CINXE.COM

<!DOCTYPE html> <html class="client-nojs vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-feature-night-mode-enabled skin-theme-clientpref-day vector-sticky-header-enabled vector-toc-available" lang="en" dir="ltr"> <head> <meta charset="UTF-8"> <title>Automatic image annotation - Wikipedia</title> <script>(function(){var className="client-js vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-feature-night-mode-enabled skin-theme-clientpref-day vector-sticky-header-enabled vector-toc-available";var cookie=document.cookie.match(/(?:^|; )enwikimwclientpreferences=([^;]+)/);if(cookie){cookie[1].split('%2C').forEach(function(pref){className=className.replace(new RegExp('(^| )'+pref.replace(/-clientpref-\w+$|[^\w-]+/g,'')+'-clientpref-\\w+( |$)'),'$1'+pref+'$2');});}document.documentElement.className=className;}());RLCONF={"wgBreakFrames":false,"wgSeparatorTransformTable":["",""],"wgDigitTransformTable":["",""],"wgDefaultDateFormat":"dmy", "wgMonthNames":["","January","February","March","April","May","June","July","August","September","October","November","December"],"wgRequestId":"22c24ad2-f953-4788-8a31-324a227a8d1f","wgCanonicalNamespace":"","wgCanonicalSpecialPageName":false,"wgNamespaceNumber":0,"wgPageName":"Automatic_image_annotation","wgTitle":"Automatic image annotation","wgCurRevisionId":1275066243,"wgRevisionId":1275066243,"wgArticleId":1931185,"wgIsArticle":true,"wgIsRedirect":false,"wgAction":"view","wgUserName":null,"wgUserGroups":["*"],"wgCategories":["CS1 maint: archived copy as title","Articles needing cleanup from November 2022","All pages needing cleanup","Cleanup tagged articles with a reason field from November 2022","Wikipedia pages needing cleanup from November 2022","Applications of artificial intelligence","Applications of computer vision"],"wgPageViewLanguage":"en","wgPageContentLanguage":"en","wgPageContentModel":"wikitext","wgRelevantPageName":"Automatic_image_annotation","wgRelevantArticleId" :1931185,"wgIsProbablyEditable":true,"wgRelevantPageIsProbablyEditable":true,"wgRestrictionEdit":[],"wgRestrictionMove":[],"wgNoticeProject":"wikipedia","wgCiteReferencePreviewsActive":false,"wgFlaggedRevsParams":{"tags":{"status":{"levels":1}}},"wgMediaViewerOnClick":true,"wgMediaViewerEnabledByDefault":true,"wgPopupsFlags":0,"wgVisualEditor":{"pageLanguageCode":"en","pageLanguageDir":"ltr","pageVariantFallbacks":"en"},"wgMFDisplayWikibaseDescriptions":{"search":true,"watchlist":true,"tagline":false,"nearby":true},"wgWMESchemaEditAttemptStepOversample":false,"wgWMEPageLength":20000,"wgEditSubmitButtonLabelPublish":true,"wgULSPosition":"interlanguage","wgULSisCompactLinksEnabled":false,"wgVector2022LanguageInHeader":true,"wgULSisLanguageSelectorEmpty":false,"wgWikibaseItemId":"Q2851778","wgCheckUserClientHintsHeadersJsApi":["brands","architecture","bitness","fullVersionList","mobile","model","platform","platformVersion"],"GEHomepageSuggestedEditsEnableTopics":true, "wgGETopicsMatchModeEnabled":false,"wgGEStructuredTaskRejectionReasonTextInputEnabled":false,"wgGELevelingUpEnabledForUser":false};RLSTATE={"ext.globalCssJs.user.styles":"ready","site.styles":"ready","user.styles":"ready","ext.globalCssJs.user":"ready","user":"ready","user.options":"loading","ext.cite.styles":"ready","skins.vector.search.codex.styles":"ready","skins.vector.styles":"ready","skins.vector.icons":"ready","jquery.makeCollapsible.styles":"ready","ext.wikimediamessages.styles":"ready","ext.visualEditor.desktopArticleTarget.noscript":"ready","ext.uls.interlanguage":"ready","wikibase.client.init":"ready","ext.wikimediaBadges":"ready"};RLPAGEMODULES=["ext.cite.ux-enhancements","mediawiki.page.media","site","mediawiki.page.ready","jquery.makeCollapsible","skins.vector.js","ext.centralNotice.geoIP","ext.centralNotice.startUp","ext.gadget.ReferenceTooltips","ext.gadget.switcher","ext.urlShortener.toolbar","ext.centralauth.centralautologin","mmv.bootstrap","ext.popups", "ext.visualEditor.desktopArticleTarget.init","ext.visualEditor.targetLoader","ext.echo.centralauth","ext.eventLogging","ext.wikimediaEvents","ext.navigationTiming","ext.uls.interface","ext.cx.eventlogging.campaigns","ext.cx.uls.quick.actions","wikibase.client.vector-2022","ext.checkUser.clientHints","ext.growthExperiments.SuggestedEditSession"];</script> <script>(RLQ=window.RLQ||[]).push(function(){mw.loader.impl(function(){return["user.options@12s5i",function($,jQuery,require,module){mw.user.tokens.set({"patrolToken":"+\\","watchToken":"+\\","csrfToken":"+\\"}); }];});});</script> <link rel="stylesheet" href="/w/load.php?lang=en&modules=ext.cite.styles%7Cext.uls.interlanguage%7Cext.visualEditor.desktopArticleTarget.noscript%7Cext.wikimediaBadges%7Cext.wikimediamessages.styles%7Cjquery.makeCollapsible.styles%7Cskins.vector.icons%2Cstyles%7Cskins.vector.search.codex.styles%7Cwikibase.client.init&only=styles&skin=vector-2022"> <script async="" src="/w/load.php?lang=en&modules=startup&only=scripts&raw=1&skin=vector-2022"></script> <meta name="ResourceLoaderDynamicStyles" content=""> <link rel="stylesheet" href="/w/load.php?lang=en&modules=site.styles&only=styles&skin=vector-2022"> <meta name="generator" content="MediaWiki 1.44.0-wmf.15"> <meta name="referrer" content="origin"> <meta name="referrer" content="origin-when-cross-origin"> <meta name="robots" content="max-image-preview:standard"> <meta name="format-detection" content="telephone=no"> <meta property="og:image" content="https://upload.wikimedia.org/wikipedia/commons/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png"> <meta property="og:image:width" content="1200"> <meta property="og:image:height" content="846"> <meta property="og:image" content="https://upload.wikimedia.org/wikipedia/commons/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png"> <meta property="og:image:width" content="800"> <meta property="og:image:height" content="564"> <meta property="og:image" content="https://upload.wikimedia.org/wikipedia/commons/thumb/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png/640px-DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png"> <meta property="og:image:width" content="640"> <meta property="og:image:height" content="451"> <meta name="viewport" content="width=1120"> <meta property="og:title" content="Automatic image annotation - Wikipedia"> <meta property="og:type" content="website"> <link rel="preconnect" href="//upload.wikimedia.org"> <link rel="alternate" media="only screen and (max-width: 640px)" href="//en.m.wikipedia.org/wiki/Automatic_image_annotation"> <link rel="alternate" type="application/x-wiki" title="Edit this page" href="/w/index.php?title=Automatic_image_annotation&action=edit"> <link rel="apple-touch-icon" href="/static/apple-touch/wikipedia.png"> <link rel="icon" href="/static/favicon/wikipedia.ico"> <link rel="search" type="application/opensearchdescription+xml" href="/w/rest.php/v1/search" title="Wikipedia (en)"> <link rel="EditURI" type="application/rsd+xml" href="//en.wikipedia.org/w/api.php?action=rsd"> <link rel="canonical" href="https://en.wikipedia.org/wiki/Automatic_image_annotation"> <link rel="license" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en"> <link rel="alternate" type="application/atom+xml" title="Wikipedia Atom feed" href="/w/index.php?title=Special:RecentChanges&feed=atom"> <link rel="dns-prefetch" href="//meta.wikimedia.org" /> <link rel="dns-prefetch" href="login.wikimedia.org"> </head> <body class="skin--responsive skin-vector skin-vector-search-vue mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-subject mw-editable page-Automatic_image_annotation rootpage-Automatic_image_annotation skin-vector-2022 action-view"><a class="mw-jump-link" href="#bodyContent">Jump to content</a> <div class="vector-header-container"> <header class="vector-header mw-header"> <div class="vector-header-start"> <nav class="vector-main-menu-landmark" aria-label="Site"> <div id="vector-main-menu-dropdown" class="vector-dropdown vector-main-menu-dropdown vector-button-flush-left vector-button-flush-right" title="Main menu" > <input type="checkbox" id="vector-main-menu-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-main-menu-dropdown" class="vector-dropdown-checkbox " aria-label="Main menu" > <label id="vector-main-menu-dropdown-label" for="vector-main-menu-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-menu mw-ui-icon-wikimedia-menu"></span> <span class="vector-dropdown-label-text">Main menu</span> </label> <div class="vector-dropdown-content"> <div id="vector-main-menu-unpinned-container" class="vector-unpinned-container"> <div id="vector-main-menu" class="vector-main-menu vector-pinnable-element"> <div class="vector-pinnable-header vector-main-menu-pinnable-header vector-pinnable-header-unpinned" data-feature-name="main-menu-pinned" data-pinnable-element-id="vector-main-menu" data-pinned-container-id="vector-main-menu-pinned-container" data-unpinned-container-id="vector-main-menu-unpinned-container" > <div class="vector-pinnable-header-label">Main menu</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-main-menu.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-main-menu.unpin">hide</button> </div> <div id="p-navigation" class="vector-menu mw-portlet mw-portlet-navigation" > <div class="vector-menu-heading"> Navigation </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="n-mainpage-description" class="mw-list-item"><a href="/wiki/Main_Page" title="Visit the main page [z]" accesskey="z"><span>Main page</span></a></li><li id="n-contents" class="mw-list-item"><a href="/wiki/Wikipedia:Contents" title="Guides to browsing Wikipedia"><span>Contents</span></a></li><li id="n-currentevents" class="mw-list-item"><a href="/wiki/Portal:Current_events" title="Articles related to current events"><span>Current events</span></a></li><li id="n-randompage" class="mw-list-item"><a href="/wiki/Special:Random" title="Visit a randomly selected article [x]" accesskey="x"><span>Random article</span></a></li><li id="n-aboutsite" class="mw-list-item"><a href="/wiki/Wikipedia:About" title="Learn about Wikipedia and how it works"><span>About Wikipedia</span></a></li><li id="n-contactpage" class="mw-list-item"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us" title="How to contact Wikipedia"><span>Contact us</span></a></li> </ul> </div> </div> <div id="p-interaction" class="vector-menu mw-portlet mw-portlet-interaction" > <div class="vector-menu-heading"> Contribute </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="n-help" class="mw-list-item"><a href="/wiki/Help:Contents" title="Guidance on how to use and edit Wikipedia"><span>Help</span></a></li><li id="n-introduction" class="mw-list-item"><a href="/wiki/Help:Introduction" title="Learn how to edit Wikipedia"><span>Learn to edit</span></a></li><li id="n-portal" class="mw-list-item"><a href="/wiki/Wikipedia:Community_portal" title="The hub for editors"><span>Community portal</span></a></li><li id="n-recentchanges" class="mw-list-item"><a href="/wiki/Special:RecentChanges" title="A list of recent changes to Wikipedia [r]" accesskey="r"><span>Recent changes</span></a></li><li id="n-upload" class="mw-list-item"><a href="/wiki/Wikipedia:File_upload_wizard" title="Add images or other media for use on Wikipedia"><span>Upload file</span></a></li> </ul> </div> </div> </div> </div> </div> </div> </nav> <a href="/wiki/Main_Page" class="mw-logo"> <img class="mw-logo-icon" src="/static/images/icons/wikipedia.png" alt="" aria-hidden="true" height="50" width="50"> <span class="mw-logo-container skin-invert"> <img class="mw-logo-wordmark" alt="Wikipedia" src="/static/images/mobile/copyright/wikipedia-wordmark-en.svg" style="width: 7.5em; height: 1.125em;"> <img class="mw-logo-tagline" alt="The Free Encyclopedia" src="/static/images/mobile/copyright/wikipedia-tagline-en.svg" width="117" height="13" style="width: 7.3125em; height: 0.8125em;"> </span> </a> </div> <div class="vector-header-end"> <div id="p-search" role="search" class="vector-search-box-vue vector-search-box-collapses vector-search-box-show-thumbnail vector-search-box-auto-expand-width vector-search-box"> <a href="/wiki/Special:Search" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only search-toggle" title="Search Wikipedia [f]" accesskey="f"><span class="vector-icon mw-ui-icon-search mw-ui-icon-wikimedia-search"></span> <span>Search</span> </a> <div class="vector-typeahead-search-container"> <div class="cdx-typeahead-search cdx-typeahead-search--show-thumbnail cdx-typeahead-search--auto-expand-width"> <form action="/w/index.php" id="searchform" class="cdx-search-input cdx-search-input--has-end-button"> <div id="simpleSearch" class="cdx-search-input__input-wrapper" data-search-loc="header-moved"> <div class="cdx-text-input cdx-text-input--has-start-icon"> <input