Scenes vs. objects: A comparative study of two approaches to context based recognition

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

Scenes vs. objects : A comparative study of two approaches to context based recognition. / Belongie, Serge; Rabinovich, Andrew.

In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, 2009, p. 92-99.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Belongie, S & Rabinovich, A 2009, 'Scenes vs. objects: A comparative study of two approaches to context based recognition', 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, pp. 92-99. https://doi.org/10.1109/CVPR.2009.5204220

APA

Belongie, S., & Rabinovich, A. (2009). Scenes vs. objects: A comparative study of two approaches to context based recognition. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, 92-99. https://doi.org/10.1109/CVPR.2009.5204220

Vancouver

Belongie S, Rabinovich A. Scenes vs. objects: A comparative study of two approaches to context based recognition. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009;92-99. https://doi.org/10.1109/CVPR.2009.5204220

Author

Belongie, Serge ; Rabinovich, Andrew. / Scenes vs. objects : A comparative study of two approaches to context based recognition. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009 ; pp. 92-99.

Bibtex

@inproceedings{59438edc175644759bb2439ad5b3399a,
title = "Scenes vs. objects: A comparative study of two approaches to context based recognition",
abstract = "Contextual models play a very important role in the task of object recognition. Over the years, two kinds of contextual models have emerged: models with contextual inference based on the statistical summary of the scene (we will refer to these as Scene Based Context models, or SBC), and models representing the context in terms of relationships among objects in the image (Object Based Context, or OBC). In designing object recognition systems, it is necessary to understand the theoretical and practical properties of such approaches. This work provides an analysis of these models and evaluates two of their representatives using the LabelMe dataset. We demonstrate a considerable margin of improvement using the OBC style approach.",
author = "Serge Belongie and Andrew Rabinovich",
year = "2009",
doi = "10.1109/CVPR.2009.5204220",
language = "English",
pages = "92--99",
journal = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",
note = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 ; Conference date: 20-06-2009 Through 25-06-2009",

}

RIS

TY - GEN

T1 - Scenes vs. objects

T2 - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

AU - Belongie, Serge

AU - Rabinovich, Andrew

PY - 2009

Y1 - 2009

N2 - Contextual models play a very important role in the task of object recognition. Over the years, two kinds of contextual models have emerged: models with contextual inference based on the statistical summary of the scene (we will refer to these as Scene Based Context models, or SBC), and models representing the context in terms of relationships among objects in the image (Object Based Context, or OBC). In designing object recognition systems, it is necessary to understand the theoretical and practical properties of such approaches. This work provides an analysis of these models and evaluates two of their representatives using the LabelMe dataset. We demonstrate a considerable margin of improvement using the OBC style approach.

AB - Contextual models play a very important role in the task of object recognition. Over the years, two kinds of contextual models have emerged: models with contextual inference based on the statistical summary of the scene (we will refer to these as Scene Based Context models, or SBC), and models representing the context in terms of relationships among objects in the image (Object Based Context, or OBC). In designing object recognition systems, it is necessary to understand the theoretical and practical properties of such approaches. This work provides an analysis of these models and evaluates two of their representatives using the LabelMe dataset. We demonstrate a considerable margin of improvement using the OBC style approach.

UR - http://www.scopus.com/inward/record.url?scp=70449586747&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2009.5204220

DO - 10.1109/CVPR.2009.5204220

M3 - Conference article

AN - SCOPUS:70449586747

SP - 92

EP - 99

JO - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

JF - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

Y2 - 20 June 2009 through 25 June 2009

ER -

ID: 302050349