Object categorization using co-occurrence, location and appearance

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

Object categorization using co-occurrence, location and appearance. / Galleguillos, Carolina; Rabinovich, Andrew; Belongie, Serge.

I: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Galleguillos, C, Rabinovich, A & Belongie, S 2008, 'Object categorization using co-occurrence, location and appearance', 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. https://doi.org/10.1109/CVPR.2008.4587799

APA

Galleguillos, C., Rabinovich, A., & Belongie, S. (2008). Object categorization using co-occurrence, location and appearance. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. https://doi.org/10.1109/CVPR.2008.4587799

Vancouver

Galleguillos C, Rabinovich A, Belongie S. Object categorization using co-occurrence, location and appearance. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. https://doi.org/10.1109/CVPR.2008.4587799

Author

Galleguillos, Carolina ; Rabinovich, Andrew ; Belongie, Serge. / Object categorization using co-occurrence, location and appearance. I: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008.

Bibtex

@inproceedings{7bdd3da577c34c1d8c67e9d3f7ccc0b8,
title = "Object categorization using co-occurrence, location and appearance",
abstract = "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.",
author = "Carolina Galleguillos and Andrew Rabinovich and Serge Belongie",
year = "2008",
doi = "10.1109/CVPR.2008.4587799",
language = "English",
journal = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",
note = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR ; Conference date: 23-06-2008 Through 28-06-2008",

}

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