class="cdx-text-input__input" type="search" name="search" placeholder="Search Wikipedia" aria-label="Search Wikipedia" autocapitalize="sentences" title="Search Wikipedia [f]" accesskey="f" id="searchInput" > <span class="cdx-text-input__icon cdx-text-input__start-icon"></span> </div> <input type="hidden" name="title" value="Special:Search"> </div> <button class="cdx-button cdx-search-input__end-button">Search</button> </form> </div> </div> </div> <nav class="vector-user-links vector-user-links-wide" aria-label="Personal tools"> <div class="vector-user-links-main"> <div id="p-vector-user-menu-preferences" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <div id="p-vector-user-menu-userpage" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <nav class="vector-appearance-landmark" aria-label="Appearance"> <div id="vector-appearance-dropdown" class="vector-dropdown " title="Change the appearance of the page's font size, width, and color" > <input type="checkbox" id="vector-appearance-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-appearance-dropdown" class="vector-dropdown-checkbox " aria-label="Appearance" > <label id="vector-appearance-dropdown-label" for="vector-appearance-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-appearance mw-ui-icon-wikimedia-appearance"></span> <span class="vector-dropdown-label-text">Appearance</span> </label> <div class="vector-dropdown-content"> <div id="vector-appearance-unpinned-container" class="vector-unpinned-container"> </div> </div> </div> </nav> <div id="p-vector-user-menu-notifications" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <div id="p-vector-user-menu-overflow" class="vector-menu mw-portlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-sitesupport-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="https://donate.wikimedia.org/?wmf_source=donate&wmf_medium=sidebar&wmf_campaign=en.wikipedia.org&uselang=en" class=""><span>Donate</span></a> </li> <li id="pt-createaccount-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="/w/index.php?title=Special:CreateAccount&returnto=Automatic+image+annotation" title="You are encouraged to create an account and log in; however, it is not mandatory" class=""><span>Create account</span></a> </li> <li id="pt-login-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="/w/index.php?title=Special:UserLogin&returnto=Automatic+image+annotation" title="You're encouraged to log in; however, it's not mandatory. [o]" accesskey="o" class=""><span>Log in</span></a> </li> </ul> </div> </div> </div> <div id="vector-user-links-dropdown" class="vector-dropdown vector-user-menu vector-button-flush-right vector-user-menu-logged-out" title="Log in and more options" > <input type="checkbox" id="vector-user-links-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-user-links-dropdown" class="vector-dropdown-checkbox " aria-label="Personal tools" > <label id="vector-user-links-dropdown-label" for="vector-user-links-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-ellipsis mw-ui-icon-wikimedia-ellipsis"></span> <span class="vector-dropdown-label-text">Personal tools</span> </label> <div class="vector-dropdown-content"> <div id="p-personal" class="vector-menu mw-portlet mw-portlet-personal user-links-collapsible-item" title="User menu" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-sitesupport" class="user-links-collapsible-item mw-list-item"><a href="https://donate.wikimedia.org/?wmf_source=donate&wmf_medium=sidebar&wmf_campaign=en.wikipedia.org&uselang=en"><span>Donate</span></a></li><li id="pt-createaccount" class="user-links-collapsible-item mw-list-item"><a href="/w/index.php?title=Special:CreateAccount&returnto=Automatic+image+annotation" title="You are encouraged to create an account and log in; however, it is not mandatory"><span class="vector-icon mw-ui-icon-userAdd mw-ui-icon-wikimedia-userAdd"></span> <span>Create account</span></a></li><li id="pt-login" class="user-links-collapsible-item mw-list-item"><a href="/w/index.php?title=Special:UserLogin&returnto=Automatic+image+annotation" title="You're encouraged to log in; however, it's not mandatory. [o]" accesskey="o"><span class="vector-icon mw-ui-icon-logIn mw-ui-icon-wikimedia-logIn"></span> <span>Log in</span></a></li> </ul> </div> </div> <div id="p-user-menu-anon-editor" class="vector-menu mw-portlet mw-portlet-user-menu-anon-editor" > <div class="vector-menu-heading"> Pages for logged out editors <a href="/wiki/Help:Introduction" aria-label="Learn more about editing"><span>learn more</span></a> </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-anoncontribs" class="mw-list-item"><a href="/wiki/Special:MyContributions" title="A list of edits made from this IP address [y]" accesskey="y"><span>Contributions</span></a></li><li id="pt-anontalk" class="mw-list-item"><a href="/wiki/Special:MyTalk" title="Discussion about edits from this IP address [n]" accesskey="n"><span>Talk</span></a></li> </ul> </div> </div> </div> </div> </nav> </div> </header> </div> <div class="mw-page-container"> <div class="mw-page-container-inner"> <div class="vector-sitenotice-container"> <div id="siteNotice"></div> </div> <div class="vector-column-start"> <div class="vector-main-menu-container"> <div id="mw-navigation"> <nav id="mw-panel" class="vector-main-menu-landmark" aria-label="Site"> <div id="vector-main-menu-pinned-container" class="vector-pinned-container"> </div> </nav> </div> </div> <div class="vector-sticky-pinned-container"> <nav id="mw-panel-toc" aria-label="Contents" data-event-name="ui.sidebar-toc" class="mw-table-of-contents-container vector-toc-landmark"> <div id="vector-toc-pinned-container" class="vector-pinned-container"> <div id="vector-toc" class="vector-toc vector-pinnable-element"> <div class="vector-pinnable-header vector-toc-pinnable-header vector-pinnable-header-pinned" data-feature-name="toc-pinned" data-pinnable-element-id="vector-toc" > <h2 class="vector-pinnable-header-label">Contents</h2> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-toc.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-toc.unpin">hide</button> </div> <ul class="vector-toc-contents" id="mw-panel-toc-list"> <li id="toc-mw-content-text" class="vector-toc-list-item vector-toc-level-1"> <a href="#" class="vector-toc-link"> <div class="vector-toc-text">(Top)</div> </a> </li> <li id="toc-See_also" class="vector-toc-list-item vector-toc-level-1 vector-toc-list-item-expanded"> <a class="vector-toc-link" href="#See_also"> <div class="vector-toc-text"> <span class="vector-toc-numb">1</span> <span>See also</span> </div> </a> <ul id="toc-See_also-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-References" class="vector-toc-list-item vector-toc-level-1 vector-toc-list-item-expanded"> <a class="vector-toc-link" href="#References"> <div class="vector-toc-text"> <span class="vector-toc-numb">2</span> <span>References</span> </div> </a> <ul id="toc-References-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Further_reading" class="vector-toc-list-item vector-toc-level-1 vector-toc-list-item-expanded"> <a class="vector-toc-link" href="#Further_reading"> <div class="vector-toc-text"> <span class="vector-toc-numb">3</span> <span>Further reading</span> </div> </a> <ul id="toc-Further_reading-sublist" class="vector-toc-list"> </ul> </li> </ul> </div> </div> </nav> </div> </div> <div class="mw-content-container"> <main id="content" class="mw-body"> <header class="mw-body-header vector-page-titlebar"> <nav aria-label="Contents" class="vector-toc-landmark"> <div id="vector-page-titlebar-toc" class="vector-dropdown vector-page-titlebar-toc vector-button-flush-left" title="Table of Contents" > <input type="checkbox" id="vector-page-titlebar-toc-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-page-titlebar-toc" class="vector-dropdown-checkbox " aria-label="Toggle the table of contents" > <label id="vector-page-titlebar-toc-label" for="vector-page-titlebar-toc-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-listBullet mw-ui-icon-wikimedia-listBullet"></span> <span class="vector-dropdown-label-text">Toggle the table of contents</span> </label> <div class="vector-dropdown-content"> <div id="vector-page-titlebar-toc-unpinned-container" class="vector-unpinned-container"> </div> </div> </div> </nav> <h1 id="firstHeading" class="firstHeading mw-first-heading"><span class="mw-page-title-main">Automatic image annotation</span></h1> <div id="p-lang-btn" class="vector-dropdown mw-portlet mw-portlet-lang" > <input type="checkbox" id="p-lang-btn-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-p-lang-btn" class="vector-dropdown-checkbox mw-interlanguage-selector" aria-label="Go to an article in another language. Available in 5 languages" > <label id="p-lang-btn-label" for="p-lang-btn-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--action-progressive mw-portlet-lang-heading-5" aria-hidden="true" ><span class="vector-icon mw-ui-icon-language-progressive mw-ui-icon-wikimedia-language-progressive"></span> <span class="vector-dropdown-label-text">5 languages</span> </label> <div class="vector-dropdown-content"> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li class="interlanguage-link interwiki-fa mw-list-item"><a href="https://fa.wikipedia.org/wiki/%D8%AD%D8%A7%D8%B4%DB%8C%D9%87%E2%80%8C%D9%86%D9%88%DB%8C%D8%B3%DB%8C_%D8%AE%D9%88%D8%AF%DA%A9%D8%A7%D8%B1_%D8%AA%D8%B5%D8%A7%D9%88%DB%8C%D8%B1" title="حاشیه‌نویسی خودکار تصاویر – Persian" lang="fa" hreflang="fa" data-title="حاشیه‌نویسی خودکار تصاویر" data-language-autonym="فارسی" data-language-local-name="Persian" class="interlanguage-link-target"><span>فارسی</span></a></li><li class="interlanguage-link interwiki-fr mw-list-item"><a href="https://fr.wikipedia.org/wiki/Annotation_automatique_d%27images" title="Annotation automatique d'images – French" lang="fr" hreflang="fr" data-title="Annotation automatique d'images" data-language-autonym="Français" data-language-local-name="French" class="interlanguage-link-target"><span>Français</span></a></li><li class="interlanguage-link interwiki-ru mw-list-item"><a href="https://ru.wikipedia.org/wiki/%D0%90%D0%B2%D1%82%D0%BE%D0%BC%D0%B0%D1%82%D0%B8%D1%87%D0%B5%D1%81%D0%BA%D0%B0%D1%8F_%D0%B0%D0%BD%D0%BD%D0%BE%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%B8%D0%B7%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F" title="Автоматическая аннотация изображения – Russian" lang="ru" hreflang="ru" data-title="Автоматическая аннотация изображения" data-language-autonym="Русский" data-language-local-name="Russian" class="interlanguage-link-target"><span>Русский</span></a></li><li class="interlanguage-link interwiki-sr mw-list-item"><a href="https://sr.wikipedia.org/wiki/Automatsko_ozna%C4%8Davanje_slika" title="Automatsko označavanje slika – Serbian" lang="sr" hreflang="sr" data-title="Automatsko označavanje slika" data-language-autonym="Српски / srpski" data-language-local-name="Serbian" class="interlanguage-link-target"><span>Српски / srpski</span></a></li><li class="interlanguage-link interwiki-zh mw-list-item"><a href="https://zh.wikipedia.org/wiki/%E5%9B%BE%E5%83%8F%E8%87%AA%E5%8A%A8%E6%A0%87%E6%B3%A8" title="图像自动标注 – Chinese" lang="zh" hreflang="zh" data-title="图像自动标注" data-language-autonym="中文" data-language-local-name="Chinese" class="interlanguage-link-target"><span>中文</span></a></li> </ul> <div class="after-portlet after-portlet-lang"><span class="wb-langlinks-edit wb-langlinks-link"><a href="https://www.wikidata.org/wiki/Special:EntityPage/Q2851778#sitelinks-wikipedia" title="Edit interlanguage links" class="wbc-editpage">Edit links</a></span></div> </div> </div> </div> </header> <div class="vector-page-toolbar"> <div class="vector-page-toolbar-container"> <div id="left-navigation"> <nav aria-label="Namespaces"> <div id="p-associated-pages" class="vector-menu vector-menu-tabs mw-portlet mw-portlet-associated-pages" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-nstab-main" class="selected vector-tab-noicon mw-list-item"><a href="/wiki/Automatic_image_annotation" title="View the content page [c]" accesskey="c"><span>Article</span></a></li><li id="ca-talk" class="vector-tab-noicon mw-list-item"><a href="/wiki/Talk:Automatic_image_annotation" rel="discussion" title="Discuss improvements to the content page [t]" accesskey="t"><span>Talk</span></a></li> </ul> </div> </div> <div id="vector-variants-dropdown" class="vector-dropdown emptyPortlet" > <input type="checkbox" id="vector-variants-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-variants-dropdown" class="vector-dropdown-checkbox " aria-label="Change language variant" > <label id="vector-variants-dropdown-label" for="vector-variants-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet" aria-hidden="true" ><span class="vector-dropdown-label-text">English</span> </label> <div