TY - GEN

T1 - Multi-class object localization by combining local contextual interactions

AU - Galleguillos, Carolina

AU - McFee, Brian

AU - Belongie, Serge

AU - Lanckriet, Gert

PY - 2010

Y1 - 2010

N2 - 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 multiclass 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.

AB - 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 multiclass 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.

UR - http://www.scopus.com/inward/record.url?scp=77956001253&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2010.5540223

DO - 10.1109/CVPR.2010.5540223

M3 - Conference article

AN - SCOPUS:77956001253

SP - 113

EP - 120

JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

SN - 1063-6919

T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010

Y2 - 13 June 2010 through 18 June 2010

ER -