An empirical study of context in object detection

Santosh K. Divvala; Derek Hoiem; James H. Hays; Alexei A. Efros; Martial Hebert

doi:10.1109/CVPRW.2009.5206532

An empirical study of context in object detection

Santosh K. Divvala, Derek Hoiem, James H. Hays, Alexei A. Efros, Martial Hebert

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using topperforming local appearance detectors as baseline. We evaluate several different sources of context and ways to utilize it. While we employ many contextual cues that have been used before, we also propose a few novel ones including the use of geographic context and a new approach for using object spatial support.

Original language	English (US)
Title of host publication	2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Publisher	IEEE Computer Society
Pages	1271-1278
Number of pages	8
ISBN (Print)	9781424439935
DOIs	https://doi.org/10.1109/CVPRW.2009.5206532
State	Published - 2009
Event	2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States Duration: Jun 20 2009 → Jun 25 2009

Publication series

Name	2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Other

Other	2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Country/Territory	United States
City	Miami, FL
Period	6/20/09 → 6/25/09

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Biomedical Engineering

Online availability

10.1109/CVPRW.2009.5206532

Library availability

Discover UIUC Full Text

Cite this

Divvala, S. K., Hoiem, D., Hays, J. H., Efros, A. A., & Hebert, M. (2009). An empirical study of context in object detection. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 (pp. 1271-1278). Article 5206532 (2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2009.5206532

An empirical study of context in object detection. / Divvala, Santosh K.; Hoiem, Derek; Hays, James H. et al.
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society, 2009. p. 1271-1278 5206532 (2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Divvala, SK, Hoiem, D, Hays, JH, Efros, AA & Hebert, M 2009, An empirical study of context in object detection. in 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009., 5206532, 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, IEEE Computer Society, pp. 1271-1278, 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, Miami, FL, United States, 6/20/09. https://doi.org/10.1109/CVPRW.2009.5206532

Divvala SK, Hoiem D, Hays JH, Efros AA, Hebert M. An empirical study of context in object detection. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society. 2009. p. 1271-1278. 5206532. (2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009). doi: 10.1109/CVPRW.2009.5206532

@inproceedings{f86a386130a0444a9435270a1107d529,

title = "An empirical study of context in object detection",

abstract = "This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using topperforming local appearance detectors as baseline. We evaluate several different sources of context and ways to utilize it. While we employ many contextual cues that have been used before, we also propose a few novel ones including the use of geographic context and a new approach for using object spatial support.",

author = "Divvala, {Santosh K.} and Derek Hoiem and Hays, {James H.} and Efros, {Alexei A.} and Martial Hebert",

year = "2009",

doi = "10.1109/CVPRW.2009.5206532",

language = "English (US)",

isbn = "9781424439935",

series = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009",

publisher = "IEEE Computer Society",

pages = "1271--1278",

booktitle = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",

note = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 ; Conference date: 20-06-2009 Through 25-06-2009",

}

TY - GEN

T1 - An empirical study of context in object detection

AU - Divvala, Santosh K.

AU - Hoiem, Derek

AU - Hays, James H.

AU - Efros, Alexei A.

AU - Hebert, Martial

PY - 2009

Y1 - 2009

N2 - This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using topperforming local appearance detectors as baseline. We evaluate several different sources of context and ways to utilize it. While we employ many contextual cues that have been used before, we also propose a few novel ones including the use of geographic context and a new approach for using object spatial support.

AB - This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using topperforming local appearance detectors as baseline. We evaluate several different sources of context and ways to utilize it. While we employ many contextual cues that have been used before, we also propose a few novel ones including the use of geographic context and a new approach for using object spatial support.

UR - http://www.scopus.com/inward/record.url?scp=70450161428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450161428&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206532

DO - 10.1109/CVPRW.2009.5206532

M3 - Conference contribution

AN - SCOPUS:70450161428

SN - 9781424439935

T3 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

SP - 1271

EP - 1278

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

PB - IEEE Computer Society

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

Y2 - 20 June 2009 through 25 June 2009

ER -

An empirical study of context in object detection

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this