Object categorization using co-occurrence, location and appearance
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Object categorization using co-occurrence, location and appearance. / Galleguillos, Carolina; Rabinovich, Andrew; Belongie, Serge.
In: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Object categorization using co-occurrence, location and appearance
AU - Galleguillos, Carolina
AU - Rabinovich, Andrew
AU - Belongie, Serge
PY - 2008
Y1 - 2008
N2 - In this work we introduce a novel approach to object categorization that incorporates two types of context - co-occurrence and relative location - with local appearance-based features. Our approach, named CoLA (for Co-occurrence, Location and Appearance), uses a conditional random field (CRF) to maximize object label agreement according to both semantic and spatial relevance. We model relative location between objects using simple pairwise features. By vector quantizing this feature space, we learn a small set of prototypical spatial relationships directly from the data. We evaluate our results on two challenging datasets: PASCAL 2007 and MSRC. The results show that combining co-occurrence and spatial context improves accuracy in as many as half of the categories compared to using co-occurrence alone.
AB - In this work we introduce a novel approach to object categorization that incorporates two types of context - co-occurrence and relative location - with local appearance-based features. Our approach, named CoLA (for Co-occurrence, Location and Appearance), uses a conditional random field (CRF) to maximize object label agreement according to both semantic and spatial relevance. We model relative location between objects using simple pairwise features. By vector quantizing this feature space, we learn a small set of prototypical spatial relationships directly from the data. We evaluate our results on two challenging datasets: PASCAL 2007 and MSRC. The results show that combining co-occurrence and spatial context improves accuracy in as many as half of the categories compared to using co-occurrence alone.
UR - http://www.scopus.com/inward/record.url?scp=51949110976&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2008.4587799
DO - 10.1109/CVPR.2008.4587799
M3 - Conference article
AN - SCOPUS:51949110976
JO - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
JF - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Y2 - 23 June 2008 through 28 June 2008
ER -
ID: 302050836