Institute of Theoretical Physics

Key Laboratory of Theoretical Physics

  Chinese Academy of Sciences

 Seminar

Title

题目

Recommendations based on deep learning: From Movie To Video

Speaker

报告人

Dong Liu, Ph.D., Associate Professor

Dong Liu received the B.S. and Ph.D. degrees, both in electrical engineering, from the University of Science and Technology of China (USTC), in 2004 and 2009, respectively. He joined the Department of Electronic Engineering and Information Science (EEIS) of USTC, as an Associate Professor in 2012. He was a Member of Research Staff at Nokia Research Center, Beijing, from 2009 to 2012. Previously, he had been a Research Intern at Microsoft Research Asia, from 2005 to 2008. Dong Liu received the 2009 IEEE CSVT Transactions Best Paper Award for the co-authored paper entitled “Image compression with edge-based inpainting.” He has authored or co-authored more than 20 papers in leading journals and conferences, which were cited more than 300 times (till March 2016) according to Google Scholar. He has been co-inventors of more than 10 patent applications, 3 of which are granted. His research interests include image and video compression and multimedia data mining.

Affiliation

所在单位

University of Science and Technology of China

Date

日期

10:30-11:30 July, 08 (Fri.),2016

Venue

地点

ITP New Building 6620

Abstract

摘要

Recent years have witnessed the information overload that calls for more efficient information filtering mechanisms for normal users. Recommendation system is an important approach to information filtering and has been developed for more than two decades. The items that can be recommended range from more structured data, like book, music, and movie, to more unstructured data, like image and video. This talk first gives a brief introduction to recommendation systems, then reviews well-known work on movie recommendation, and then presents our recent work on image recommendation based on deep learning. How to address video recommendation is still very challenging and under investigation.

Contact person

所内合作者

Pan Zhang