Advances in deep learning approaches for image tagging

The advent of mobile devices and media cloud services has led to the unprecedented growth of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Image tagging is the task of assigning human-friendly tags to an image so t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:APSIPA transactions on signal and information processing 2017, Vol.6 (1)
Hauptverfasser: Fu, Jianlong, Rui, Yong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 1
container_start_page
container_title APSIPA transactions on signal and information processing
container_volume 6
creator Fu, Jianlong
Rui, Yong
description The advent of mobile devices and media cloud services has led to the unprecedented growth of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Image tagging is the task of assigning human-friendly tags to an image so that the semantic tags can better reflect the content of the image and therefore can help users better access that image. The quality of image tagging depends on the quality of concept modeling which builds a mapping from concepts to visual images. While significant progresses are made in the past decade on image tagging, the previous approaches can only achieve limited success due to the limited concept representation ability from hand-crafted features (e.g., Scale-Invariant Feature Transform, GIST, Histogram of Oriented Gradients, etc.). Further progresses are made, since the efficient and effective deep learning algorithms have been developed. The purpose of this paper is to categorize and evaluate different image tagging approaches based on deep learning techniques. We also discuss the relevant problems and applications to image tagging, including data collection, evaluation metrics, and existing commercial systems. We conclude the advantages of different image tagging paradigms and propose several promising research directions for future works.
doi_str_mv 10.1017/ATSIP.2017.12
format Article
fullrecord <record><control><sourceid>cambridge_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1017_ATSIP_2017_12</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><cupid>10_1017_ATSIP_2017_12</cupid><sourcerecordid>10_1017_ATSIP_2017_12</sourcerecordid><originalsourceid>FETCH-LOGICAL-c386t-438d135accf15f519a6cc3b0bb03e2db5448355fa5c081d835c0c9d10930de893</originalsourceid><addsrcrecordid>eNp1j0trwzAQhEVpoSHNsXf9ATu7kmXLRxP6CARaaHoWsh6uQ2IbKS3031dpcuilp_1gZpYZQu4RcgSsls32bf2as4Q5sisyY1DIrKqAX__hW7KIcQcAiEzUZTEjZWO_9GBcpP1ArXMT3Tsdhn7oqJ6mMGrzkTQ_BtofdOfoUXddEu_Ijdf76BaXOyfvjw_b1XO2eXlar5pNZrgsj1nBpUUutDEehRdY69IY3kLbAnfMtqIoJBfCa2FAok1swNQWoeZgnaz5nGTnvyaMMQbn1RRSkfCtENRpt_rdrU67FbLkX178-tCG3nZO7cbPMKSO_yR-AIUzWVU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Advances in deep learning approaches for image tagging</title><source>Cambridge University Press Wholly Gold Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Fu, Jianlong ; Rui, Yong</creator><creatorcontrib>Fu, Jianlong ; Rui, Yong</creatorcontrib><description>The advent of mobile devices and media cloud services has led to the unprecedented growth of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Image tagging is the task of assigning human-friendly tags to an image so that the semantic tags can better reflect the content of the image and therefore can help users better access that image. The quality of image tagging depends on the quality of concept modeling which builds a mapping from concepts to visual images. While significant progresses are made in the past decade on image tagging, the previous approaches can only achieve limited success due to the limited concept representation ability from hand-crafted features (e.g., Scale-Invariant Feature Transform, GIST, Histogram of Oriented Gradients, etc.). Further progresses are made, since the efficient and effective deep learning algorithms have been developed. The purpose of this paper is to categorize and evaluate different image tagging approaches based on deep learning techniques. We also discuss the relevant problems and applications to image tagging, including data collection, evaluation metrics, and existing commercial systems. We conclude the advantages of different image tagging paradigms and propose several promising research directions for future works.</description><identifier>ISSN: 2048-7703</identifier><identifier>EISSN: 2048-7703</identifier><identifier>DOI: 10.1017/ATSIP.2017.12</identifier><language>eng</language><publisher>Cambridge, UK: Cambridge University Press</publisher><subject>Industrial Technology Advances</subject><ispartof>APSIPA transactions on signal and information processing, 2017, Vol.6 (1)</ispartof><rights>Copyright © The Authors, 2017</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c386t-438d135accf15f519a6cc3b0bb03e2db5448355fa5c081d835c0c9d10930de893</citedby><cites>FETCH-LOGICAL-c386t-438d135accf15f519a6cc3b0bb03e2db5448355fa5c081d835c0c9d10930de893</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.cambridge.org/core/product/identifier/S2048770317000129/type/journal_article$$EHTML$$P50$$Gcambridge$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,4024,23318,27923,27924,27925,55804</link.rule.ids></links><search><creatorcontrib>Fu, Jianlong</creatorcontrib><creatorcontrib>Rui, Yong</creatorcontrib><title>Advances in deep learning approaches for image tagging</title><title>APSIPA transactions on signal and information processing</title><addtitle>APSIPA Transactions on Signal and Information Processing</addtitle><description>The advent of mobile devices and media cloud services