Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2010.5540015
Title: Semantic context modeling with maximal margin conditional random fields for automatic image annotation
Authors: Xiang, Y.
Zhou, X.
Liu, Z.
Chua, T.-S. 
Ngo, C.-W.
Issue Date: 2010
Source: Xiang, Y., Zhou, X., Liu, Z., Chua, T.-S., Ngo, C.-W. (2010). Semantic context modeling with maximal margin conditional random fields for automatic image annotation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 3368-3375. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2010.5540015
Abstract: Context modeling for Vision Recognition and Automatic Image Annotation (AIA) has attracted increasing attentions in recent years. For various contextual information and resources, semantic context has been exploited in AIA and brings promising results. However, previous works either casted the problem into structural classification or adopted multi-layer modeling, which suffer from the problems of scalability or model efficiency. In this paper, we propose a novel discriminative Conditional Random Field (CRF) model for semantic context modeling in AIA, which is built over semantic concepts and treats an image as a whole observation without segmentation. Our model captures the interactions between semantic concepts from both semantic level and visual level in an integrated manner. Specifically, we employ graph structure to model contextual relationships between semantic concepts. The potential functions are designed based on linear discriminative models, which enables us to propose a novel decoupled hinge loss function for maximal margin parameter estimation. We train the model by solving a set of independent quadratic programming problems with our derived contextual kernel. The experiments are conducted on commonly used benchmarks: Corel and TRECVID data sets for evaluation. The experimental results show that compared with the state-of-the-art methods, our method achieves significant improvement on annotation performance. ©2010 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/40446
ISBN: 9781424469840
ISSN: 10636919
DOI: 10.1109/CVPR.2010.5540015
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

24
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

12
checked on Nov 21, 2017

Page view(s)

79
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.