[image 00435] 講演会のお知らせ: Prof. Winston Hsu, National Taiwan University

[Shin'ichi Satoh]

image-mlの皆様、

国立情報学研究所の佐藤真一です。National Taiwan UniversityのWinston
Hsu博士による以下の講演会のお知らせをお送りいたします。参加無料、参加
登録も不要です。どうぞご参加下さい。

-- Shin'ichi


日時: 1月20日(月) 15:00-16:00
場所: 国立情報学研究所 12階 会議室1208
http://www.nii.ac.jp/access/

Title:
Mobile Visual Recognition for Thousand-Scale Concepts -- Opportunities and Challenges

Speaker:
Prof. Winston H. Hsu, 
Graduate Institute of Networking and Multimedia &
Department of Computer Science and Information Engineering
National Taiwan University

http://www.csie.ntu.edu.tw/~winston


Abstract:

The rapid development of technologies in both hardware and software have made content-based multimedia services feasible on mobile devices such as smartphones and tablets; and the strong needs for mobile visual search and recognition have been emerging. So does the emergence for Internet of Things -- potentially visual signals will communicate intensively between the embedded devices and the servers. While many real applications require a large-scale recognition system, the same technologies that support server-based scalable visual recognition may not be feasible on mobile (or embedded) devices due to the resource constraints. Although the client-server framework ensures the scalability, the real-time response subjects to the limitation on network bandwidth. Therefore, the main challenge for mobile visual recognition system should be the recognition bitrate, which is the amount of data transmission under the same recognition performance. For this talk, we will review first how the thousand-scale recognition systems have been developing. We then introduce two strategies we having been working on for mobile visual recognition -- (1) label space compression for human attribute detection and (2) the brand-new paradigm in “compression for recognition.” For the latter, we exploit and compare various strategies such as compact features, feature compression, feature signatures by hashing, image scaling, etc., to enable low bitrate mobile visual recognition. We will demonstrate the exciting findings in the evaluations on the large-scale image dataset and highlight certain opportunities for further investigations. 

Short Bio:

Dr. Winston Hsu is an active researcher dedicated to novel algorithms and systems for ultra-large-scale image/video retrieval, social media mining/recommendation, multimedia analytics, and mobile and cloud-based multimedia applications. He is keen to realizing advanced researches towards business deliverables via academia-industry collaborations. He is an Associate Professor in the Department of Computer Science and Information Engineering, National Taiwan University. He received his Ph.D. degree (2007) from Columbia University, New York. Before that, he worked for years as a founding engineer in the multimedia software company, CyberLink Corp., where experiencing Engineer, Project Leader, and R&D Manager.
 
He has been recognized with technical awards and best paper awards in multimedia research community (e.g., ACM Multimedia 2006 Best Paper Runner-Up, First Prize in ACM Multimedia Grand Challenge 2011, First Prize in MSR-Bing Image Retrieval Challenge 2013, ACM Multimedia 2013 Grand Challenge Multimodal Award, etc.). He delivered keynote speeches and lectured several highly rated and very attended tutorials in top conferences (e.g., ACM Multimedia 2008/2009, SIGIR 2008, and ICASSP 2009/2011). He is on the Editorial Board for IEEE Multimedia Magazine and IEEE MSA TC.  He is in the organizing committee for ACM Multimedia (2010/2012/2013), ICME 2009, PCM 2013/2014, MMM 2013, ICMR 2015. He is in the technical committee for major conferences (ACM Multimedia 2009-2013, SIGIR 2011/2013, WWW 2011, CIKM 2011, ICME 2006-2014). He is recently awarded 2011 Ta-You Wu Memorial Award, a national and prestigious recognition for young researchers, and 2013 National Outstanding IT Elite Award.