class="vector-dropdown-content"> <div id="p-variants" class="vector-menu mw-portlet mw-portlet-variants emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> </div> </div> </nav> </div> <div id="right-navigation" class="vector-collapsible"> <nav aria-label="Views"> <div id="p-views" class="vector-menu vector-menu-tabs mw-portlet mw-portlet-views" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-view" class="selected vector-tab-noicon mw-list-item"><a href="/wiki/Automatic_image_annotation"><span>Read</span></a></li><li id="ca-edit" class="vector-tab-noicon mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&action=edit" title="Edit this page [e]" accesskey="e"><span>Edit</span></a></li><li id="ca-history" class="vector-tab-noicon mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&action=history" title="Past revisions of this page [h]" accesskey="h"><span>View history</span></a></li> </ul> </div> </div> </nav> <nav class="vector-page-tools-landmark" aria-label="Page tools"> <div id="vector-page-tools-dropdown" class="vector-dropdown vector-page-tools-dropdown" > <input type="checkbox" id="vector-page-tools-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-page-tools-dropdown" class="vector-dropdown-checkbox " aria-label="Tools" > <label id="vector-page-tools-dropdown-label" for="vector-page-tools-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet" aria-hidden="true" ><span class="vector-dropdown-label-text">Tools</span> </label> <div class="vector-dropdown-content"> <div id="vector-page-tools-unpinned-container" class="vector-unpinned-container"> <div id="vector-page-tools" class="vector-page-tools vector-pinnable-element"> <div class="vector-pinnable-header vector-page-tools-pinnable-header vector-pinnable-header-unpinned" data-feature-name="page-tools-pinned" data-pinnable-element-id="vector-page-tools" data-pinned-container-id="vector-page-tools-pinned-container" data-unpinned-container-id="vector-page-tools-unpinned-container" > <div class="vector-pinnable-header-label">Tools</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-page-tools.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-page-tools.unpin">hide</button> </div> <div id="p-cactions" class="vector-menu mw-portlet mw-portlet-cactions emptyPortlet vector-has-collapsible-items" title="More options" > <div class="vector-menu-heading"> Actions </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-more-view" class="selected vector-more-collapsible-item mw-list-item"><a href="/wiki/Automatic_image_annotation"><span>Read</span></a></li><li id="ca-more-edit" class="vector-more-collapsible-item mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&action=edit" title="Edit this page [e]" accesskey="e"><span>Edit</span></a></li><li id="ca-more-history" class="vector-more-collapsible-item mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&action=history"><span>View history</span></a></li> </ul> </div> </div> <div id="p-tb" class="vector-menu mw-portlet mw-portlet-tb" > <div class="vector-menu-heading"> General </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="t-whatlinkshere" class="mw-list-item"><a href="/wiki/Special:WhatLinksHere/Automatic_image_annotation" title="List of all English Wikipedia pages containing links to this page [j]" accesskey="j"><span>What links here</span></a></li><li id="t-recentchangeslinked" class="mw-list-item"><a href="/wiki/Special:RecentChangesLinked/Automatic_image_annotation" rel="nofollow" title="Recent changes in pages linked from this page [k]" accesskey="k"><span>Related changes</span></a></li><li id="t-upload" class="mw-list-item"><a href="//en.wikipedia.org/wiki/Wikipedia:File_Upload_Wizard" title="Upload files [u]" accesskey="u"><span>Upload file</span></a></li><li id="t-specialpages" class="mw-list-item"><a href="/wiki/Special:SpecialPages" title="A list of all special pages [q]" accesskey="q"><span>Special pages</span></a></li><li id="t-permalink" class="mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&oldid=1275066243" title="Permanent link to this revision of this page"><span>Permanent link</span></a></li><li id="t-info" class="mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&action=info" title="More information about this page"><span>Page information</span></a></li><li id="t-cite" class="mw-list-item"><a href="/w/index.php?title=Special:CiteThisPage&page=Automatic_image_annotation&id=1275066243&wpFormIdentifier=titleform" title="Information on how to cite this page"><span>Cite this page</span></a></li><li id="t-urlshortener" class="mw-list-item"><a href="/w/index.php?title=Special:UrlShortener&url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FAutomatic_image_annotation"><span>Get shortened URL</span></a></li><li id="t-urlshortener-qrcode" class="mw-list-item"><a href="/w/index.php?title=Special:QrCode&url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FAutomatic_image_annotation"><span>Download QR code</span></a></li> </ul> </div> </div> <div id="p-coll-print_export" class="vector-menu mw-portlet mw-portlet-coll-print_export" > <div class="vector-menu-heading"> Print/export </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="coll-download-as-rl" class="mw-list-item"><a href="/w/index.php?title=Special:DownloadAsPdf&page=Automatic_image_annotation&action=show-download-screen" title="Download this page as a PDF file"><span>Download as PDF</span></a></li><li id="t-print" class="mw-list-item"><a href="/w/index.php?title=Automatic_image_annotation&printable=yes" title="Printable version of this page [p]" accesskey="p"><span>Printable version</span></a></li> </ul> </div> </div> <div id="p-wikibase-otherprojects" class="vector-menu mw-portlet mw-portlet-wikibase-otherprojects" > <div class="vector-menu-heading"> In other projects </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="t-wikibase" class="wb-otherproject-link wb-otherproject-wikibase-dataitem mw-list-item"><a href="https://www.wikidata.org/wiki/Special:EntityPage/Q2851778" title="Structured data on this page hosted by Wikidata [g]" accesskey="g"><span>Wikidata item</span></a></li> </ul> </div> </div> </div> </div> </div> </div> </nav> </div> </div> </div> <div class="vector-column-end"> <div class="vector-sticky-pinned-container"> <nav class="vector-page-tools-landmark" aria-label="Page tools"> <div id="vector-page-tools-pinned-container" class="vector-pinned-container"> </div> </nav> <nav class="vector-appearance-landmark" aria-label="Appearance"> <div id="vector-appearance-pinned-container" class="vector-pinned-container"> <div id="vector-appearance" class="vector-appearance vector-pinnable-element"> <div class="vector-pinnable-header vector-appearance-pinnable-header vector-pinnable-header-pinned" data-feature-name="appearance-pinned" data-pinnable-element-id="vector-appearance" data-pinned-container-id="vector-appearance-pinned-container" data-unpinned-container-id="vector-appearance-unpinned-container" > <div class="vector-pinnable-header-label">Appearance</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-appearance.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-appearance.unpin">hide</button> </div> </div> </div> </nav> </div> </div> <div id="bodyContent" class="vector-body" aria-labelledby="firstHeading" data-mw-ve-target-container> <div class="vector-body-before-content"> <div class="mw-indicators"> </div> <div id="siteSub" class="noprint">From Wikipedia, the free encyclopedia</div> </div> <div id="contentSub"><div id="mw-content-subtitle"></div></div> <div id="mw-content-text" class="mw-body-content"><div class="mw-content-ltr mw-parser-output" lang="en" dir="ltr"><figure class="mw-default-size" typeof="mw:File/Thumb"><a href="/wiki/File:DenseCap_(Johnson_et_al.,_2016)_(cropped).png" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png/300px-DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png" decoding="async" width="300" height="212" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png/450px-DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/a/ae/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png/600px-DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png 2x" data-file-width="702" data-file-height="495" /></a><figcaption>Output of DenseCap "dense captioning" software, analysing a photograph of a man riding an elephant</figcaption></figure> <p><b>Automatic image annotation</b> (also known as <b>automatic image tagging</b> or <b>linguistic indexing</b>) is the process by which a computer system automatically assigns <a href="/wiki/Metadata" title="Metadata">metadata</a> in the form of <a href="/wiki/Photo_caption" title="Photo caption">captioning</a> or <a href="/wiki/Index_term" title="Index term">keywords</a> to a <a href="/wiki/Digital_image" title="Digital image">digital image</a>. This application of <a href="/wiki/Computer_vision" title="Computer vision">computer vision</a> techniques is used in <a href="/wiki/Image_retrieval" title="Image retrieval">image retrieval</a> systems to organize and locate images of interest from a <a href="/wiki/Database" title="Database">database</a>. </p><p>This method can be regarded as a type of <a href="/wiki/Multiclass_classification" title="Multiclass classification">multi-class</a> <a href="/wiki/Image_recognition" class="mw-redirect" title="Image recognition">image classification</a> with a very large number of classes - as large as the vocabulary size. Typically, <a href="/wiki/Image_analysis" title="Image analysis">image analysis</a> in the form of extracted <a href="/wiki/Feature_vector" class="mw-redirect" title="Feature vector">feature vectors</a> and the training annotation words are used by <a href="/wiki/Machine_learning" title="Machine learning">machine learning</a> techniques to attempt to automatically apply annotations to new images.<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup> The first methods learned the correlations between <a href="/wiki/Feature_(computer_vision)" title="Feature (computer vision)">image features</a> and training annotations. Subsequently, techniques were developed using <a href="/wiki/Machine_translation" title="Machine translation">machine translation</a> to to attempt to translate the textual vocabulary into the 'visual vocabulary,' represented by clustered regions known as <i>blobs.</i> Subsequent work has included classification approaches, relevance models, and other related methods. </p><p>The advantages of automatic image annotation versus <a href="/wiki/Content-based_image_retrieval" title="Content-based image retrieval">content-based image retrieval</a> (CBIR) are that queries can be more naturally specified by the user.<sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup> At present, Content-Based Image Retrieval (CBIR) generally requires users to search by image concepts such as color and <a href="/wiki/Texture_(visual_arts)" title="Texture (visual arts)">texture</a> or by finding example queries. However, certain image features in example images may override the concept that the user is truly focusing on. Traditional methods of image retrieval, such as those used by libraries, have relied on manually annotated images, which is expensive and time-consuming, especially given the large and constantly growing image databases in existence. </p> <div class="mw-heading mw-heading2"><h2 id="See_also">See also</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Automatic_image_annotation&action=edit&section=1" title="Edit section: See also"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <ul><li><a href="/wiki/Content-based_image_retrieval" title="Content-based image retrieval">Content-based image retrieval</a></li> <li><a href="/wiki/Object_categorization_from_image_search" title="Object categorization from image search">Object categorization from image search</a></li> <li><a href="/wiki/Object_detection" title="Object detection">Object detection</a></li> <li><a href="/wiki/Outline_of_object_recognition" title="Outline of object recognition">Outline of object recognition</a></li></ul> <div class="mw-heading mw-heading2"><h2 id="References">References</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Automatic_image_annotation&action=edit&section=2" title="Edit section: References"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1239543626">.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}</style><div class="reflist"> <div class="mw-references-wrap"><ol class="references"> <li id="cite_note-1"><span class="mw-cite-backlink"><b><a href="#cite_ref-1">^</a></b></span> <span class="reference-text"><style data-mw-deduplicate="TemplateStyles:r1238218222">.