Integrating rich information for video recommendation with multi-task rank aggregation

  • Xiaojian Zhao*
  • , Guangda Li
  • , Meng Wang
  • , Jin Yuan
  • , Zheng Jun Zha
  • , Zhoujun Li
  • , Tat Seng Chua
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Video recommendation is an important approach for helping people to access interesting videos. In this paper, we propose a scheme to integrate rich information for video recommendation. We regard video recommendation as a ranking problem and generate multiple ranking lists by exploring different information sources. A multitask rank aggregation approach is proposed to integrate the ranking lists for different users in a joint manner. Our scheme is flexible and can easily incorporate other methods by adding their generated ranking lists into our multi-task learning algorithm. We conduct experiments with 76 users and more than 10, 000 videos. The results demonstrate the feasibility and effectiveness of our approach.

Original languageEnglish
Title of host publicationMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops
Pages1521-1524
Number of pages4
DOIs
StatePublished - 2011
Event19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11 - Scottsdale, AZ, United States
Duration: 28 Nov 20111 Dec 2011

Publication series

NameMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops

Conference

Conference19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11
Country/TerritoryUnited States
CityScottsdale, AZ
Period28/11/111/12/11

Keywords

  • Multi-task rank aggregation
  • Video recommendation

Fingerprint

Dive into the research topics of 'Integrating rich information for video recommendation with multi-task rank aggregation'. Together they form a unique fingerprint.

Cite this