Objects in context

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Standard

Objects in context. / Rabinovich, Andrew; Vedaldi, Andrea; Galleguillos, Carolina; Wiewiora, Eric; Belongie, Serge.

2007. Paper præsenteret ved 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brasilien.

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Harvard

Rabinovich, A, Vedaldi, A, Galleguillos, C, Wiewiora, E & Belongie, S 2007, 'Objects in context', Paper fremlagt ved 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brasilien, 14/10/2007 - 21/10/2007. https://doi.org/10.1109/ICCV.2007.4408986

APA

Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., & Belongie, S. (2007). Objects in context. Paper præsenteret ved 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brasilien. https://doi.org/10.1109/ICCV.2007.4408986

Vancouver

Rabinovich A, Vedaldi A, Galleguillos C, Wiewiora E, Belongie S. Objects in context. 2007. Paper præsenteret ved 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brasilien. https://doi.org/10.1109/ICCV.2007.4408986

Author

Rabinovich, Andrew ; Vedaldi, Andrea ; Galleguillos, Carolina ; Wiewiora, Eric ; Belongie, Serge. / Objects in context. Paper præsenteret ved 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brasilien.

Bibtex

@conference{af4a880b27314833b94b58ae09b70332,
title = "Objects in context",
abstract = "In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model. Using a conditional random field (CRF) framework, oar approach maximizes object label agreement according to contextual relevance. We compare two sources of context: one learned from training data and another queried from Google Sets. The overall performance of the proposed framework is evaluated on the PASCAL and MSRC datasets. Our findings conclude that incorporating context into object categorization greatly imrproves categorization accuracy.",
author = "Andrew Rabinovich and Andrea Vedaldi and Carolina Galleguillos and Eric Wiewiora and Serge Belongie",
year = "2007",
doi = "10.1109/ICCV.2007.4408986",
language = "English",
note = "2007 IEEE 11th International Conference on Computer Vision, ICCV ; Conference date: 14-10-2007 Through 21-10-2007",

}

RIS

TY - CONF

T1 - Objects in context

AU - Rabinovich, Andrew

AU - Vedaldi, Andrea

AU - Galleguillos, Carolina

AU - Wiewiora, Eric

AU - Belongie, Serge

PY - 2007

Y1 - 2007

N2 - In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model. Using a conditional random field (CRF) framework, oar approach maximizes object label agreement according to contextual relevance. We compare two sources of context: one learned from training data and another queried from Google Sets. The overall performance of the proposed framework is evaluated on the PASCAL and MSRC datasets. Our findings conclude that incorporating context into object categorization greatly imrproves categorization accuracy.

AB - In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model. Using a conditional random field (CRF) framework, oar approach maximizes object label agreement according to contextual relevance. We compare two sources of context: one learned from training data and another queried from Google Sets. The overall performance of the proposed framework is evaluated on the PASCAL and MSRC datasets. Our findings conclude that incorporating context into object categorization greatly imrproves categorization accuracy.

UR - http://www.scopus.com/inward/record.url?scp=50649096757&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2007.4408986

DO - 10.1109/ICCV.2007.4408986

M3 - Paper

AN - SCOPUS:50649096757

T2 - 2007 IEEE 11th International Conference on Computer Vision, ICCV

Y2 - 14 October 2007 through 21 October 2007

ER -

ID: 302052099