Ecole d'ingénieur et centre de recherche en télécommunications

Gathering training sample automatically for social event visual modeling

Liu, Xueliang; Huet, Benoit

SAM 2012, ACM International Workshop on Socially Aware Multimedia, In conjunction with ACM Multimedia 2012, 29 October 2012, Nara, Japan

In recent years, the emergence of social media on the Internet has derived many of interesting research and applications. In this paper, a novel framework is proposed to model the visual appearance of social events using automatically collected training samples on the basis of photo context analysis. While collecting positive samples can be achieved easily thanks to explicitly identifying tags, finding representative negative samples from the vast amount of irrelevant multimedia documents is a more challenging task. Here, we argue and demonstrate that the most common negative sample, originating from the same location as the event to be modeled, are best suited for the task. A novel ranking approach is devised to select a set of negative samples. The visual event models are learned from automatically collected samples using SVM. The results reported here show that the event models are effctive to filter out irrelevant photos and perform with a high accuracy on various social events categories.

Document Doi Bibtex

Mots Clés:Events, social media, multimedia semantics
Type:Conférence
Langue:English
Ville:Nara
Pays:JAPON
Date:
Département:Communications Multimédia
Eurecom ref:3780
Copyright: © ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in SAM 2012, ACM International Workshop on Socially Aware Multimedia, In conjunction with ACM Multimedia 2012, 29 October 2012, Nara, Japan http://dx.doi.org/10.1145/2390876.2390881
Bibtex: @inproceedings{EURECOM+3780, doi = {http://dx.doi.org/10.1145/2390876.2390881}, year = {2012}, title = {{G}athering training sample automatically for social event visual modeling}, author = {{L}iu, {X}ueliang and {H}uet, {B}enoit}, booktitle = {{SAM} 2012, {ACM} {I}nternational {W}orkshop on {S}ocially {A}ware {M}ultimedia, {I}n conjunction with {ACM} {M}ultimedia 2012, 29 {O}ctober 2012, {N}ara, {J}apan}, address = {{N}ara, {JAPON}}, month = {10}, url = {http://www.eurecom.fr/publication/3780} }
Voir aussi: