DocumentCode :
3410124
Title :
Multi-class object localization by combining local contextual interactions
Author :
Galleguillos, Carolina ; McFee, Brian ; Belongie, Serge ; Lanckriet, Gert
Author_Institution :
Comput. Sci. & Eng. Dept., Univ. of California, San Diego, CA, USA
fYear :
2010
fDate :
13-18 June 2010
Firstpage :
113
Lastpage :
120
Abstract :
Recent work in object localization has shown that the use of contextual cues can greatly improve accuracy over models that use appearance features alone. Although many of these models have successfully explored different types of contextual sources, they only consider one type of contextual interaction (e.g., pixel, region or object level interactions), leaving open questions about the true potential contribution of context. Furthermore, contributions across object classes and over appearance features still remain unknown. In this work, we introduce a novel model for multi-class object localization that incorporates different levels of contextual interactions. We study contextual interactions at pixel, region and object level by using three different sources of context: semantic, boundary support and contextual neighborhoods. Our framework learns a single similarity metric from multiple kernels, combining pixel and region interactions with appearance features, and then uses a conditional random field to incorporate object level interactions. We perform experiments on two challenging image databases: MSRC and PASCAL VOC 2007. Experimental results show that our model outperforms current state-of-the-art contextual frameworks and reveals individual contributions for each contextual interaction level, as well as the importance of each type of feature in object localization.
Keywords :
feature extraction; image resolution; user interfaces; PASCAL VOC 2007; boundary support; contextual neighborhoods; local contextual interactions; multiclass object localization; object level interactions; potential contribution; Computer science; Computer vision; Context modeling; Face detection; Horses; Image classification; Image databases; Kernel; Layout; Nearest neighbor searches;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
Conference_Location :
San Francisco, CA
ISSN :
1063-6919
Print_ISBN :
978-1-4244-6984-0
Type :
conf
DOI :
10.1109/CVPR.2010.5540223
Filename :
5540223
Link To Document :
بازگشت