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("//upload.wikimedia.org/wikipedia/commons/6/65/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("//upload.wikimedia.org/wikipedia/commons/d/d6/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("//upload.wikimedia.org/wikipedia/commons/a/aa/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("//upload.wikimedia.org/wikipedia/commons/4/4c/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}</style><cite id="CITEREFBarratTabbone2010" class="citation journal cs1">Barrat, Sabine; Tabbone, Salvatore (2010-05-01). <a rel="nofollow" class="external text" href="https://www.sciencedirect.com/science/article/abs/pii/S1047320310000301">"Modeling, classifying and annotating weakly annotated images using Bayesian network"</a>. <i>Journal of Visual Communication and Image Representation</i>. <b>21</b> (4): <span class="nowrap">355–</span>363. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.jvcir.2010.02.010">10.1016/j.jvcir.2010.02.010</a>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1047-3203">1047-3203</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Journal+of+Visual+Communication+and+Image+Representation&rft.atitle=Modeling%2C+classifying+and+annotating+weakly+annotated+images+using+Bayesian+network&rft.volume=21&rft.issue=4&rft.pages=%3Cspan+class%3D%22nowrap%22%3E355-%3C%2Fspan%3E363&rft.date=2010-05-01&rft_id=info%3Adoi%2F10.1016%2Fj.jvcir.2010.02.010&rft.issn=1047-3203&rft.aulast=Barrat&rft.aufirst=Sabine&rft.au=Tabbone%2C+Salvatore&rft_id=https%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fabs%2Fpii%2FS1047320310000301&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></span> </li> <li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20140808134447/http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf">"Archived copy"</a> <span class="cs1-format">(PDF)</span>. <i>i.yz.yamagata-u.ac.jp</i>. Archived from <a rel="nofollow" class="external text" href="http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 8 August 2014<span class="reference-accessdate">. Retrieved <span class="nowrap">13 January</span> 2022</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=i.yz.yamagata-u.ac.jp&rft.atitle=Archived+copy&rft_id=http%3A%2F%2Fi.yz.yamagata-u.ac.jp%2Fpaper%2Finoue04irix.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span><span class="cs1-maint citation-comment"><code class="cs1-code">{{<a href="/wiki/Template:Cite_web" title="Template:Cite web">cite web</a>}}</code>: CS1 maint: archived copy as title (<a href="/wiki/Category:CS1_maint:_archived_copy_as_title" title="Category:CS1 maint: archived copy as title">link</a>)</span></span> </li> </ol></div></div> <ul><li><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFDattaDhiraj_JoshiJia_LiJames_Z._Wang2008" class="citation journal cs1">Datta, Ritendra; Dhiraj Joshi; <a href="/wiki/Jia_Li" title="Jia Li">Jia Li</a>; James Z. Wang (2008). <a rel="nofollow" class="external text" href="http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/">"Image Retrieval: Ideas, Influences, and Trends of the New Age"</a>. <i>ACM Computing Surveys</i>. <b>40</b> (2): <span class="nowrap">1–</span>60. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1145%2F1348246.1348248">10.1145/1348246.1348248</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:7060187">7060187</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=ACM+Computing+Surveys&rft.atitle=Image+Retrieval%3A+Ideas%2C+Influences%2C+and+Trends+of+the+New+Age&rft.volume=40&rft.issue=2&rft.pages=%3Cspan+class%3D%22nowrap%22%3E1-%3C%2Fspan%3E60&rft.date=2008&rft_id=info%3Adoi%2F10.1145%2F1348246.1348248&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A7060187%23id-name%3DS2CID&rft.aulast=Datta&rft.aufirst=Ritendra&rft.au=Dhiraj+Joshi&rft.au=Jia+Li&rft.au=James+Z.+Wang&rft_id=http%3A%2F%2Finfolab.stanford.edu%2F~wangz%2Fproject%2Fimsearch%2Freview%2FJOUR%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></li> <li><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFNicolas_HervéNozha_Boujemaa2007" class="citation conference cs1">Nicolas Hervé; Nozha Boujemaa (2007). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20110520140240/http://www-rocq.inria.fr/~nherve/nherve_civr2007.pdf">"Image annotation : which approach for realistic databases ?"</a> <span class="cs1-format">(PDF)</span>. <i>ACM International Conference on Image and Video Retrieval</i>. Archived from <a rel="nofollow" class="external text" href="http://www-rocq.inria.fr/~nherve/nherve_civr2007.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2011-05-20.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Image+annotation+%3A+which+approach+for+realistic+databases+%3F&rft.btitle=ACM+International+Conference+on+Image+and+Video+Retrieval&rft.date=2007&rft.au=Nicolas+Herv%C3%A9&rft.au=Nozha+Boujemaa&rft_id=http%3A%2F%2Fwww-rocq.inria.fr%2F~nherve%2Fnherve_civr2007.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></li> <li><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFM_Inoue2004" class="citation conference cs1">M Inoue (2004). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20140808134447/http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf">"On the need for annotation-based image retrieval"</a> <span class="cs1-format">(PDF)</span>. <i>Workshop on Information Retrieval in Context</i>. pp. <span class="nowrap">44–</span>46. Archived from <a rel="nofollow" class="external text" href="http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2014-08-08.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=On+the+need+for+annotation-based+image+retrieval&rft.btitle=Workshop+on+Information+Retrieval+in+Context&rft.pages=%3Cspan+class%3D%22nowrap%22%3E44-%3C%2Fspan%3E46&rft.date=2004&rft.au=M+Inoue&rft_id=http%3A%2F%2Fi.yz.yamagata-u.ac.jp%2Fpaper%2Finoue04irix.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></li></ul> <div class="mw-heading mw-heading2"><h2 id="Further_reading">Further reading</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Automatic_image_annotation&action=edit&section=3" title="Edit section: Further reading"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1251242444">.mw-parser-output .ambox{border:1px solid #a2a9b1;border-left:10px solid #36c;background-color:#fbfbfb;box-sizing:border-box}.mw-parser-output .ambox+link+.ambox,.mw-parser-output .ambox+link+style+.ambox,.mw-parser-output .ambox+link+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+style+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+link+.ambox{margin-top:-1px}html body.mediawiki .mw-parser-output .ambox.mbox-small-left{margin:4px 1em 4px 0;overflow:hidden;width:238px;border-collapse:collapse;font-size:88%;line-height:1.25em}.mw-parser-output .ambox-speedy{border-left:10px solid #b32424;background-color:#fee7e6}.mw-parser-output .ambox-delete{border-left:10px solid #b32424}.mw-parser-output .ambox-content{border-left:10px solid #f28500}.mw-parser-output .ambox-style{border-left:10px solid #fc3}.mw-parser-output .ambox-move{border-left:10px solid #9932cc}.mw-parser-output .ambox-protection{border-left:10px solid #a2a9b1}.mw-parser-output .ambox .mbox-text{border:none;padding:0.25em 0.5em;width:100%}.mw-parser-output .ambox .mbox-image{border:none;padding:2px 0 2px 0.5em;text-align:center}.mw-parser-output .ambox .mbox-imageright{border:none;padding:2px 0.5em 2px 0;text-align:center}.mw-parser-output .ambox .mbox-empty-cell{border:none;padding:0;width:1px}.mw-parser-output .ambox .mbox-image-div{width:52px}@media(min-width:720px){.mw-parser-output .ambox{margin:0 10%}}@media print{body.ns-0 .mw-parser-output .ambox{display:none!important}}</style><table class="box-Cleanup plainlinks metadata ambox ambox-style ambox-Cleanup" role="presentation"><tbody><tr><td class="mbox-image"><div class="mbox-image-div"><span typeof="mw:File"><span><img alt="" src="//upload.wikimedia.org/wikipedia/en/thumb/f/f2/Edit-clear.svg/40px-Edit-clear.svg.png" decoding="async" width="40" height="40" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/en/thumb/f/f2/Edit-clear.svg/60px-Edit-clear.svg.png 1.5x, //upload.wikimedia.org/wikipedia/en/thumb/f/f2/Edit-clear.svg/80px-Edit-clear.svg.png 2x" data-file-width="48" data-file-height="48" /></span></span></div></td><td class="mbox-text"><div class="mbox-text-span">This section may <b>require <a href="/wiki/Wikipedia:Cleanup" title="Wikipedia:Cleanup">cleanup</a></b> to meet Wikipedia's <a href="/wiki/Wikipedia:Manual_of_Style" title="Wikipedia:Manual of Style">quality standards</a>. The specific problem is: <b>long and multiline format.</b><span class="hide-when-compact"> Please help <a href="/wiki/Special:EditPage/Automatic_image_annotation" title="Special:EditPage/Automatic image annotation">improve this section</a> if you can.</span> <span class="date-container"><i>(<span class="date">November 2022</span>)</i></span><span class="hide-when-compact"><i> (<small><a href="/wiki/Help:Maintenance_template_removal" title="Help:Maintenance template removal">Learn how and when to remove this message</a></small>)</i></span></div></td></tr></tbody></table> <ul><li>Word co-occurrence model</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFY_MoriH_TakahashiR_Oka1999" class="citation conference cs1">Y Mori; H Takahashi & R Oka (1999). "Image-to-word transformation based on dividing and vector quantizing images with words.". <i>Proceedings of the International Workshop on Multimedia Intelligent Storage and Retrieval Management</i>. <a href="/wiki/CiteSeerX_(identifier)" class="mw-redirect" title="CiteSeerX (identifier)">CiteSeerX</a> <span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.1704">10.1.1.31.1704</a></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Image-to-word+transformation+based+on+dividing+and+vector+quantizing+images+with+words.&rft.btitle=Proceedings+of+the+International+Workshop+on+Multimedia+Intelligent+Storage+and+Retrieval+Management&rft.date=1999&rft_id=https%3A%2F%2Fciteseerx.ist.psu.edu%2Fviewdoc%2Fsummary%3Fdoi%3D10.1.1.31.1704%23id-name%3DCiteSeerX&rft.au=Y+Mori&rft.au=H+Takahashi&rft.au=R+Oka&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Annotation as machine translation</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFP_DuyguluK_BarnardN_de_FretiasD_Forsyth2002" class="citation conference cs1">P Duygulu; K Barnard; N de Fretias & D Forsyth (2002). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20050305174408/http://vision.cs.arizona.edu/kobus/research/publications/ECCV-02-1/">"Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary"</a>. <i>Proceedings of the European Conference on Computer Vision</i>. pp. <span class="nowrap">97–</span>112. Archived from <a rel="nofollow" class="external text" href="http://vision.cs.arizona.edu/kobus/research/publications/ECCV-02-1/">the original</a> on 2005-03-05.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Object+recognition+as+machine+translation%3A+Learning+a+lexicon+for+a+fixed+image+vocabulary&rft.btitle=Proceedings+of+the+European+Conference+on+Computer+Vision&rft.pages=%3Cspan+class%3D%22nowrap%22%3E97-%3C%2Fspan%3E112&rft.date=2002&rft.au=P+Duygulu&rft.au=K+Barnard&rft.au=N+de+Fretias&rft.au=D+Forsyth&rft_id=http%3A%2F%2Fvision.cs.arizona.edu%2Fkobus%2Fresearch%2Fpublications%2FECCV-02-1%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Statistical models</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_LiJ_Z_Wang2006" class="citation conference cs1">J Li & J Z Wang (2006). <a rel="nofollow" class="external text" href="http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/ACMMM06/">"Real-time Computerized Annotation of Pictures"</a>. <i>Proc. ACM Multimedia</i>. pp. <span class="nowrap">911–</span>920.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Real-time+Computerized+Annotation+of+Pictures&rft.btitle=Proc.+ACM+Multimedia&rft.pages=%3Cspan+class%3D%22nowrap%22%3E911-%3C%2Fspan%3E920&rft.date=2006&rft.au=J+Li&rft.au=J+Z+Wang&rft_id=http%3A%2F%2Fwww-db.stanford.edu%2F~wangz%2Fproject%2Fimsearch%2FALIP%2FACMMM06%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_Z_WangJ_Li2002" class="citation conference cs1">J Z Wang & J Li (2002). <a rel="nofollow" class="external text" href="http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/ACM02/">"Learning-Based Linguistic Indexing of Pictures with 2-D MHMMs"</a>. <i>Proc. ACM Multimedia</i>. pp. <span class="nowrap">436–</span>445.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Learning-Based+Linguistic+Indexing+of+Pictures+with+2-D+MHMMs&rft.btitle=Proc.