, and Yuxin Peng, “Unified Constraint Propagation on Multi-View Data", 27th AAAI Conference on Artificial Intelligence (AAAI), pp. 640-646, Bellevue, Washington, USA, Jul. 14-18, 2013. (EI)【pdf】
  6. Guangyao Zhou, Zhiwu Lu, and Yuxin Peng, "L1-Graph Construction Using Structured Sparsity",Neurocomputing, Vol. 120, pp. 441-452, Nov. 2013. (SCI, EI, IF_2013=2.005)【pdf】
  7. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Exploiting Semantic and Visual Context for Effective Video Annotation", IEEE Transactions on Multimedia (TMM), Vol. 15, No. 6, pp. 1400-1414, Oct. 2013. (SCI, EI, IF_2013=1.776)【pdf】
  8. Zhiwu Lu, and Yuxin Peng, “Exhaustive and Efficient Constraint Propagation: A Graph-Based Learning Approach and Its Applications”, International Journal of Computer Vision (IJCV), Vol. 103, No. 3, pp. 306-325 , Jul. 2013. (SCI, EI, IF_2013= 3.533)【pdf】
  9. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "Cross-Media Retrieval by Intra-Media and Inter-Media Correlation Mining", Multimedia Systems(MMSJ), Vol. 19, No. 5, pp. 395-406, Oct. 2013. (SCI, EI, IF_2013=0.443)【pdf】
  10. Jian Yi, Yuxin Peng, and Jianguo Xiao, "A Temporal Context Model for Boosting Video Annotation", Science China, Vol. 56, Issue 11, pp. 1-14, No. 2013. (SCI, EI, IF_2013=0.702)【pdf】
  11. Zhiwu Lu, and Yuxin Peng, "Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition", Pattern Recognition (PR), Vol. 46, No. 7, pp. 1799-1809, Jul. 2013. (SCI, EI, IF_2013= 2.584)【pdf】
  12. Zhiguo Yang, Yuxin Peng, and Jianguo Xiao, "Vocabulary hierarchy optimisation based on spatial context and category information", International Journal of Multimedia Intelligence and Security (IJMIS), Vol. 3, No. 1, pp. 93-107, Sep. 2013.【pdf】
  13. Yuxin Peng, Xiaohua Zhai, Jian Zhang, et, al., "PKU-ICST at TRECVID 2013:Instance Search Task",TRECVID), Gaithersburg, MD, USA, Nov. 20-22, 2013.【pdf】
2012:
  1. Zhiwu Lu, and Yuxin Peng, "Heterogeneous Constraint Propagation with Constrained Sparse Representation", 12th IEEE International Conference on Data Mining (ICDM), pp. 1002-1007, Brussels, Belgium, Dec. 10 - 13, 2012. (EI, ISTP)【pdf】
  2. Zhiwu Lu, and Yuxin Peng, "Image Annotation by Semantic Sparse Recoding of Visual Content", 20th ACM Multimedia Conference (ACM MM), pp. 499-508, Nara, Japan, Oct. 29 - Nov. 2, 2012. (Full paper)(EI)【pdf】
  3. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "PDSS: Patch-Descriptor-Similarity Space for Effective Face Verification", 20th ACM Multimedia Conference (ACM MM), pp. 961-964, Nara, Japan, Oct. 29 - Nov. 2, 2012. (EI) 【pdf】
  4. Li Ling, Xiaohua Zhai, and Yuxin Peng, "Tri-space and Ranking Based Heterogeneous Similarity Measure for Cross-Media Retrieval", 21st International Conference on Pattern Recognition (ICPR), pp. 230-233, Tsukuba, Japan, Nov. 11-15, 2012. (EI, ISTP)【pdf】
  5. Yuxin Peng, Xiaohua Zhai, Jian Zhang, et, al., "PKU-ICST at TRECVID 2012: Instance Search Task", TRECVID, Maryland, USA, Nov. 26-28, 2012. (EI)【pdf】
  6. Yuxin Peng, Yunbo Peng, Xiaohua Zhai, et, al., "PKU-ICST at TRECVID 2012: Known-item Search Task", TRECVID, Maryland, USA, Nov. 26-28, 2012. (EI)【pdf】
