DocumentCode
3345811
Title
Saliency based joint topic discovery for object categorization
Author
Li, Zhidong ; Wang, Yang ; Geers, Glenn ; Chen, Jing ; Yang, Jun ; Laird, John
fYear
2010
fDate
26-29 Sept. 2010
Firstpage
4581
Lastpage
4584
Abstract
We present a novel approach of saliency based image categorization using topic model. In each image, salient foreground objects are discriminated from background scene by saliency detection. Then topic model is used to jointly discover topics of foreground and background. Our approach can categorize images in a completely unsupervised manner and achieve higher performance than previous categorization methods, especially for those images with similar foreground/background.
Keywords
image retrieval; unsupervised learning; background scene; object categorization; saliency based image categorization; saliency based joint topic discovery; saliency detection; salient foreground object; topic model; unsupervised learning; Accuracy; Computational modeling; Computer vision; Conferences; Image segmentation; Probabilistic logic; Visualization; PLSA; image categorization; saliency detection; topic model; unsupervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location
Hong Kong
ISSN
1522-4880
Print_ISBN
978-1-4244-7992-4
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2010.5652167
Filename
5652167
Link To Document