An empirical study of context in object detection

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 contrib...

Full description

Saved in:
Bibliographic Details
Main Authors: Divvala, Santosh K, Hoiem, Derek, Hays, James H, Efros, Alexei A, Hebert, Martial
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Computer vision
Context modeling
Gas detectors
Layout
Object detection
Ocean temperature
Pixel
Sea surface
Shape
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c244t-231ec0725b1e7e65aa356320fa9acbc771e1ebe7989a1c1b44a813bcad1bce2e3
cites
container_end_page 1278
container_issue
container_start_page 1271
container_title
container_volume
creator Divvala, Santosh K
Hoiem, Derek
Hays, James H
Efros, Alexei A
Hebert, Martial
description 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 top-performing 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.
doi_str_mv 10.1109/CVPR.2009.5206532
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5206532</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5206532</ieee_id><sourcerecordid>5206532</sourcerecordid><originalsourceid>FETCH-LOGICAL-c244t-231ec0725b1e7e65aa356320fa9acbc771e1ebe7989a1c1b44a813bcad1bce2e3</originalsourceid><addsrcrecordid>eNo1j9FKwzAUhiMquM09gHiTF2g956RNmstRdAqDDVFvR5KeQsbWjjaCe3sHzquP_-b7-YR4QMgRwT7VX5v3nABsXhLoUtGVmFtTYUFFoaxFvBbT_0F0IyYIWmXaor0T03HcAZAyBBOBi07y4RiHGNxejum7Ocm-laHvEv8kGTvZ-x2HJBtOZ8S-uxe3rduPPL9wJj5fnj_q12y1Xr7Vi1UWzrcpI4UcwFDpkQ3r0jlVakXQOuuCD8YgI3s2trIOA_qicBUqH1yDPjCxmonHP29k5u1xiAc3nLaXXPULKMJGpw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>An empirical study of context in object detection</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Divvala, Santosh K ; Hoiem, Derek ; Hays, James H ; Efros, Alexei A ; Hebert, Martial</creator><creatorcontrib>Divvala, Santosh K ; Hoiem, Derek ; Hays, James H ; Efros, Alexei A ; Hebert, Martial</creatorcontrib><description>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 top-performing 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.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 1424439922</identifier><identifier>ISBN: 9781424439928</identifier><identifier>EISBN: 9781424439911</identifier><identifier>EISBN: 1424439914</identifier><identifier>DOI: 10.1109/CVPR.2009.5206532</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Computer vision ; Context modeling ; Gas detectors ; Layout ; Object detection ; Ocean temperature ; Pixel ; Sea surface ; Shape</subject><ispartof>2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, p.1271-1278</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c244t-231ec0725b1e7e65aa356320fa9acbc771e1ebe7989a1c1b44a813bcad1bce2e3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5206532$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5206532$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Divvala, Santosh K</creatorcontrib><creatorcontrib>Hoiem, Derek</creatorcontrib><creatorcontrib>Hays, James H</creatorcontrib><creatorcontrib>Efros, Alexei A</creatorcontrib><creatorcontrib>Hebert, Martial</creatorcontrib><title>An empirical study of context in object detection</title><title>2009 IEEE Conference on Computer Vision and Pattern Recognition</title><addtitle>CVPR</addtitle><description>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 top-performing 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.</description><subject>Cameras</subject><subject>Computer vision</subject><subject>Context modeling</subject><subject>Gas detectors</subject><subject>Layout</subject><subject>Object detection</subject><subject>Ocean temperature</subject><subject>Pixel</subject><subject>Sea surface</subject><subject>Shape</subject><issn>1063-6919</issn><isbn>1424439922</isbn><isbn>9781424439928</isbn><isbn>9781424439911</isbn><isbn>1424439914</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j9FKwzAUhiMquM09gHiTF2g956RNmstRdAqDDVFvR5KeQsbWjjaCe3sHzquP_-b7-YR4QMgRwT7VX5v3nABsXhLoUtGVmFtTYUFFoaxFvBbT_0F0IyYIWmXaor0T03HcAZAyBBOBi07y4RiHGNxejum7Ocm-laHvEv8kGTvZ-x2HJBtOZ8S-uxe3rduPPL9wJj5fnj_q12y1Xr7Vi1UWzrcpI4UcwFDpkQ3r0jlVakXQOuuCD8YgI3s2trIOA_qicBUqH1yDPjCxmonHP29k5u1xiAc3nLaXXPULKMJGpw</recordid><startdate>200906</startdate><enddate>200906</enddate><creator>Divvala, Santosh K</creator><creator>Hoiem, Derek</creator><creator>Hays, James H</creator><creator>Efros, Alexei A</creator><creator>Hebert, Martial</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200906</creationdate><title>An empirical study of context in object detection</title><author>Divvala, Santosh K ; Hoiem, Derek ; Hays, James H ; Efros, Alexei A ; Hebert, Martial</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c244t-231ec0725b1e7e65aa356320fa9acbc771e1ebe7989a1c1b44a813bcad1bce2e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Cameras</topic><topic>Computer vision</topic><topic>Context modeling</topic><topic>Gas detectors</topic><topic>Layout</topic><topic>Object detection</topic><topic>Ocean temperature</topic><topic>Pixel</topic><topic>Sea surface</topic><topic>Shape</topic><toplevel>online_resources</toplevel><creatorcontrib>Divvala, Santosh K</creatorcontrib><creatorcontrib>Hoiem, Derek</creatorcontrib><creatorcontrib>Hays, James H</creatorcontrib><creatorcontrib>Efros, Alexei A</creatorcontrib><creatorcontrib>Hebert, Martial</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Divvala, Santosh K</au><au>Hoiem, Derek</au><au>Hays, James H</au><au>Efros, Alexei A</au><au>Hebert, Martial</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>An empirical study of context in object detection</atitle><btitle>2009 IEEE Conference on Computer Vision and Pattern Recognition</btitle><stitle>CVPR</stitle><date>2009-06</date><risdate>2009</risdate><spage>1271</spage><epage>1278</epage><pages>1271-1278</pages><issn>1063-6919</issn><isbn>1424439922</isbn><isbn>9781424439928</isbn><eisbn>9781424439911</eisbn><eisbn>1424439914</eisbn><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 top-performing 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.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.2009.5206532</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1063-6919
ispartof 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, p.1271-1278
issn 1063-6919
language eng
recordid cdi_ieee_primary_5206532
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Cameras
Computer vision
Context modeling
Gas detectors
Layout
Object detection
Ocean temperature
Pixel
Sea surface
Shape
title An empirical study of context in object detection
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T04%3A51%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=An%20empirical%20study%20of%20context%20in%20object%20detection&rft.btitle=2009%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition&rft.au=Divvala,%20Santosh%20K&rft.date=2009-06&rft.spage=1271&rft.epage=1278&rft.pages=1271-1278&rft.issn=1063-6919&rft.isbn=1424439922&rft.isbn_list=9781424439928&rft_id=info:doi/10.1109/CVPR.2009.5206532&rft.eisbn=9781424439911&rft.eisbn_list=1424439914&rft_dat=%3Cieee_6IE%3E5206532%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c244t-231ec0725b1e7e65aa356320fa9acbc771e1ebe7989a1c1b44a813bcad1bce2e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5206532&rfr_iscdi=true