Objects in context
Research output: Contribution to conference › Paper › Research › peer-review
Standard
Objects in context. / Rabinovich, Andrew; Vedaldi, Andrea; Galleguillos, Carolina; Wiewiora, Eric; Belongie, Serge.
2007. Paper presented at 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brazil.Research output: Contribution to conference › Paper › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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