+ACM+Multimedia&rft.pages=%3Cspan+class%3D%22nowrap%22%3E436-%3C%2Fspan%3E445&rft.date=2002&rft.au=J+Z+Wang&rft.au=J+Li&rft_id=http%3A%2F%2Fwww-db.stanford.edu%2F~wangz%2Fproject%2Fimsearch%2FALIP%2FACM02%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Automatic linguistic indexing of pictures</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_LiJ_Z_Wang2008" class="citation conference cs1">J Li & J Z Wang (2008). <a rel="nofollow" class="external text" href="http://infolab.stanford.edu/~wangz/project/imsearch/ALIP/PAMI08/">"Real-time Computerized Annotation of Pictures"</a>. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Real-time+Computerized+Annotation+of+Pictures&rft.btitle=IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence&rft.date=2008&rft.au=J+Li&rft.au=J+Z+Wang&rft_id=http%3A%2F%2Finfolab.stanford.edu%2F~wangz%2Fproject%2Fimsearch%2FALIP%2FPAMI08%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_LiJ_Z_Wang2003" class="citation conference cs1">J Li & J Z Wang (2003). <a rel="nofollow" class="external text" href="http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/PAMI03/">"Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach"</a>. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. pp. <span class="nowrap">1075–</span>1088.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+Linguistic+Indexing+of+Pictures+by+a+Statistical+Modeling+Approach&rft.btitle=IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence&rft.pages=%3Cspan+class%3D%22nowrap%22%3E1075-%3C%2Fspan%3E1088&rft.date=2003&rft.au=J+Li&rft.au=J+Z+Wang&rft_id=http%3A%2F%2Fwww-db.stanford.edu%2F~wangz%2Fproject%2Fimsearch%2FALIP%2FPAMI03%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Hierarchical Aspect Cluster Model</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFK_BarnardD_A_Forsyth2001" class="citation conference cs1">K Barnard; D A Forsyth (2001). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20070928161148/http://kobus.ca/research/publications/ICCV-01/">"Learning the Semantics of Words and Pictures"</a>. <i>Proceedings of International Conference on Computer Vision</i>. pp. <span class="nowrap">408–</span>415. Archived from <a rel="nofollow" class="external text" href="http://kobus.ca/research/publications/ICCV-01/">the original</a> on 2007-09-28.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Learning+the+Semantics+of+Words+and+Pictures&rft.btitle=Proceedings+of+International+Conference+on+Computer+Vision&rft.pages=%3Cspan+class%3D%22nowrap%22%3E408-%3C%2Fspan%3E415&rft.date=2001&rft.au=K+Barnard&rft.au=D+A+Forsyth&rft_id=http%3A%2F%2Fkobus.ca%2Fresearch%2Fpublications%2FICCV-01%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Latent Dirichlet Allocation model</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFD_BleiA_NgM_Jordan2003" class="citation conference cs1">D Blei; A Ng & M Jordan (2003). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20050316213517/http://www.ics.uci.edu/~liang/seminars/win05/papers/blei03-latent-dirichlet.pdf">"Latent Dirichlet allocation"</a> <span class="cs1-format">(PDF)</span>. <i>Journal of Machine Learning Research</i>. pp. 3:993–1022. Archived from <a rel="nofollow" class="external text" href="http://www.ics.uci.edu/~liang/seminars/win05/papers/blei03-latent-dirichlet.pdf">the original</a> <span class="cs1-format">(PDF)</span> on March 16, 2005.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Latent+Dirichlet+allocation&rft.btitle=Journal+of+Machine+Learning+Research&rft.pages=3%3A993-1022&rft.date=2003&rft.au=D+Blei&rft.au=A+Ng&rft.au=M+Jordan&rft_id=http%3A%2F%2Fwww.ics.uci.edu%2F~liang%2Fseminars%2Fwin05%2Fpapers%2Fblei03-latent-dirichlet.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li><a href="/wiki/Supervised_learning" title="Supervised learning">Supervised</a> <a href="/wiki/Multiclass_labeling" class="mw-redirect" title="Multiclass labeling">multiclass labeling</a></li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFG_CarneiroA_B_ChanP_MorenoN_Vasconcelos2006" class="citation conference cs1">G Carneiro; A B Chan; P Moreno & N Vasconcelos (2006). <a rel="nofollow" class="external text" href="http://www.svcl.ucsd.edu/publications/journal/2007/pami/pami07-semantics.pdf">"Supervised Learning of Semantic Classes for Image Annotation and Retrieval"</a> <span class="cs1-format">(PDF)</span>. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. pp. <span class="nowrap">394–</span>410.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Supervised+Learning+of+Semantic+Classes+for+Image+Annotation+and+Retrieval&rft.btitle=IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence&rft.pages=%3Cspan+class%3D%22nowrap%22%3E394-%3C%2Fspan%3E410&rft.date=2006&rft.au=G+Carneiro&rft.au=A+B+Chan&rft.au=P+Moreno&rft.au=N+Vasconcelos&rft_id=http%3A%2F%2Fwww.svcl.ucsd.edu%2Fpublications%2Fjournal%2F2007%2Fpami%2Fpami07-semantics.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Texture similarity</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFR_W_PicardT_P_Minka1995" class="citation conference cs1">R W Picard & T P Minka (1995). <a rel="nofollow" class="external text" href="http://citeseer.ist.psu.edu/picard95vision.html">"Vision Texture for Annotation"</a>. <i>Multimedia Systems</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Vision+Texture+for+Annotation&rft.btitle=Multimedia+Systems&rft.date=1995&rft.au=R+W+Picard&rft.au=T+P+Minka&rft_id=http%3A%2F%2Fciteseer.ist.psu.edu%2Fpicard95vision.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Support Vector Machines</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFC_CusanoG_CioccaR_Scettini2004" class="citation journal cs1">C Cusano; G Ciocca & R Scettini (2004). Santini, Simone & Schettini, Raimondo (eds.). "Image Annotation Using SVM". <i>Internet Imaging V</i>. <b>5304</b>: <span class="nowrap">330–</span>338. <a href="/wiki/Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/2003SPIE.5304..330C">2003SPIE.5304..330C</a>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1117%2F12.526746">10.1117/12.526746</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:16246057">16246057</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Internet+Imaging+V&rft.atitle=Image+Annotation+Using+SVM&rft.volume=5304&rft.pages=%3Cspan+class%3D%22nowrap%22%3E330-%3C%2Fspan%3E338&rft.date=2004&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A16246057%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.1117%2F12.526746&rft_id=info%3Abibcode%2F2003SPIE.5304..330C&rft.au=C+Cusano&rft.au=G+Ciocca&rft.au=R+Scettini&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Ensemble of Decision Trees and Random Subwindows</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFR_MareeP_GeurtsJ_PiaterL_Wehenkel2005" class="citation conference cs1">R Maree; P Geurts; J Piater & L Wehenkel (2005). <a rel="nofollow" class="external text" href="http://www.montefiore.ulg.ac.be/~maree/#publications">"Random Subwindows for Robust Image Classification"</a>. <i>Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition</i>. pp. 1:34–30.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Random+Subwindows+for+Robust+Image+Classification&rft.btitle=Proceedings+of+the+IEEE+International+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.pages=1%3A34-30&rft.date=2005&rft.au=R+Maree&rft.au=P+Geurts&rft.au=J+Piater&rft.au=L+Wehenkel&rft_id=http%3A%2F%2Fwww.montefiore.ulg.ac.be%2F~maree%2F%23publications&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Maximum Entropy</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_JeonR_Manmatha2004" class="citation conference cs1">J Jeon; R Manmatha (2004). <a rel="nofollow" class="external text" href="http://ciir.cs.umass.edu/pubfiles/mm-355.pdf">"Using Maximum Entropy for Automatic Image Annotation"</a> <span class="cs1-format">(PDF)</span>. <i>Int'l Conf on Image and Video Retrieval (CIVR 2004)</i>. pp. <span class="nowrap">24–</span>32.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Using+Maximum+Entropy+for+Automatic+Image+Annotation&rft.btitle=Int%27l+Conf+on+Image+and+Video+Retrieval+%28CIVR+2004%29&rft.pages=%3Cspan+class%3D%22nowrap%22%3E24-%3C%2Fspan%3E32&rft.date=2004&rft.au=J+Jeon&rft.au=R+Manmatha&rft_id=http%3A%2F%2Fciir.cs.umass.edu%2Fpubfiles%2Fmm-355.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Relevance models</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_JeonV_LavrenkoR_Manmatha2003" class="citation conference cs1">J Jeon; V Lavrenko & R Manmatha (2003). <a rel="nofollow" class="external text" href="http://ciir.cs.umass.edu/pubfiles/mm-41.pdf">"Automatic image annotation and retrieval using cross-media relevance models"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval</i>. pp. <span class="nowrap">119–</span>126.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+image+annotation+and+retrieval+using+cross-media+relevance+models&rft.btitle=Proceedings+of+the+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+Retrieval&rft.pages=%3Cspan+class%3D%22nowrap%22%3E119-%3C%2Fspan%3E126&rft.date=2003&rft.au=J+Jeon&rft.au=V+Lavrenko&rft.au=R+Manmatha&rft_id=http%3A%2F%2Fciir.cs.umass.edu%2Fpubfiles%2Fmm-41.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Relevance models using continuous probability density functions</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFV_LavrenkoR_ManmathaJ_Jeon2003" class="citation conference cs1">V Lavrenko; R Manmatha & J Jeon (2003). <a rel="nofollow" class="external text" href="http://ciir.cs.umass.edu/pubfiles/mm-46.pdf">"A model for learning the semantics of pictures"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of the 16th Conference on Advances in Neural Information Processing Systems NIPS</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=A+model+for+learning+the+semantics+of+pictures&rft.btitle=Proceedings+of+the+16th+Conference+on+Advances+in+Neural+Information+Processing+Systems+NIPS&rft.date=2003&rft.au=V+Lavrenko&rft.au=R+Manmatha&rft.au=J+Jeon&rft_id=http%3A%2F%2Fciir.cs.umass.edu%2Fpubfiles%2Fmm-46.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Coherent Language Model</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFR_JinJ_Y_ChaiL_Si2004" class="citation conference cs1">R Jin; J Y Chai; L Si (2004). <a rel="nofollow" class="external text" href="http://www.cse.msu.edu/~rongjin/publications/acmmm04.jin.pdf">"Effective Automatic Image Annotation via A Coherent Language Model and Active Learning"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of MM'04</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Effective+Automatic+Image+Annotation+via+A+Coherent+Language+Model+and+Active+Learning&rft.btitle=Proceedings+of+MM%2704&rft.date=2004&rft.au=R+Jin&rft.au=J+Y+Chai&rft.au=L+Si&rft_id=http%3A%2F%2Fwww.cse.msu.edu%2F~rongjin%2Fpublications%2Facmmm04.jin.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Inference networks</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFD_MetzlerR_Manmatha2004" class="citation conference cs1">D Metzler & R Manmatha (2004). <a rel="nofollow" class="external text" href="http://ciir.cs.umass.edu/pubfiles/mm-346.pdf">"An inference network approach to image retrieval"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of the International Conference on Image and Video Retrieval</i>. pp. <span class="nowrap">42–</span>50.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=An+inference+network+approach+to+image+retrieval&rft.btitle=Proceedings+of+the+International+Conference+on+Image+and+Video+Retrieval&rft.pages=%3Cspan+class%3D%22nowrap%22%3E42-%3C%2Fspan%3E50&rft.date=2004&rft.au=D+Metzler&rft.au=R+Manmatha&rft_id=http%3A%2F%2Fciir.cs.umass.edu%2Fpubfiles%2Fmm-346.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Multiple Bernoulli distribution</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFS_FengR_ManmathaV_Lavrenko2004" class="citation conference cs1">S Feng; R Manmatha & V Lavrenko (2004). <a rel="nofollow" class="external text" href="http://ciir.cs.umass.edu/pubfiles/mm-333.pdf">"Multiple Bernoulli relevance models for image and video annotation"</a> <span class="cs1-format">(PDF)</span>. <i>IEEE Conference on Computer Vision and Pattern Recognition</i>. pp. <span class="nowrap">1002–</span>1009.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Multiple+Bernoulli+relevance+models+for+image+and+video+annotation&rft.btitle=IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.pages=%3Cspan+class%3D%22nowrap%22%3E1002-%3C%2Fspan%3E1009&rft.date=2004&rft.au=S+Feng&rft.au=R+Manmatha&rft.au=V+Lavrenko&rft_id=http%3A%2F%2Fciir.cs.umass.edu%2Fpubfiles%2Fmm-333.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Multiple design alternatives</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_Y_PanH-J_YangP_DuyguluC_Faloutsos2004" class="citation conference cs1">J Y Pan; H-J Yang; P Duygulu; C Faloutsos (2004). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20041209191242/http://www.informedia.cs.cmu.edu/documents/ICME04AutoICap.pdf">"Automatic Image Captioning"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of the 2004 IEEE International Conference on Multimedia and Expo (ICME'04)</i>. Archived from <a rel="nofollow" class="external text" href="http://www.informedia.cs.cmu.edu/documents/ICME04AutoICap.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2004-12-09.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+Image+Captioning&rft.btitle=Proceedings+of+the+2004+IEEE+International+Conference+on+Multimedia+and+Expo+%28ICME%2704%29&rft.date=2004&rft.au=J+Y+Pan&rft.au=H-J+Yang&rft.au=P+Duygulu&rft.au=C+Faloutsos&rft_id=http%3A%2F%2Fwww.informedia.cs.cmu.edu%2Fdocuments%2FICME04AutoICap.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Image captioning</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFQuan_Hoang_LamQuang_Duy_LeKiet_Van_NguyenNgan_Luu-Thuy_Nguyen2020" class="citation conference cs1">Quan Hoang Lam; Quang Duy Le; Kiet Van Nguyen; Ngan Luu-Thuy Nguyen (2020). <a rel="nofollow" class="external text" href="https://link.springer.com/chapter/10.1007/978-3-030-63007-2_57">"UIT-ViIC: A Dataset for the First Evaluation on Vietnamese Image Captioning"</a>. <i>Proceedings of the 2020 International Conference on Computational Collective Intelligence (ICCCI 2020)</i>. <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/2002.00175">2002.00175</a></span>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-030-63007-2_57">10.1007/978-3-030-63007-2_57</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=UIT-ViIC%3A+A+Dataset+for+the+First+Evaluation+on+Vietnamese+Image+Captioning&rft.btitle=Proceedings+of+the+2020+International+Conference+on+Computational+Collective+Intelligence+%28ICCCI+2020%29&rft.date=2020&rft_id=info%3Aarxiv%2F2002.00175&rft_id=info%3Adoi%2F10.1007%2F978-3-030-63007-2_57&rft.au=Quan+Hoang+Lam&rft.au=Quang+Duy+Le&rft.au=Kiet+Van+Nguyen&rft.au=Ngan+Luu-Thuy+Nguyen&rft_id=https%3A%2F%2Flink.springer.com%2Fchapter%2F10.1007%2F978-3-030-63007-2_57&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Natural scene annotation</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJ_FanY_GaoH_LuoG_Xu2004" class="citation conference cs1">J Fan; Y Gao; H Luo; G Xu (2004). <a rel="nofollow" class="external text" href="http://portal.acm.org/ft_gateway.cfm?id=1009055&type=pdf&coll=GUIDE&dl=GUIDE&CFID=1581830&CFTOKEN=99651762">"Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation"</a>. <i>Proceedings of the 27th annual international conference on Research and development in information retrieval</i>. pp. <span class="nowrap">361–</span>368.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+Image+Annotation+by+Using+Concept-Sensitive+Salient+Objects+for+Image+Content+Representation&rft.btitle=Proceedings+of+the+27th+annual+international+conference+on+Research+and+development+in+information+retrieval&rft.pages=%3Cspan+class%3D%22nowrap%22%3E361-%3C%2Fspan%3E368&rft.date=2004&rft.au=J+Fan&rft.au=Y+Gao&rft.au=H+Luo&rft.au=G+Xu&rft_id=http%3A%2F%2Fportal.acm.org%2Fft_gateway.cfm%3Fid%3D1009055%26type%3Dpdf%26coll%3DGUIDE%26dl%3DGUIDE%26CFID%3D1581830%26CFTOKEN%3D99651762&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Relevant low-level global filters</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFA_OlivaA_Torralba2001" class="citation conference cs1">A Oliva & A Torralba (2001). <a rel="nofollow" class="external text" href="http://cvcl.mit.edu/Papers/IJCV01-Oliva-Torralba.pdf">"Modeling the shape of the scene: a holistic representation of the spatial envelope"</a> <span class="cs1-format">(PDF)</span>. <i>International Journal of Computer Vision</i>. pp. 42:145–175.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Modeling+the+shape+of+the+scene%3A+a+holistic+representation+of+the+spatial+envelope&rft.btitle=International+Journal+of+Computer+Vision&rft.pages=42%3A145-175&rft.date=2001&rft.au=A+Oliva&rft.au=A+Torralba&rft_id=http%3A%2F%2Fcvcl.mit.edu%2FPapers%2FIJCV01-Oliva-Torralba.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Global image features and nonparametric density estimation</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFA_Yavlinsky,_E_SchofieldS_Rüger2005" class="citation conference cs1">A Yavlinsky, E Schofield & S Rüger (2005). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20051220164354/http://km.doc.ic.ac.uk/www-pub/civr05-annotation.pdf">"Automated Image Annotation Using Global Features and Robust Nonparametric Density Estimation"</a> <span class="cs1-format">(PDF)</span>. <i>Int'l Conf on Image and Video Retrieval (CIVR, Singapore, Jul 2005)</i>. Archived from <a rel="nofollow" class="external text" href="http://km.doc.ic.ac.uk/www-pub/civr05-annotation.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2005-12-20.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automated+Image+Annotation+Using+Global+Features+and+Robust+Nonparametric+Density+Estimation&rft.btitle=Int%27l+Conf+on+Image+and+Video+Retrieval+%28CIVR%2C+Singapore%2C+Jul+2005%29&rft.date=2005&rft.au=A+Yavlinsky%2C+E+Schofield&rft.au=S+R%C3%BCger&rft_id=http%3A%2F%2Fkm.doc.ic.ac.uk%2Fwww-pub%2Fcivr05-annotation.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Video semantics</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFN_VasconcelosA_Lippman2001" class="citation conference cs1">N Vasconcelos & A Lippman (2001). <a rel="nofollow" class="external text" href="http://www.svcl.ucsd.edu/publications/journal/2000/ip/ip00.pdf">"Statistical Models of Video Structure for Content Analysis and Characterization"</a> <span class="cs1-format">(PDF)</span>. <i>IEEE Transactions on Image Processing</i>. pp. <span class="nowrap">1–</span>17.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Statistical+Models+of+Video+Structure+for+Content+Analysis+and+Characterization&rft.btitle=IEEE+Transactions+on+Image+Processing&rft.pages=%3Cspan+class%3D%22nowrap%22%3E1-%3C%2Fspan%3E17&rft.date=2001&rft.au=N+Vasconcelos&rft.au=A+Lippman&rft_id=http%3A%2F%2Fwww.svcl.ucsd.edu%2Fpublications%2Fjournal%2F2000%2Fip%2Fip00.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFIlaria_BartoliniMarco_PatellaCorrado_Romani2010" class="citation conference cs1">Ilaria Bartolini; Marco Patella & Corrado Romani (2010). <a rel="nofollow" class="external text" href="http://dl.acm.org/citation.cfm?doid=1862344.1862364">"Shiatsu: Semantic-based Hierarchical Automatic Tagging of Videos by Segmentation Using Cuts"</a>. <i>3rd ACM International Multimedia Workshop on Automated Information Extraction in Media Production (AIEMPro10)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Shiatsu%3A+Semantic-based+Hierarchical+Automatic+Tagging+of+Videos+by+Segmentation+Using+Cuts&rft.btitle=3rd+ACM+International+Multimedia+Workshop+on+Automated+Information+Extraction+in+Media+Production+%28AIEMPro10%29&rft.date=2010&rft.au=Ilaria+Bartolini&rft.au=Marco+Patella&rft.au=Corrado+Romani&rft_id=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fdoid%3D1862344.1862364&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Image Annotation Refinement</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFYohan_JinLatifur_KhanLei_WangMamoun_Awad2005" class="citation conference cs1">Yohan Jin; <a href="/wiki/Latifur_Khan" title="Latifur Khan">Latifur Khan</a>; Lei Wang & Mamoun Awad (2005). <a rel="nofollow" class="external text" href="http://portal.acm.org/citation.cfm?id=1101305&dl=GUIDE,">"Image annotations by combining multiple evidence & wordNet"</a>. <i>13th Annual ACM International Conference on Multimedia (MM 05)</i>. pp. <span class="nowrap">706–</span>715.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Image+annotations+by+combining+multiple+evidence+%26+wordNet&rft.btitle=13th+Annual+ACM+International+Conference+on+Multimedia+%28MM+05%29&rft.pages=%3Cspan+class%3D%22nowrap%22%3E706-%3C%2Fspan%3E715&rft.date=2005&rft.au=Yohan+Jin&rft.au=Latifur+Khan&rft.au=Lei+Wang&rft.au=Mamoun+Awad&rft_id=http%3A%2F%2Fportal.acm.org%2Fcitation.cfm%3Fid%3D1101305%26dl%3DGUIDE%2C&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFChanghu_WangFeng_JingLei_ZhangHong-Jiang_Zhang2006" class="citation conference cs1">Changhu Wang; Feng Jing; Lei Zhang & Hong-Jiang Zhang (2006). <a rel="nofollow" class="external text" href="http://portal.acm.org/citation.cfm?id=1180639.1180774#,">"Image annotation refinement using random walk with restarts"</a>. <i>14th Annual ACM International Conference on Multimedia (MM 06)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Image+annotation+refinement+using+random+walk+with+restarts&rft.btitle=14th+Annual+ACM+International+Conference+on+Multimedia+%28MM+06%29&rft.date=2006&rft.au=Changhu+Wang&rft.au=Feng+Jing&rft.au=Lei+Zhang&rft.au=Hong-Jiang+Zhang&rft_id=http%3A%2F%2Fportal.acm.org%2Fcitation.cfm%3Fid%3D1180639.1180774%23%2C&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFChanghu_WangFeng_JingLei_ZhangHong-Jiang_Zhang2007" class="citation conference cs1">Changhu Wang; Feng Jing; Lei Zhang & Hong-Jiang Zhang (2007). "content-based image annotation refinement". <i>IEEE Conference on Computer Vision and Pattern Recognition (CVPR 07)</i>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FCVPR.2007.383221">10.1109/CVPR.2007.383221</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=content-based+image+annotation+refinement&rft.btitle=IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR+07%29&rft.date=2007&rft_id=info%3Adoi%2F10.1109%2FCVPR.2007.383221&rft.au=Changhu+Wang&rft.au=Feng+Jing&rft.au=Lei+Zhang&rft.au=Hong-Jiang+Zhang&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFIlaria_BartoliniPaolo_Ciaccia2007" class="citation conference cs1">Ilaria Bartolini & Paolo Ciaccia (2007). "Imagination: Exploiting Link Analysis for Accurate Image Annotation". <i>Springer Adaptive Multimedia Retrieval</i>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-540-79860-6_3">10.1007/978-3-540-79860-6_3</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Imagination%3A+Exploiting+Link+Analysis+for+Accurate+Image+Annotation&rft.btitle=Springer+Adaptive+Multimedia+Retrieval&rft.date=2007&rft_id=info%3Adoi%2F10.1007%2F978-3-540-79860-6_3&rft.au=Ilaria+Bartolini&rft.au=Paolo+Ciaccia&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd> <dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFIlaria_BartoliniPaolo_Ciaccia2010" class="citation conference cs1">Ilaria Bartolini & Paolo Ciaccia (2010). <a rel="nofollow" class="external text" href="http://dl.acm.org/citation.cfm?doid=1868366.1868371">"Multi-dimensional Keyword-based Image Annotation and Search"</a>. <i>2nd ACM International Workshop on Keyword Search on Structured Data (KEYS 2010)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Multi-dimensional+Keyword-based+Image+Annotation+and+Search&rft.btitle=2nd+ACM+International+Workshop+on+Keyword+Search+on+Structured+Data+%28KEYS+2010%29&rft.date=2010&rft.au=Ilaria+Bartolini&rft.au=Paolo+Ciaccia&rft_id=http%3A%2F%2Fdl.acm.org%2Fcitation.cfm%3Fdoid%3D1868366.1868371&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Automatic Image Annotation by Ensemble of Visual Descriptors</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFEmre_AkbasFatos_Y._Vural2007" class="citation conference cs1">Emre Akbas & Fatos Y. Vural (2007). "Automatic Image Annotation by Ensemble of Visual Descriptors". <i>Intl. Conf. on Computer Vision (CVPR) 2007, Workshop on Semantic Learning Applications in Multimedia</i>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FCVPR.2007.383484">10.1109/CVPR.2007.383484</a>. <a href="/wiki/Hdl_(identifier)" class="mw-redirect" title="Hdl (identifier)">hdl</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://hdl.handle.net/11511%2F16027">11511/16027</a></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+Image+Annotation+by+Ensemble+of+Visual+Descriptors&rft.btitle=Intl.+Conf.+on+Computer+Vision+%28CVPR%29+2007%2C+Workshop+on+Semantic+Learning+Applications+in+Multimedia&rft.date=2007&rft_id=info%3Ahdl%2F11511%2F16027&rft_id=info%3Adoi%2F10.1109%2FCVPR.2007.383484&rft.au=Emre+Akbas&rft.au=Fatos+Y.+Vural&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>A New Baseline for Image Annotation</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFAmeesh_Makadia_and_Vladimir_Pavlovic_and_Sanjiv_Kumar2008" class="citation conference cs1">Ameesh Makadia and Vladimir Pavlovic and Sanjiv Kumar (2008). <a rel="nofollow" class="external text" href="http://www.cs.rutgers.edu/~vladimir/pub/makadia08eccv.pdf">"A New Baseline for Image Annotation"</a> <span class="cs1-format">(PDF)</span>. <i>European Conference on Computer Vision (ECCV)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=A+New+Baseline+for+Image+Annotation&rft.btitle=European+Conference+on+Computer+Vision+%28ECCV%29&rft.date=2008&rft.au=Ameesh+Makadia+and+Vladimir+Pavlovic+and+Sanjiv+Kumar&rft_id=http%3A%2F%2Fwww.cs.rutgers.edu%2F~vladimir%2Fpub%2Fmakadia08eccv.