Salient Object Subitizing

We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision 2017-09, Vol.124 (2), p.169-186
Hauptverfasser: Zhang, Jianming, Ma, Shugao, Sameki, Mehrnoosh, Sclaroff, Stan, Betke, Margrit, Lin, Zhe, Shen, Xiaohui, Price, Brian, Měch, Radomír
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 186
container_issue 2
container_start_page 169
container_title International journal of computer vision
container_volume 124
creator Zhang, Jianming
Ma, Shugao
Sameki, Mehrnoosh
Sclaroff, Stan
Betke, Margrit
Lin, Zhe
Shen, Xiaohui
Price, Brian
Měch, Radomír
description We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.
doi_str_mv 10.1007/s11263-017-1011-0
format Article
fullrecord <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_1925068264</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A499747611</galeid><sourcerecordid>A499747611</sourcerecordid><originalsourceid>FETCH-LOGICAL-c389t-548af4f37a63d84cfcfe3be85b3b63cbcbbef90ecf8f719097cc57a2ebddd0b43</originalsourceid><addsrcrecordid>eNp1kE1LAzEQhoMoWKs_oLeCJw9bZ5LdzeZYih8FoWD1HJJsUlLa3brJgvrrTVkP9iBzGBieZ2Z4CZkgzBCA3wdEWrIMkGcIiBmckREWnGWYQ3FORiAoZEUp8JJchbAFAFpRNiKTtdp528TpSm-tidN1r330377ZXJMLp3bB3vz2MXl_fHhbPGcvq6flYv6SGVaJmBV5pVzuGFclq6vcOOMs07YqNNMlM9pobZ0Aa1zlOAoQ3JiCK2p1XdegczYmt8PeQ9d-9DZEuW37rkknJQpaQFnR8kjNBmqjdlb6xrWxUyZVbffetI11Ps3nuRA85yViEu5OhMRE-xk3qg9BLtevpywOrOnaEDrr5KHze9V9SQR5jFcO8coUrzzGKyE5dHBCYpuN7f68_a_0A6mIevo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1925068264</pqid></control><display><type>article</type><title>Salient Object Subitizing</title><source>SpringerNature Journals</source><creator>Zhang, Jianming ; Ma, Shugao ; Sameki, Mehrnoosh ; Sclaroff, Stan ; Betke, Margrit ; Lin, Zhe ; Shen, Xiaohui ; Price, Brian ; Měch, Radomír</creator><creatorcontrib>Zhang, Jianming ; Ma, Shugao ; Sameki, Mehrnoosh ; Sclaroff, Stan ; Betke, Margrit ; Lin, Zhe ; Shen, Xiaohui ; Price, Brian ; Měch, Radomír</creatorcontrib><description>We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.</description><identifier>ISSN: 0920-5691</identifier><identifier>EISSN: 1573-1405</identifier><identifier>DOI: 10.1007/s11263-017-1011-0</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Analysis ; Artificial Intelligence ; Artificial neural networks ; Computer Imaging ; Computer Science ; Cues ; Human performance ; Image detection ; Image Processing and Computer Vision ; Image retrieval ; Mathematical models ; Neural networks ; Object recognition ; Pattern Recognition ; Pattern Recognition and Graphics ; Predictions ; Salience ; Vision ; Vision systems</subject><ispartof>International journal of computer vision, 2017-09, Vol.124 (2), p.169-186</ispartof><rights>Springer Science+Business Media New York 2017</rights><rights>COPYRIGHT 2017 Springer</rights><rights>International Journal of Computer Vision is a copyright of Springer, 2017.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c389t-548af4f37a63d84cfcfe3be85b3b63cbcbbef90ecf8f719097cc57a2ebddd0b43</citedby><cites>FETCH-LOGICAL-c389t-548af4f37a63d84cfcfe3be85b3b63cbcbbef90ecf8f719097cc57a2ebddd0b43</cites><orcidid>0000-0002-9954-6294 ; 0000-0002-0711-4313</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11263-017-1011-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11263-017-1011-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Zhang, Jianming</creatorcontrib><creatorcontrib>Ma, Shugao</creatorcontrib><creatorcontrib>Sameki, Mehrnoosh</creatorcontrib><creatorcontrib>Sclaroff, Stan</creatorcontrib><creatorcontrib>Betke, Margrit</creatorcontrib><creatorcontrib>Lin, Zhe</creatorcontrib><creatorcontrib>Shen, Xiaohui</creatorcontrib><creatorcontrib>Price, Brian</creatorcontrib><creatorcontrib>Měch, Radomír</creatorcontrib><title>Salient Object Subitizing</title><title>International journal of computer vision</title><addtitle>Int J Comput Vis</addtitle><description>We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.</description><subject>Analysis</subject><subject>Artificial Intelligence</subject><subject>Artificial neural networks</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Cues</subject><subject>Human performance</subject><subject>Image detection</subject><subject>Image Processing and Computer Vision</subject><subject>Image retrieval</subject><subject>Mathematical models</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Pattern Recognition</subject><subject>Pattern Recognition and Graphics</subject><subject>Predictions</subject><subject>Salience</subject><subject>Vision</subject><subject>Vision