博士论坛

博士论坛第八十八期学术报告信息

作者:admin 日期:2015-09-17 20:15:00 浏览:

时间: 2015年9月21日上午10:00

地点: 武汉大学本科生院楼(原出版社大楼)南613会议室

报告人:Dr   Xian-Sheng Hua

报告人国籍: 中国

报告人简介: 2015年加入阿里巴巴搜索事业部,任研究员/资深总监,负责大数据多媒体内容分析及搜索算法团队。在此之前先后在微软中国研究院、微软总部Bing搜索引擎以及微软美国研究院任主管研究员、首席研发主管以及资深研究员。北京大学博士毕业,一直从事图像、视频内容分析和搜索方面的研究和开发工作。在国际会议和期刊上发表论文250余篇,拥有50余项授权专利,H Index为50。2008年因视频搜索方面的突出贡献获麻省理工学院《技术评论》 TR35“全球35个35岁以下青年创新者”称号,2012年任多媒体领域顶级国际会议 ACM   Multimeida 程序委员会主席,2012和2013年连续两年任IEEE多媒体会议ICME程序委员会主席,还是多个多媒体、AI及搜索领域国际会议的领域主席(包括KDD,SIGIR,IJCAI,MM,ICME等),曾任或现任IEEE   Trans. On Multimedia及ACM Trans. On Intelligent Systems and Technology杂志副编,曾获包括ACM  Multimedia和IEEE Trans. On CSVT等在内的多项最佳论文奖。

 

报告摘要: Visual   search has been studied for decades since 1990s and it was called “content-based   image retrieval” in the   beginning. It almost died in the early 21st century and then becomes very hot   in recent years mainly due to the rapid development of distributed computing,   high-dimensional indexing, deep learning and big data analytical techniques.   Many visual search research prototypes and preliminary products are available   to the public. However, is real-world visual search really coming? Have we   solved all the big technical and non-technical challenges? Are semantic gaps   and intention gaps still there, and do they really matter? How big data   analyses and deep learning techniques can help here? Are people really using   it and why do they want to use it? Which direction that visual search is   going towards? What are still missing? In this talk, we will discuss all   these questions based on a real-world visual search engine that has a   considerable number of users. And we will also introduce the upcoming   “Alibaba Large-Scale Image Search Challenge”, in which we will award more   than 400K RMB in total to winning teams.

 

                                                                                                                  邀请人: 胡瑞敏 教授