has led to the unprecedented growth of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Image tagging is the task of assigning human-friendly tags to an image so that the semantic tags can better reflect the content of the image and therefore can help users better access that image. The quality of image tagging depends on the quality of concept modeling which builds a mapping from concepts to visual images. While significant progresses are made in the past decade on image tagging, the previous approaches can only achieve limited success due to the limited concept representation ability from hand-crafted features (e.g., Scale-Invariant Feature Transform, GIST, Histogram of Oriented Gradients, etc.). Further progresses are made, since the efficient and effective deep learning algorithms have been developed. The purpose of this paper is to categorize and evaluate different image tagging approaches based on deep learning techniques. We also discuss the relevant problems and applications to image tagging, including data collection, evaluation metrics, and existing commercial systems. We conclude the advantages of different image tagging paradigms and propose several promising research directions for future works.</description><subject>Industrial Technology Advances</subject><issn>2048-7703</issn><issn>2048-7703</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>IKXGN</sourceid><recordid>eNp1j0trwzAQhEVpoSHNsXf9ATu7kmXLRxP6CARaaHoWsh6uQ2IbKS3031dpcuilp_1gZpYZQu4RcgSsls32bf2as4Q5sisyY1DIrKqAX__hW7KIcQcAiEzUZTEjZWO_9GBcpP1ArXMT3Tsdhn7oqJ6mMGrzkTQ_BtofdOfoUXddEu_Ijdf76BaXOyfvjw_b1XO2eXlar5pNZrgsj1nBpUUutDEehRdY69IY3kLbAnfMtqIoJBfCa2FAok1swNQWoeZgnaz5nGTnvyaMMQbn1RRSkfCtENRpt_rdrU67FbLkX178-tCG3nZO7cbPMKSO_yR-AIUzWVU</recordid><startdate>2017</startdate><enddate>2017</enddate><creator>Fu, Jianlong</creator><creator>Rui, Yong</creator><general>Cambridge University Press</general><scope>IKXGN</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>2017</creationdate><title>Advances in deep learning approaches for image tagging</title><author>Fu, Jianlong ; Rui, Yong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c386t-438d135accf15f519a6cc3b0bb03e2db5448355fa5c081d835c0c9d10930de893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Industrial Technology Advances</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fu, Jianlong</creatorcontrib><creatorcontrib>Rui, Yong</creatorcontrib><collection>Cambridge University Press Wholly Gold Open Access Journals</collection><collection>CrossRef</collection><jtitle>APSIPA transactions on signal and information processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fu, Jianlong</au><au>Rui, Yong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Advances in deep learning approaches for image tagging</atitle><jtitle>APSIPA transactions on signal and information processing</jtitle><addtitle>APSIPA Transactions on Signal and Information Processing</addtitle><date>2017</date><risdate>2017</risdate><volume>6</volume><issue>1</issue><issn>2048-7703</issn><eissn>2048-7703</eissn><abstract>The advent of mobile devices and media cloud services has led to the unprecedented growth of personal photo collections. One of the fundamental problems in managing the increasing number of photos is automatic image tagging. Image tagging is the task of assigning human-friendly tags to an image so that the semantic tags can better reflect the content of the image and therefore can help users better access that image. The quality of image tagging depends on the quality of concept modeling which builds a mapping from concepts to visual images. While significant progresses are made in the past decade on image tagging, the previous approaches can only achieve limited success due to the limited concept representation ability from hand-crafted features (e.g., Scale-Invariant Feature Transform, GIST, Histogram of Oriented Gradients, etc.). Further progresses are made, since the efficient and effective deep learning algorithms have been developed. The purpose of this paper is to categorize and evaluate different image tagging approaches based on deep learning techniques. We also discuss the relevant problems and applications to image tagging, including data collection, evaluation metrics, and existing commercial systems. We conclude the advantages of different image tagging paradigms and propose several promising research directions for future works.</abstract><cop>Cambridge, UK</cop><pub>Cambridge University Press</pub><doi>10.1017/ATSIP.2017.12</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2048-7703
ispartof APSIPA transactions on signal and information processing, 2017, Vol.6 (1)
issn 2048-7703
2048-7703
language eng
recordid cdi_crossref_primary_10_1017_ATSIP_2017_12
source Cambridge University Press Wholly Gold Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals
subjects Industrial Technology Advances
title Advances in deep learning approaches for image tagging
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T19%3A02%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-cambridge_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Advances%20in%20deep%20learning%20approaches%20for%20image%20tagging&rft.jtitle=APSIPA%20transactions%20on%20signal%20and%20information%20processing&rft.au=Fu,%20Jianlong&rft.date=2017&rft.volume=6&rft.issue=1&rft.issn=2048-7703&rft.eissn=2048-7703&rft_id=info:doi/10.1017/ATSIP.2017.12&rft_dat=%3Ccambridge_cross%3E10_1017_ATSIP_2017_12%3C/cambridge_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_cupid=10_1017_ATSIP_2017_12&rfr_iscdi=true