systems</subject><issn>0920-5691</issn><issn>1573-1405</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp1kE1LAzEQhoMoWKs_oLeCJw9bZ5LdzeZYih8FoWD1HJJsUlLa3brJgvrrTVkP9iBzGBieZ2Z4CZkgzBCA3wdEWrIMkGcIiBmckREWnGWYQ3FORiAoZEUp8JJchbAFAFpRNiKTtdp528TpSm-tidN1r330377ZXJMLp3bB3vz2MXl_fHhbPGcvq6flYv6SGVaJmBV5pVzuGFclq6vcOOMs07YqNNMlM9pobZ0Aa1zlOAoQ3JiCK2p1XdegczYmt8PeQ9d-9DZEuW37rkknJQpaQFnR8kjNBmqjdlb6xrWxUyZVbffetI11Ps3nuRA85yViEu5OhMRE-xk3qg9BLtevpywOrOnaEDrr5KHze9V9SQR5jFcO8coUrzzGKyE5dHBCYpuN7f68_a_0A6mIevo</recordid><startdate>20170901</startdate><enddate>20170901</enddate><creator>Zhang, Jianming</creator><creator>Ma, Shugao</creator><creator>Sameki, Mehrnoosh</creator><creator>Sclaroff, Stan</creator><creator>Betke, Margrit</creator><creator>Lin, Zhe</creator><creator>Shen, Xiaohui</creator><creator>Price, Brian</creator><creator>Měch, Radomír</creator><general>Springer US</general><general>Springer</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>3V.</scope><scope>7SC</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PYYUZ</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0002-9954-6294</orcidid><orcidid>https://orcid.org/0000-0002-0711-4313</orcidid></search><sort><creationdate>20170901</creationdate><title>Salient Object Subitizing</title><author>Zhang, Jianming ; Ma, Shugao ; Sameki, Mehrnoosh ; Sclaroff, Stan ; Betke, Margrit ; Lin, Zhe ; Shen, Xiaohui ; Price, Brian ; Měch, Radomír</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c389t-548af4f37a63d84cfcfe3be85b3b63cbcbbef90ecf8f719097cc57a2ebddd0b43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Analysis</topic><topic>Artificial Intelligence</topic><topic>Artificial neural networks</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Cues</topic><topic>Human performance</topic><topic>Image detection</topic><topic>Image Processing and Computer Vision</topic><topic>Image retrieval</topic><topic>Mathematical models</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Pattern Recognition</topic><topic>Pattern Recognition and Graphics</topic><topic>Predictions</topic><topic>Salience</topic><topic>Vision</topic><topic>Vision systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Jianming</creatorcontrib><creatorcontrib>Ma, Shugao</creatorcontrib><creatorcontrib>Sameki, Mehrnoosh</creatorcontrib><creatorcontrib>Sclaroff, Stan</creatorcontrib><creatorcontrib>Betke, Margrit</creatorcontrib><creatorcontrib>Lin, Zhe</creatorcontrib><creatorcontrib>Shen, Xiaohui</creatorcontrib><creatorcontrib>Price, Brian</creatorcontrib><creatorcontrib>Měch, Radomír</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>Access via ABI/INFORM (ProQuest)</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM Global</collection><collection>Computing Database</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ABI/INFORM Collection China</collection><collection>ProQuest Central Basic</collection><jtitle>International journal of computer vision</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Jianming</au><au>Ma, Shugao</au><au>Sameki, Mehrnoosh</au><au>Sclaroff, Stan</au><au>Betke, Margrit</au><au>Lin, Zhe</au><au>Shen, Xiaohui</au><au>Price, Brian</au><au>Měch, Radomír</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Salient Object Subitizing</atitle><jtitle>International journal of computer vision</jtitle><stitle>Int J Comput Vis</stitle><date>2017-09-01</date><risdate>2017</risdate><volume>124</volume><issue>2</issue><spage>169</spage><epage>186</epage><pages>169-186</pages><issn>0920-5691</issn><eissn>1573-1405</eissn><abstract>We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s11263-017-1011-0</doi><tpages>18</tpages><orcidid>https://orcid.org/0000-0002-9954-6294</orcidid><orcidid>https://orcid.org/0000-0002-0711-4313</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0920-5691
ispartof International journal of computer vision, 2017-09, Vol.124 (2), p.169-186
issn 0920-5691
1573-1405
language eng
recordid cdi_proquest_journals_1925068264
source SpringerNature Journals
subjects Analysis
Artificial Intelligence
Artificial neural networks
Computer Imaging
Computer Science
Cues
Human performance
Image detection
Image Processing and Computer Vision
Image retrieval
Mathematical models
Neural networks
Object recognition
Pattern Recognition
Pattern Recognition and Graphics
Predictions
Salience
Vision
Vision systems
title Salient Object Subitizing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T16%3A46%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Salient%20Object%20Subitizing&rft.jtitle=International%20journal%20of%20computer%20vision&rft.au=Zhang,%20Jianming&rft.date=2017-09-01&rft.volume=124&rft.issue=2&rft.spage=169&rft.epage=186&rft.pages=169-186&rft.issn=0920-5691&rft.eissn=1573-1405&rft_id=info:doi/10.1007/s11263-017-1011-0&rft_dat=%3Cgale_proqu%3EA499747611%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1925068264&rft_id=info:pmid/&rft_galeid=A499747611&rfr_iscdi=true