DocumentCode :
2984099
Title :
Towards Automatic Image Understanding and Mining via Social Curation
Author :
Ishiguro, Katsuhiko ; Kimura, Akihiro ; Takeuchi, Ken
Author_Institution :
NTT Commun. Sci. Labs., NTT Corp., Kyoto, Japan
fYear :
2012
fDate :
10-13 Dec. 2012
Firstpage :
906
Lastpage :
911
Abstract :
The amount and variety of multimedia data such as images, movies and music available on over social networks are increasing rapidly. However, the ability to analyze and exploit these unorganized multimedia data remains inadequate, even with state-of-the-art media processing techniques. Our finding in this paper is that the emerging social curation service is a promising information source for the automatic understanding and mining of images distributed and exchanged via social media. One remarkable virtue of social curation service datasets is that they are weakly supervised: the content in the service is manually collected, selected and maintained by users. This is very different from other social information sources, and we can utilize this characteristics for media content mining without expensive media processing techniques. In this paper we present a machine learning system for predicting view counts of images in social curation data as the first step to automatic image content evaluation. Our experiments confirm that the simple features extracted from a social curation corpus are much superior in terms of count prediction than the gold-standard image features of computer vision research.
Keywords :
data mining; feature extraction; image processing; learning (artificial intelligence); multimedia computing; social networking (online); automatic image content evaluation; automatic image mining; automatic image understanding; feature extraction; machine learning system; media content mining; movies; multimedia data; music; social curation service; social media; social network; view count prediction; Computer vision; Context; Data mining; Feature extraction; Histograms; Media; Motion pictures; Social curation; automatic image understanding and evaluation; feature extraction; regression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Mining (ICDM), 2012 IEEE 12th International Conference on
Conference_Location :
Brussels
ISSN :
1550-4786
Print_ISBN :
978-1-4673-4649-8
Type :
conf
DOI :
10.1109/ICDM.2012.37
Filename :
6413834
Link To Document :
بازگشت