  7. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "Cross-Modality Correlation Propagation for Cross-Media Retrieval", 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2337-2340, Kyoto, Japan, Mar. 25-30, 2012. (EI, ISTP)【pdf】【source code】
  8. Zhiguo Yang, Yuxin Peng, and Jianguo Xiao, "Visual Vocabulary Optimization with Spatial Context for Image Annotation and Classification", 18th International Conference on MultiMedia Modeling (MMM), pp. 89-102, Klagenfurt, Austria, Jan. 4-6, 2012. (EI, ISTP)【pdf】
  9. Xiaohua Zhai, Yuxin Peng, and Jianguo Xiao, "Effective Heterogeneous Similarity Measure with Nearest Neighbors for Cross-Media Retrieval", 18th International Conference on MultiMedia Modeling (MMM), pp. 312-322, Klagenfurt, Austria, Jan. 4-6, 2012. (EI, ISTP)【pdf】【source code】
2011:
  1. Zhiwu Lu, Horace H.S. Ip, and Yuxin Peng, "Contextual Kernel and Spectral Methods for Learning the Semantics of Images", IEEE Transactions on Image Processing (TIP), Vol. 20, No. 6, pp. 1739-1750, Jun. 2011. (SCI, EI, IF_2011=3.042)【pdf】
  2. Yuxin Peng, Zhiguo Yang and Jian Yi, "Web Video Search by Mutual Boosting between the Inside and Outside Text of Video", 11th annual international ACM/IEEE Joint Conference on Digital Libraries (JCDL), pp. 391-392, Ottawa, Canada, Jun. 2011. (EI)【pdf】
  3. Zhiwu Lu, and Yuxin Peng, "Latent Semantic Learning by Efficient Sparse Coding with Hypergraph Regularization", 25th AAAI Conference on Artificial Intelligence (AAAI), pp. 411-416, San Francisco, California, USA, Aug. 2011. (EI)【pdf】
  4. Zhenyong Fu, Zhiwu Lu, Horace H.S. Ip, Yuxin Peng, and Hongtao Lu, "Symmetric Graph Regularized Constraint Propagation", 25th AAAI Conference on Artificial Intelligence (AAAI), pp. 350-355, San Francisco, California, USA, Aug. 2011. (EI)【pdf】
  5. Zhiwu Lu, Yuxin Peng, and Horace H.S. Ip, "Spectral Learning of Latent Semantics for Action Recognition", 13th International Conference of Computer Vision (ICCV), pp. 1503-1510, Barcelona, Spain, Nov. 2011. (EI, ISTP)【pdf】
  6. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Mining Concept Relationship in Temporal Context for Effective Video Annotation", 19th ACM Multimedia Conference (ACM MM), pp. 1053-1056, Scottsdale, Arizona, USA, Nov. 2011. (EI)【pdf】
  7. Zhiwu Lu, and Yuxin Peng, "Combining Latent Semantic Learning and Reduced Hypergraph Learning for Semi-Supervised Image Categorization", 19th ACM Multimedia Conference (ACM MM), pp. 1409-1412, Arizona, USA, Nov. 2011. (EI)【pdf】
  8. Zhiwu Lu, Yuxin Peng, and Horace H.S. Ip, "Combining Multiple Clusterings Using Fast Simulated Annealing", Pattern Recognition Letters (PRL), Vol. 32, Issue 15, pp. 1956-1961, Nov. 2011. (SCI, EI, IF_2011=1.034)【pdf】
  9. 易剑, 彭宇新, 肖建国, "一种基于颜色聚类和多帧融合的视频文字识别方法", 软件学报, 2011年, 第22卷第12期, 2919~2933页. (EI)【pdf】
2010:
  1. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Refining Video Annotation by Exploiting Inter-Shot Context", 18th ACM Multimedia Conference (ACM MM), pp. 1103-1106, Firenze, Italy, 25-29, Oct. 2010. (EI)【pdf】
  2. Hao Li, and Yuxin Peng, "Effective Multi-level Image Representation for Image Categorization", 20th International Conference on Pattern Recognition (ICPR), pp. 1048-1051, Istanbul, Turkey, Aug. 23-26, 2010. (EI)【pdf】
  3. Yuxin Peng, and Jia Yao, "AdaOUBoost: Adaptive Over-sampling and Under-sampling to Boost the Concept Learning in Large Scale Imbalanced Data Sets", 11th ACM SIGMM International Conference on Multimedia Information Retrieval (MIR), pp. 111-118, Philadelphia, Pennsylvania, USA, Mar. 29-31, 2010. (EI)【pdf】
  4. Yuxin Peng, and Jianguo Xiao, "Story-based Retrieval by Learning and Measuring the Concept-based and Content-based Similarity", 16th International MultiMedia Modeling Conference (MMM), pp. 370-378, Chongqing, China, Jan. 6-8, 2010. (EI, ISTP)【pdf】
  5. Zhiwu Lu, Yuxin Peng, and Horace H.S. Ip, "Gaussian Mixture Learning via Robust Competitive Agglomeration", Pattern Recognition Letters (PRL), Vol. 31, Issue 7, pp. 539-547, 2010. (SCI, EI, IF_2010=1.213)【pdf】
  6. Zhiwu Lu, Yuxin Peng, and Horace H.S. Ip, "Image Categorization via Robust PLSA", Pattern Recognition Letters (PRL), Vol. 31, Issue 1, pp. 36-43, Jan., 2010. (SCI, EI, IF_2010=1.213)【pdf】
2009:
  1. Yuxin Peng, Zhiguo Yang, Lei Cao, et, al., "PKU-ICST at TRECVID 2009: High Level Feature Extraction and Search", TRECVID, Maryland USA, Nov. 16-17, 2009. (EI)
  2. Yuxin Peng, Zhiwu Lu, and Jianguo Xiao, "Semantic Concept Annotation Based on Audio PLSA Model", 17th ACM Multimedia Conference (ACM MM), pp. 841-844, Beijing, China, Oct. 19-24, 2009. (EI)
  3. Yuxin Peng, Zhiguo Yang, and Jianguo Xiao, "Audio Retrieval by Segment-based Manifold-ranking", 10th IEEE International Conference on Multimedia and Expo (ICME), pp. 686-689, Cancun, Mexico, Jun. 28 - Jul. 3, 2009. (EI, ISTP)
  4. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Using Multiple Frame Integration for the Text Recognition of Video", 10th International Conference on Document Analysis and Recognition (ICDAR), pp. 71-75, Barcelona, Spain, Jul. 26-29, 2009. (EI)
2008:
  1. Yuxin Peng, Zhiguo Yang, Jian Yi, Lei Cao, Hao Li, and Jia Yao, "Peking University at TRECVID 2008: High Level Feature Extraction", TRECVID, Maryland USA, Nov. 17-18, 2008. (EI)
  2. Zhiwu Lu, Yuxin Peng, and Jianguo Xiao, "From Comparing Clusterings to Combining Clusterings", 22nd AAAI Conference on Artificial Intelligence (AAAI), pp. 665-670, Chicago, Illinois, USA, Jul. 13–17, 2008. (EI)
  3. Zhiwu Lu, Yuxin Peng, and Jianguo Xiao, "Unsupervised Learning of Finite Mixtures Using Entropy Regularization and Its Application to Image Segmentation", 21th IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 641-648, Alaska, USA, Jun. 23-28, 2008. (EI, ISTP)
  4. Zhiwu Lu, and Yuxin Peng, "A Semi-supervised Learning Algorithm on Gaussian Mixture with Automatic Model Selection", Neural Processing Letters (NPL), Vol. 27, No. 1, pp. 57-66, 2008. (SCI, EI, IF_2010=1.088)
2007:
  1. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Color-based Clustering for Text Detection and Extraction in Image", 15th ACM Multimedia Conference (ACM MM), pp. 847-850, Augsburg, Germany, Sep. 24-29, 2007. (EI)
  2. Jian Yi, Yuxin Peng, and Jianguo Xiao, "Color-based Text Extraction for the Image", 8th Pacific-Rim Conference on Multimedia (PCM), pp. 393-396, HongKong, China, Dec. 11-14, 2007. (EI, ISTP)
  3. Yuxin Peng, Chong-Wah Ngo, and Jianguo Xiao, "OM-based Video Shot Retrieval by One-to-One Matching", Multimedia Tools and Applications (MTAP), Vol. 34, No. 2, pp. 249-266, Aug. 2007. (SCI, EI, ISTP)
2006:
  1. Yuxin Peng, and Chong-Wah Ngo, "Clip-Based Similarity Measure for Query-Dependent Clip Retrieval and Video Summarization", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 16, No. 5, pp. 612-627, May. 2006. (SCI, EI, IF_2008=2.951)
  2. Yuxin Peng, Chong-Wah Ngo, Cuihua Fang, Xiaoou Chen, and Jianguo Xiao, "Audio Similarity Measure by Graph Modeling and Matching", 14th ACM Multimedia Conference (ACM MM), pp. 603-606, Santa Barbara, CA USA, Oct. 23-27, 2006. (EI)
  3. Yuxin Peng, Cuihua Fang, and Xiaoou Chen, "Using Earth Mover's Distance for Audio Clip Retrieval", 7th Pacific-Rim Conference on Multimedia (PCM), pp. 405-413, Hangzhou, China, Nov. 2-4, 2006. (EI, ISTP)
2005:
  1. Yuxin Peng, and Chong-Wah Ngo, "EMD-Based Video Clip Retrieval by Many-to-Many Matching", 4th ACM International Conference on Image and Video Retrieval (CIVR), pp. 71-81, Singapore, Jul. 20-22, 2005. (SCI, EI, ISTP)
  2. Yuxin Peng, and Chong-Wah Ngo, "Hot Event Detection and Summarization by Graph Modeling and Matching", 4th ACM International Conference on Image and Video Retrieval (CIVR), pp.257-266, Singapore, Jul. 20-22, 2005. (SCI, EI, ISTP)
  3. Yuxin Peng, and Chong-Wah Ngo, "Shot-based Retrieval by Integrating Color and Motion Features", 8th International Joint Conference on Information Sciences (JCIS), pp. 827-830, Salt Lake City, USA, Jul. 21-26, 2005. (ISTP)
  4. Xiaojun Wan, and Yuxin Peng, "A New Retrieval Model Based on TextTiling for Document Similarity Search", Journal of Computer Science and Technology (JCST), Vol. 20, No. 4, pp. 552-558, Jul. 2005. (SCI, EI)
  5. Xiaojun Wan, and Yuxin Peng, "The Earth Mover's Distance as a Semantic Measure for Document Similarity", ACM 14th Conference on Information and Knowledge Management (CIKM), pp. 301-302, Bremen, Germany, Oct. 31 – Nov. 5, 2005. (EI)
  6. Xiaojun Wan, and Yuxin Peng, "A New Re-Ranking Method for Generic Chinese Text Summarization and its Evaluation", 8th International Conference on Asian Digital Libraries (ICADL), pp. 171-175, Bangkok, Thailand, Dec. 12-15, 2005. (SCI, EI, ISTP)
2004:
  1. Yuxin Peng, and Chong-Wah Ngo. "Clip-based Similarity Measure for Hierarchical Video Retrieval", 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR), pp. 53-60, New York, USA, Oct. 15-16, 2004. (EI)
  2. 彭宇新, Ngo Chong-Wah, 肖建国, "一种基于二分图最优匹配的镜头检索方法", 电子学报, 2004年7月, 第32卷第7期, 1135~1139页. (EI)
  3. Xiaojun Wan, and Yuxin Peng, "A Measure Based on Optimal Matching in Graph Theory for Document Similarity", 1st Asia Information Retrieval Symposium (AIRS), pp. 227-238, Beijing, China, Oct. 18-20, 2004. (SCI, EI, ISTP)
  4. 董庆杰, 彭宇新, 郭宗明, 肖建国, "一种新的基于模糊聚类的镜头检索方法", 计算机工程与应用, 2004年1月, 第40卷第1期, 56-57页.
2003:
  1. Yuxin Peng, Chong-Wah Ngo, Qing-Jie Dong, Zongming Guo, and Jianguo Xiao, "Video Clip Retrieval by Maximal Matching and Optimal Matching in Graph Theory", 4th IEEE International Conference on Multimedia and Expo (ICME), pp. 317-320, Maryland, USA, Jul. 6-9, 2003. (EI, ISTP)
  2. 彭宇新, Ngo Chong-Wah, 董庆杰, 郭宗明, 肖建国, "一种通过视频片段进行视频检索的方法", 软件学报, 2003年8月, 第14卷第8期, 1409~1417页. (EI)

教学活动

主讲课程
  • 课程名称:数字图像处理
  • 教学对象:北京大学信息科学技术学院研究生
  • 时 间:2005年春季-至今
实习学生/保研学生/访问学生计划( 此信息长期有效):详情>>

联系方式

  • 电话:010-82529699
  • 传真:010-62754532
  • 邮件:pengyuxin(AT)pku.edu.cn