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <p>Simultaneous Image Classification and Annotation </p> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFChong_Wang_and_David_Blei_and_Li_Fei-Fei2009" class="citation conference cs1">Chong Wang and David Blei and Li Fei-Fei (2009). <a rel="nofollow" class="external text" href="http://cs.stanford.edu/groups/vision/documents/WangBleiFei-Fei_CVPR2009.pdf">"Simultaneous Image Classification and Annotation"</a> <span class="cs1-format">(PDF)</span>. <i>Conf. on Computer Vision and Pattern Recognition (CVPR)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Simultaneous+Image+Classification+and+Annotation&rft.btitle=Conf.+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.date=2009&rft.au=Chong+Wang+and+David+Blei+and+Li+Fei-Fei&rft_id=http%3A%2F%2Fcs.stanford.edu%2Fgroups%2Fvision%2Fdocuments%2FWangBleiFei-Fei_CVPR2009.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFMatthieu_Guillaumin_and_Thomas_Mensink_and_Jakob_Verbeek_and_Cordelia_Schmid2009" class="citation conference cs1">Matthieu Guillaumin and Thomas Mensink and Jakob Verbeek and Cordelia Schmid (2009). <a rel="nofollow" class="external text" href="https://lear.inrialpes.fr/pubs/2009/GMVS09/GMVS09.pdf">"TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation"</a> <span class="cs1-format">(PDF)</span>. <i>Intl. Conf. on Computer Vision (ICCV)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=TagProp%3A+Discriminative+Metric+Learning+in+Nearest+Neighbor+Models+for+Image+Auto-Annotation&rft.btitle=Intl.+Conf.+on+Computer+Vision+%28ICCV%29&rft.date=2009&rft.au=Matthieu+Guillaumin+and+Thomas+Mensink+and+Jakob+Verbeek+and+Cordelia+Schmid&rft_id=https%3A%2F%2Flear.inrialpes.fr%2Fpubs%2F2009%2FGMVS09%2FGMVS09.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Image Annotation Using Metric Learning in Semantic Neighbourhoods</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFYashaswi_VermaC._V._Jawahar2012" class="citation conference cs1">Yashaswi Verma & C. V. Jawahar (2012). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20130514202446/http://researchweb.iiit.ac.in/%7Eyashaswi.verma/eccv12/vj_eccv12.pdf">"Image Annotation Using Metric Learning in Semantic Neighbourhoods"</a> <span class="cs1-format">(PDF)</span>. <i>European Conference on Computer Vision (ECCV)</i>. Archived from <a rel="nofollow" class="external text" href="http://researchweb.iiit.ac.in/~yashaswi.verma/eccv12/vj_eccv12.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2013-05-14<span class="reference-accessdate">. Retrieved <span class="nowrap">2014-02-26</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Image+Annotation+Using+Metric+Learning+in+Semantic+Neighbourhoods&rft.btitle=European+Conference+on+Computer+Vision+%28ECCV%29&rft.date=2012&rft.au=Yashaswi+Verma&rft.au=C.+V.+Jawahar&rft_id=http%3A%2F%2Fresearchweb.iiit.ac.in%2F~yashaswi.verma%2Feccv12%2Fvj_eccv12.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Automatic Image Annotation Using Deep Learning Representations</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFVenkatesh_N._MurthySubhransu_Maji_and_R._Manmatha2015" class="citation conference cs1">Venkatesh N. Murthy & Subhransu Maji and R. Manmatha (2015). <a rel="nofollow" class="external text" href="https://people.cs.umass.edu/~smaji/papers/embeddings-icmr15s.pdf">"Automatic Image Annotation Using Deep Learning Representations"</a> <span class="cs1-format">(PDF)</span>. <i>International Conference on Multimedia (ICMR)</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Automatic+Image+Annotation+Using+Deep+Learning+Representations&rft.btitle=International+Conference+on+Multimedia+%28ICMR%29&rft.date=2015&rft.au=Venkatesh+N.+Murthy&rft.au=Subhransu+Maji+and+R.+Manmatha&rft_id=https%3A%2F%2Fpeople.cs.umass.edu%2F~smaji%2Fpapers%2Fembeddings-icmr15s.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Holistic Image Annotation using Salient Regions and Background Image Information</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSarinFahrmairWagnerKameyama2012" class="citation conference cs1">Sarin, Supheakmungkol; Fahrmair, Michael; Wagner, Matthias & Kameyama, Wataru (2012). <a rel="nofollow" class="external text" href="https://www.jstage.jst.go.jp/article/ipsjjip/20/1/20_1_250/_pdf/-char/en"><i>Leveraging Features from Background and Salient Regions for Automatic Image Annotation</i></a>. Journal of Information Processing. Vol. 20. pp. <span class="nowrap">250–</span>266.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.btitle=Leveraging+Features+from+Background+and+Salient+Regions+for+Automatic+Image+Annotation&rft.pages=%3Cspan+class%3D%22nowrap%22%3E250-%3C%2Fspan%3E266&rft.date=2012&rft.aulast=Sarin&rft.aufirst=Supheakmungkol&rft.au=Fahrmair%2C+Michael&rft.au=Wagner%2C+Matthias&rft.au=Kameyama%2C+Wataru&rft_id=https%3A%2F%2Fwww.jstage.jst.go.jp%2Farticle%2Fipsjjip%2F20%2F1%2F20_1_250%2F_pdf%2F-char%2Fen&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <ul><li>Medical Image Annotation using bayesian networks and active learning</li></ul> <dl><dd><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFN._B._MarvastiE._Yörük_and_B._Acar2018" class="citation conference cs1">N. B. Marvasti & E. Yörük and B. Acar (2018). <a rel="nofollow" class="external text" href="https://www.researchgate.net/publication/320935564">"Computer-Aided Medical Image Annotation: Preliminary Results With Liver Lesions in CT"</a>. <i>IEEE Journal of Biomedical and Health Informatics</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=conference&rft.atitle=Computer-Aided+Medical+Image+Annotation%3A+Preliminary+Results+With+Liver+Lesions+in+CT&rft.btitle=IEEE+Journal+of+Biomedical+and+Health+Informatics&rft.date=2018&rft.au=N.+B.+Marvasti&rft.au=E.+Y%C3%B6r%C3%BCk+and+B.+Acar&rft_id=https%3A%2F%2Fwww.researchgate.net%2Fpublication%2F320935564&rfr_id=info%3Asid%2Fen.wikipedia.org%3AAutomatic+image+annotation" class="Z3988"></span></dd></dl> <div class="navbox-styles"><style data-mw-deduplicate="TemplateStyles:r1129693374">.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}</style><style data-mw-deduplicate="TemplateStyles:r1236075235">.mw-parser-output .navbox{box-sizing:border-box;border:1px solid #a2a9b1;width:100%;clear:both;font-size:88%;text-align:center;padding:1px;margin:1em auto 0}.mw-parser-output .navbox .navbox{margin-top:0}.mw-parser-output .navbox+.navbox,.mw-parser-output .navbox+.navbox-styles+.navbox{margin-top:-1px}.mw-parser-output .navbox-inner,.mw-parser-output .navbox-subgroup{width:100%}.mw-parser-output .navbox-group,.mw-parser-output .navbox-title,.mw-parser-output .navbox-abovebelow{padding:0.25em 1em;line-height:1.5em;text-align:center}.mw-parser-output .navbox-group{white-space:nowrap;text-align:right}.mw-parser-output .navbox,.mw-parser-output .navbox-subgroup{background-color:#fdfdfd}.mw-parser-output .navbox-list{line-height:1.5em;border-color:#fdfdfd}.mw-parser-output .navbox-list-with-group{text-align:left;border-left-width:2px;border-left-style:solid}.mw-parser-output tr+tr>.navbox-abovebelow,.mw-parser-output tr+tr>.navbox-group,.mw-parser-output tr+tr>.navbox-image,.mw-parser-output tr+tr>.navbox-list{border-top:2px solid #fdfdfd}.mw-parser-output .navbox-title{background-color:#ccf}.mw-parser-output .navbox-abovebelow,.mw-parser-output .navbox-group,.mw-parser-output .navbox-subgroup .navbox-title{background-color:#ddf}.mw-parser-output .navbox-subgroup .navbox-group,.mw-parser-output .navbox-subgroup .navbox-abovebelow{background-color:#e6e6ff}.mw-parser-output .navbox-even{background-color:#f7f7f7}.mw-parser-output .navbox-odd{background-color:transparent}.mw-parser-output .navbox .hlist td dl,.mw-parser-output .navbox .hlist td ol,.mw-parser-output .navbox .hlist td ul,.mw-parser-output .navbox td.hlist dl,.mw-parser-output .navbox td.hlist ol,.mw-parser-output .navbox td.hlist ul{padding:0.125em 0}.mw-parser-output .navbox .navbar{display:block;font-size:100%}.mw-parser-output .navbox-title .navbar{float:left;text-align:left;margin-right:0.5em}body.skin--responsive .mw-parser-output .navbox-image img{max-width:none!important}@media print{body.ns-0 .mw-parser-output .navbox{display:none!important}}</style></div><div role="navigation" class="navbox" aria-labelledby="Computer_vision148" style="padding:3px"><table class="nowraplinks mw-collapsible expanded navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><style data-mw-deduplicate="TemplateStyles:r1239400231">.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}</style><div class="navbar plainlinks hlist navbar-mini"><ul><li class="nv-view"><a href="/wiki/Template:Computer_vision_footer" title="Template:Computer vision footer"><abbr title="View this template">v</abbr></a></li><li class="nv-talk"><a href="/wiki/Template_talk:Computer_vision_footer" title="Template talk:Computer vision footer"><abbr title="Discuss this template">t</abbr></a></li><li class="nv-edit"><a href="/wiki/Special:EditPage/Template:Computer_vision_footer" title="Special:EditPage/Template:Computer vision footer"><abbr title="Edit this template">e</abbr></a></li></ul></div><div id="Computer_vision148" style="font-size:114%;margin:0 4em"><a href="/wiki/Computer_vision" title="Computer vision">Computer vision</a></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">Categories</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Category:Datasets_in_computer_vision" title="Category:Datasets in computer vision">Datasets</a></li> <li><a href="/wiki/Digital_geometry" title="Digital geometry">Digital geometry</a></li> <li><a href="/wiki/Category:Commercial_computer_vision_systems" title="Category:Commercial computer vision systems">Commercial systems</a></li> <li><a href="/wiki/Category:Feature_detection_(computer_vision)" title="Category:Feature detection (computer vision)">Feature detection</a></li> <li><a href="/wiki/Category:Geometry_in_computer_vision" title="Category:Geometry in computer vision">Geometry</a></li> <li><a href="/wiki/Category:Image_sensor_technology_in_computer_vision" title="Category:Image sensor technology in computer vision">Image sensor technology</a></li> <li><a href="/wiki/Category:Learning_in_computer_vision" title="Category:Learning in computer vision">Learning</a></li> <li><a href="/wiki/Mathematical_morphology" title="Mathematical morphology">Morphology</a></li> <li><a href="/wiki/Category:Motion_in_computer_vision" title="Category:Motion in computer vision">Motion analysis</a></li> <li><a href="/wiki/Category:Image_noise_reduction_techniques" title="Category:Image noise reduction techniques">Noise reduction techniques</a></li> <li><a href="/wiki/Category:Object_recognition_and_categorization" title="Category:Object recognition and categorization">Recognition and categorization</a></li> <li><a href="/wiki/Category:Computer_vision_research_infrastructure" title="Category:Computer vision research infrastructure">Research infrastructure</a></li> <li><a href="/wiki/Category:Computer_vision_researchers" title="Category:Computer vision researchers">Researchers</a></li> <li><a href="/wiki/Category:Image_segmentation" title="Category:Image segmentation">Segmentation</a></li> <li><a href="/wiki/Category:Computer_vision_software" title="Category:Computer vision software">Software</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Technologies</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Computer_stereo_vision" title="Computer stereo vision">Computer stereo vision</a></li> <li><a href="/wiki/Motion_capture" title="Motion capture">Motion capture</a></li> <li><a href="/wiki/Outline_of_object_recognition" title="Outline of object recognition">Object recognition</a> <ul><li><a href="/wiki/3D_object_recognition" title="3D object recognition">3D object recognition</a></li></ul></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Category:Applications_of_computer_vision" title="Category:Applications of computer vision">Applications</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th id="3D_reconstruction21" scope="row" class="navbox-group" style="width:1%"><a href="/wiki/3D_reconstruction" title="3D reconstruction">3D reconstruction</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/3D_reconstruction_from_multiple_images" title="3D reconstruction from multiple images">3D reconstruction from multiple images</a></li> <li><a href="/wiki/2D_to_3D_conversion" title="2D to 3D conversion">2D to 3D conversion</a></li> <li><a href="/wiki/Gaussian_splatting" title="Gaussian splatting">Gaussian splatting</a></li> <li><a href="/wiki/Neural_radiance_field" title="Neural radiance field">Neural radiance field</a></li> <li><a href="/wiki/Shape_from_focus" title="Shape from focus">Shape