DocumentCode :
2403126
Title :
Object image retrieval by exploiting online knowledge resources
Author :
Wang, Gang ; Forsyth, David
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL
fYear :
2008
fDate :
23-28 June 2008
Firstpage :
1
Lastpage :
8
Abstract :
We describe a method to retrieve images found on Web pages with specified object class labels, using an analysis of text around the image and of image appearance. Our method determines whether an object is both described in text and appears in a image using a discriminative image model and a generative text model. Our models are learnt by exploiting established online knowledge resources (Wikipedia pages for text; Flickr and Caltech data sets for image). These resources provide rich text and object appearance information. We describe results on two data sets. The first is Bergpsilas collection of ten animal categories; on this data set, we outperform previous approaches (Berg et al., 2006; Schroff et al., 2007). We have also collected five more categories. Experimental results show the effectiveness of our approach on this new data set.
Keywords :
image retrieval; text analysis; discriminative image model; generative text model; object class labels; object image retrieval; online knowledge resources; text analysis; Animals; Bicycles; Computer science; Displays; Image analysis; Image retrieval; Labeling; Search engines; Web pages; Wikipedia;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Conference_Location :
Anchorage, AK
ISSN :
1063-6919
Print_ISBN :
978-1-4244-2242-5
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2008.4587818
Filename :
4587818
Link To Document :
بازگشت