讲座题目：用于内容识别的哈希：从媒体同步到图像检索

讲座人：韩军功 教授

讲座时间：10:10-11:40

讲座日期：2016-09-13

地点：长安校区文津楼三段5层522学术研讨室

主办单位：8188www威尼斯 智能视觉计算团队

讲座内容简介：

在过去的几年里， 基于哈希码的最近邻搜索因为其高效的性能获得了学术界的广泛关注，其核心算法已经在很多场景中进行了应用。在这个讲座中，我将用两个自己参加的实例来讲述如何在不同应用背景的情况下使用哈希码，来进行内容识别。第一个实例是展示在工业界如何通过识别语音哈希码来同步不同的媒体设备，比如同步电视和移动终端设备；另外一个实例展示了我们如何从理论的角度来改进著名的ITQ方法，并且证明整个算法的普适性和收敛性。通过讲座，希望大家能够对工业界做研究和学术界做研究的不同有一定认识。

讲座人简介

韩军功博士于2004年9月获得西安电子科技大学通信与信息处理专业博士学位， 博士期间在微软亚洲研究院网络多媒体组任研究助理一年。现任英国Northumbria大学计算机系终身教职。在加入Northumbria大学之前韩博士曾任荷兰飞利浦内容识别研究院(Civolution)高级科学家（2012-2015），作为公司视/音频指纹识别方向的首席科学家领导这一方向的产品开发工作，作为第一人开发的基于音频指纹识别的产品SyncNow获得一项工业大奖，算法专利已经通过国际专利查新审核。2010年-2012年， 韩博士就职于荷兰皇家科学院数学和计算机研究所，作为项目联合负责人参与欧盟第七框架研究项目一项。2005年-2010年，韩博士任职于荷兰埃因霍温工业大学，参与多项欧盟项目的研究工作，并指导博士、硕士将近10人。

韩军功在多模态数据分析、多媒体内容识别，计算机视觉、视频压缩以及多媒体数据安全等方向发表文章90余篇；其中一篇1作文章google scholar 引用率超过450次。他兼任Elsevier Neurocomputing (SCI IF 2.1) 杂志和Springer Multimedia Tools and Applications (SCI IF 1.4) 杂志的副主编以及3个国际著名杂志（IEEE Trans Neural Network and Learning System, IEEE Trans Cybernetics 等）的特约客座编委；同时他还是IEEE Industry DSP Technology的常务委员会委员，IEEE Multimedia Communications的技术委员会委员。

Hashing for Content Identification: from Synchronization to Retrieval

Date of event：2016-9-13

Time of event: 10:10-11:40

Title of Lecture： Hashing for Content Identification: from Synchronization to Retrieval

Lecturer：Prof. Jungong Han

Venue: 522 room of School of Computer Science, Wenjin Building

Hosted by: School of Computer Science

About the Lecture：

In the past few years, nearest neighbor search methods based on hashing have gained considerable attention for effective and efficient large-scale similarity search, facilitating a variety of applications. In this talk, we will elaborate two recent works, which are audio hashing for multi-screen synchronization and robust iterative quantization for image search. The former extracts hash code from the audio signal and exploits it as a signature for content identification while the latter generalizes a widely-used ITQ algorithm by extending it from L_2 norm to L_pq norm. The intention is to showcase the difference of carrying out research activities in industry and academia.

Profile of the Lecturer：

Jungong Han is currently a Senior Lecturer with the Department of Computer Science and Digital Technologies at Northumbria University, Newcastle, UK. He received his Ph.D. degree in Telecommunication and Information System from Xidian University, China, in 2004. During his Ph.D study, he spent one year at Internet Media group of Microsoft Research Asia, China. Previously, he was a Senior Scientist (2012-2015) with Civolution Technology (a combining synergy of Philips Content Identification and Thomson STS), a Research Staff (2010-2012) with the Centre for Mathematics and Computer Science (CWI), and a Senior Researcher (2005-2010) with the Technical University of Eindhoven (TU/e) in Netherlands.

Dr. Han’s research interests include Computer Vision, Multimedia Content Identification, Multi-Sensor Data Fusion and Multimedia Security. He has written and co-authored over 90 papers including 3 invited papers in these areas. His first-author paper published in 2013 has to date been cited for more than 450 times, which is recognized as one of the pioneering works in the field of depth based computer vision. Apart from publishing scientific articles, Dr. Han also dedicates to transferring the academic achievements to the commercial products. During his employment with TU/e, his software (C implementation of the proposed algorithm) has been commercialized and utilized by a start-up company. During the period of working in Civolution, his Audio Fingerprinting algorithm was implemented in SyncNow product, which won several industrial awards.

He is an Associate Editor of Elsevier Neurocomputing and an Editorial Board Member of Springer Multimedia Tools and Applications. He served as TPC member, Session Chair, and the reviewer for various conferences and journals. He has been (lead) Guest Editor for five international journals, such as IEEE-T-SMCB, IEEE-T-NNLS, Pattern recognition letters and Neurocomputing. Since 2009, he is a voting member of IEEE Multimedia Communications Technical Committee (MMTC). Since 2012, he has been a member of IEEE Industry DSP Technology Standing Committee. Dr. Han was the recipient of the UK Royal Society Newton Mobile Award in 2016.