social curation; contexts; graph clustering; classification
Abstract :
[en] This paper proposes a novel method of discovering a set of image contents sharing a specific context (attributes or implicit meaning) with the help of image collections obtained from social curation platforms. Socially curated contents are promising to analyze various kinds of multimedia information, since they are manually filtered and organized based on specific individual preferences, interests or perspectives. Our proposed method fully exploits the process of social curation: (1) How image contents are manually grouped together by users, and (2) how image contents are distributed in the platform. Our method reveals the fact that image contents with a specific context are naturally grouped together and every image content includes really various contexts that cannot necessarily be verbalized by texts.
Disciplines :
Computer science
Author, co-author :
Kimura, Akisato; NTT Corporation > Communication Science Laboratories > Learning and Intelligent Systems Research Group
Ishiguro, Katsuhiko; NTT Corporation > Communication Science Laboratories > Learning and Intelligent Systems Research Group
Marcos Alvarez, Alejandro ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Kataoka, Kaori; NTT Corporation > Media Intelligence Laboratories
Murasaki, Kazuhiko; NTT Corporation > Media Intelligence Laboratories
Yamada, Makoto; NTT Corporation > Communication Science Laboratories > Learning and Intelligent Systems Research Group
Language :
English
Title :
Image Context Discovery from Socially Curated Contents
Publication date :
October 2013
Event name :
The 21st ACM International Conference on Multimedia (ACMMM2013)
Event organizer :
ACM
Event place :
Barcelona, Spain
Event date :
from 21-10-2013 to 25-10-2013
Audience :
International
Main work title :
Proceedings of the 21st ACM International Conference on Multimedia
