Please use this identifier to cite or link to this item:
Title: Contextualizing object detection and classification
Authors: Song, Z. 
Chen, Q.
Huang, Z.
Hua, Y.
Yan, S. 
Issue Date: 2011
Citation: Song, Z.,Chen, Q.,Huang, Z.,Hua, Y.,Yan, S. (2011). Contextualizing object detection and classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 1585-1592. ScholarBank@NUS Repository.
Abstract: In this paper, we investigate how to iteratively and mutually boost object classification and detection by taking the outputs from one task as the context of the other one. First, instead of intuitive feature and context concatenation or postprocessing with context, the so-called Contextualized Support Vector Machine (Context-SVM) is proposed, where the context takes the responsibility of dynamically adjusting the classification hyperplane, and thus the context-adaptive classifier is achieved. Then, an iterative training procedure is presented. In each step, Context-SVM, associated with the output context from one task (object classification or detection), is instantiated to boost the performance for the other task, whose augmented outputs are then further used to improve the former task by Context-SVM. The proposed solution is evaluated on the object classification and detection tasks of PASCAL Visual Object Challenge (VOC) 2007 and 2010, and achieves the state-of-the-art performance. © 2011 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN: 9781457703942
ISSN: 10636919
DOI: 10.1109/CVPR.2011.5995330
Appears in Collections:Staff Publications

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


checked on Nov 12, 2019

Page view(s)

checked on Oct 27, 2019

Google ScholarTM



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