Weakly supervised object localization via maximal entropy random walk

Wang, Liantao, Zhao, Ji, Hu, Xuelei and Lu, Jianfeng (2014). Weakly supervised object localization via maximal entropy random walk. In: 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, (1614-1617). 27-30 October 2014. doi:10.1109/ICIP.2014.7025323

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Wang, Liantao
Zhao, Ji
Hu, Xuelei
Lu, Jianfeng
Title of paper Weakly supervised object localization via maximal entropy random walk
Conference name 2014 IEEE International Conference on Image Processing (ICIP)
Conference location Paris, France
Conference dates 27-30 October 2014
Journal name 2014 IEEE International Conference on Image Processing, ICIP 2014
Series 2014 IEEE International Conference on Image Processing, ICIP 2014
Place of Publication Piscataway, NJ, United States
Publisher IEEE
Publication Year 2014
Sub-type Fully published paper
DOI 10.1109/ICIP.2014.7025323
Open Access Status Not yet assessed
ISBN 9781479957514
Start page 1614
End page 1617
Total pages 4
Language eng
Abstract/Summary In this paper, we investigate the problem of weakly supervised object localization in images. For such a problem, the goal is to predict the locations of objects in test images while the labels of the training images are given at image-level. That means a label only indicates whether an image contains objects or not, but does not provide the exact locations of the objects. We propose to address this problem using Maximal Entropy Random Walk (MERW). Specifically, we first train a linear SVM classifier with the weakly labeled data. Based on bag-of-words feature representation, the response of a region to the linear SVM classifier can be formulated as the sum of the feature-weights within the region. For a test image, by properly constructing a graph on the feature-points, the stationary distribution of a MERW can indicate the region with the densest positive feature-weights, and thus provides a probabilistic object localization. Experiments compared with state-of-the-art methods on two datasets validate the performance of our method.
Subjects 1707 Computer Vision and Pattern Recognition
Keyword Maximal entropy random walk
Object localization
Weakly supervised learning
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collection: School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 2 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Fri, 26 Jun 2015, 20:51:54 EST by Xuelei Hu on behalf of School of Information Technol and Elec Engineering