from focus</a></li> <li><a href="/wiki/Simultaneous_localization_and_mapping" title="Simultaneous localization and mapping">Simultaneous localization and mapping</a></li> <li><a href="/wiki/Structure_from_motion" title="Structure from motion">Structure from motion</a></li> <li><a href="/wiki/View_synthesis" title="View synthesis">View synthesis</a></li> <li><a href="/wiki/Visual_hull" title="Visual hull">Visual hull</a></li> <li><a href="/wiki/4D_reconstruction" title="4D reconstruction">4D reconstruction</a> <ul><li><a href="/wiki/Free_viewpoint_television" title="Free viewpoint television">Free viewpoint television</a></li> <li><a href="/wiki/Volumetric_capture" title="Volumetric capture">Volumetric capture</a></li></ul></li></ul> </div></td></tr></tbody></table><div> <ul><li><a href="/wiki/3D_pose_estimation" title="3D pose estimation">3D pose estimation</a></li> <li><a href="/wiki/Activity_recognition" title="Activity recognition">Activity recognition</a></li> <li><a href="/wiki/Audio-visual_speech_recognition" title="Audio-visual speech recognition">Audio-visual speech recognition</a></li> <li><a class="mw-selflink selflink">Automatic image annotation</a></li> <li><a href="/wiki/Automatic_number-plate_recognition" title="Automatic number-plate recognition">Automatic number-plate recognition</a></li> <li><a href="/wiki/Automated_species_identification" title="Automated species identification">Automated species identification</a></li> <li><a href="/wiki/Augmented_reality" title="Augmented reality">Augmented reality</a></li> <li><a href="/wiki/Bioimage_informatics" title="Bioimage informatics">Bioimage informatics</a></li> <li><a href="/wiki/Blob_detection" title="Blob detection">Blob detection</a></li> <li><a href="/wiki/Computer-aided_diagnosis" title="Computer-aided diagnosis">Computer-aided diagnosis</a></li> <li><a href="/wiki/Content-based_image_retrieval" title="Content-based image retrieval">Content-based image retrieval</a> <ul><li><a href="/wiki/Reverse_image_search" title="Reverse image search">Reverse image search</a></li></ul></li> <li><a href="/wiki/Eye_tracking" title="Eye tracking">Eye tracking</a></li> <li><a href="/wiki/Facial_recognition_system" title="Facial recognition system">Face recognition</a></li> <li><a href="/wiki/Foreground_detection" title="Foreground detection">Foreground detection</a></li> <li><a href="/wiki/Gesture_recognition" title="Gesture recognition">Gesture recognition</a></li> <li><a href="/wiki/Image_denoising" class="mw-redirect" title="Image denoising">Image denoising</a></li> <li><a href="/wiki/Image_restoration_by_artificial_intelligence" title="Image restoration by artificial intelligence">Image restoration</a></li> <li><a href="/wiki/Landmark_detection" title="Landmark detection">Landmark detection</a></li> <li><a href="/wiki/Medical_image_computing" title="Medical image computing">Medical image computing</a></li> <li><a href="/wiki/Object_detection" title="Object detection">Object detection</a> <ul><li><a href="/wiki/Moving_object_detection" title="Moving object detection">Moving object detection</a></li> <li><a href="/wiki/Small_object_detection" title="Small object detection">Small object detection</a></li></ul></li> <li><a href="/wiki/Optical_character_recognition" title="Optical character recognition">Optical character recognition</a></li> <li><a href="/wiki/Pose_tracking" title="Pose tracking">Pose tracking</a></li> <li><a href="/wiki/Remote_sensing" title="Remote sensing">Remote sensing</a></li> <li><a href="/wiki/Robotic_mapping" title="Robotic mapping">Robotic mapping</a></li> <li><a href="/wiki/Self-driving_car" title="Self-driving car">Autonomous vehicles</a></li> <li><a href="/wiki/Video_content_analysis" title="Video content analysis">Video content analysis</a></li> <li><a href="/wiki/Video_motion_analysis" title="Video motion analysis">Video motion analysis</a></li> <li><a href="/wiki/Artificial_intelligence_for_video_surveillance" title="Artificial intelligence for video surveillance">Video surveillance</a></li> <li><a href="/wiki/Video_tracking" title="Video tracking">Video tracking</a></li></ul></div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div><b><a href="/wiki/Category:Computer_vision" title="Category:Computer vision">Main category</a></b></div></td></tr></tbody></table></div>    </div><noscript><img src="https://login.wikimedia.org/wiki/Special:CentralAutoLogin/start?useformat=desktop&type=1x1&usesul3=0" alt="" width="1" height="1" style="border: none; position: absolute;"></noscript> <div class="printfooter" data-nosnippet="">Retrieved from "<a dir="ltr" href="https://en.wikipedia.org/w/index.php?title=Automatic_image_annotation&oldid=1275066243">https://en.wikipedia.org/w/index.php?title=Automatic_image_annotation&oldid=1275066243</a>"</div></div> <div id="catlinks" class="catlinks" data-mw="interface"><div id="mw-normal-catlinks" class="mw-normal-catlinks"><a href="/wiki/Help:Category" title="Help:Category">Categories</a>: <ul><li><a href="/wiki/Category:Applications_of_artificial_intelligence" title="Category:Applications of artificial intelligence">Applications of artificial intelligence</a></li><li><a href="/wiki/Category:Applications_of_computer_vision" title="Category:Applications of computer vision">Applications of computer vision</a></li></ul></div><div id="mw-hidden-catlinks" class="mw-hidden-catlinks mw-hidden-cats-hidden">Hidden categories: <ul><li><a href="/wiki/Category:CS1_maint:_archived_copy_as_title" title="Category:CS1 maint: archived copy as title">CS1 maint: archived copy as title</a></li><li><a href="/wiki/Category:Articles_needing_cleanup_from_November_2022" title="Category:Articles needing cleanup from November 2022">Articles needing cleanup from November 2022</a></li><li><a href="/wiki/Category:All_pages_needing_cleanup" title="Category:All pages needing cleanup">All pages needing cleanup</a></li><li><a href="/wiki/Category:Cleanup_tagged_articles_with_a_reason_field_from_November_2022" title="Category:Cleanup tagged articles with a reason field from November 2022">Cleanup tagged articles with a reason field from November 2022</a></li><li><a href="/wiki/Category:Wikipedia_pages_needing_cleanup_from_November_2022" title="Category:Wikipedia pages needing cleanup from November 2022">Wikipedia pages needing cleanup from November 2022</a></li></ul></div></div> </div> </main> </div> <div class="mw-footer-container"> <footer id="footer" class="mw-footer" > <ul id="footer-info"> <li id="footer-info-lastmod"> This page was last edited on 10 February 2025, at 21:36<span class="anonymous-show"> (UTC)</span>.</li> <li id="footer-info-copyright">Text is available under the <a href="/wiki/Wikipedia:Text_of_the_Creative_Commons_Attribution-ShareAlike_4.0_International_License" title="Wikipedia:Text of the Creative Commons Attribution-ShareAlike 4.0 International License">Creative Commons Attribution-ShareAlike 4.0 License</a>; additional terms may apply. By using this site, you agree to the <a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Terms_of_Use" class="extiw" title="foundation:Special:MyLanguage/Policy:Terms of Use">Terms of Use</a> and <a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Privacy_policy" class="extiw" title="foundation:Special:MyLanguage/Policy:Privacy policy">Privacy Policy</a>. Wikipedia® is a registered trademark of the <a rel="nofollow" class="external text" href="https://wikimediafoundation.org/">Wikimedia Foundation, Inc.</a>, a non-profit organization.</li> </ul> <ul id="footer-places"> <li id="footer-places-privacy"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Privacy_policy">Privacy policy</a></li> <li id="footer-places-about"><a href="/wiki/Wikipedia:About">About Wikipedia</a></li> <li id="footer-places-disclaimers"><a href="/wiki/Wikipedia:General_disclaimer">Disclaimers</a></li> <li id="footer-places-contact"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us">Contact Wikipedia</a></li> <li id="footer-places-wm-codeofconduct"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Universal_Code_of_Conduct">Code of Conduct</a></li> <li id="footer-places-developers"><a href="https://developer.wikimedia.org">Developers</a></li> <li id="footer-places-statslink"><a href="https://stats.wikimedia.org/#/en.wikipedia.org">Statistics</a></li> <li id="footer-places-cookiestatement"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Cookie_statement">Cookie statement</a></li> <li id="footer-places-mobileview"><a href="//en.m.wikipedia.org/w/index.php?title=Automatic_image_annotation&mobileaction=toggle_view_mobile" class="noprint stopMobileRedirectToggle">Mobile view</a></li> </ul> <ul id="footer-icons" class="noprint"> <li id="footer-copyrightico"><a href="https://wikimediafoundation.org/" class="cdx-button cdx-button--fake-button cdx-button--size-large cdx-button--fake-button--enabled"><img src="/static/images/footer/wikimedia-button.svg" width="84" height="29" alt="Wikimedia Foundation" lang="en" loading="lazy"></a></li> <li id="footer-poweredbyico"><a href="https://www.mediawiki.org/" class="cdx-button cdx-button--fake-button cdx-button--size-large cdx-button--fake-button--enabled"><img src="/w/resources/assets/poweredby_mediawiki.svg" alt="Powered by MediaWiki" width="88" height="31" loading="lazy"></a></li> </ul> </footer> </div> </div> </div> <div class="vector-header-container vector-sticky-header-container"> <div id="vector-sticky-header" class="vector-sticky-header"> <div class="vector-sticky-header-start"> <div class="vector-sticky-header-icon-start vector-button-flush-left vector-button-flush-right" aria-hidden="true"> <button class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-sticky-header-search-toggle" tabindex="-1" data-event-name="ui.vector-sticky-search-form.icon"><span class="vector-icon mw-ui-icon-search mw-ui-icon-wikimedia-search"></span> <span>Search</span> </button> </div> <div role="search" class="vector-search-box-vue vector-search-box-show-thumbnail vector-search-box"> <div class="vector-typeahead-search-container"> <div class="cdx-typeahead-search cdx-typeahead-search--show-thumbnail"> <form action="/w/index.php" id="vector-sticky-search-form" class="cdx-search-input cdx-search-input--has-end-button"> <div class="cdx-search-input__input-wrapper" data-search-loc="header-moved"> <div class="cdx-text-input cdx-text-input--has-start-icon"> <input class="cdx-text-input__input" type="search" name="search" placeholder="Search Wikipedia"> <span class="cdx-text-input__icon cdx-text-input__start-icon"></span> </div> <input type="hidden" name="title" value="Special:Search"> </div> <button class="cdx-button cdx-search-input__end-button">Search</button> </form> </div> </div> </div> <div class="vector-sticky-header-context-bar"> <nav aria-label="Contents" class="vector-toc-landmark"> <div id="vector-sticky-header-toc" class="vector-dropdown mw-portlet mw-portlet-sticky-header-toc vector-sticky-header-toc vector-button-flush-left" > <input type="checkbox" id="vector-sticky-header-toc-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-sticky-header-toc" class="vector-dropdown-checkbox " aria-label="Toggle the table of contents" > <label id="vector-sticky-header-toc-label" for="vector-sticky-header-toc-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-listBullet mw-ui-icon-wikimedia-listBullet"></span> <span class="vector-dropdown-label-text">Toggle the table of contents</span> </label> <div class="vector-dropdown-content"> <div id="vector-sticky-header-toc-unpinned-container" class="vector-unpinned-container"> </div> </div> </div> </nav> <div class="vector-sticky-header-context-bar-primary" aria-hidden="true" ><span class="mw-page-title-main">Automatic image annotation</span></div> </div> </div> <div class="vector-sticky-header-end" aria-hidden="true"> <div class="vector-sticky-header-icons"> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-talk-sticky-header" tabindex="-1" data-event-name="talk-sticky-header"><span class="vector-icon mw-ui-icon-speechBubbles mw-ui-icon-wikimedia-speechBubbles"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-subject-sticky-header" tabindex="-1" data-event-name="subject-sticky-header"><span class="vector-icon mw-ui-icon-article mw-ui-icon-wikimedia-article"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-history-sticky-header" tabindex="-1" data-event-name="history-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-history mw-ui-icon-wikimedia-wikimedia-history"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only mw-watchlink" id="ca-watchstar-sticky-header" tabindex="-1" data-event-name="watch-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-star mw-ui-icon-wikimedia-wikimedia-star"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-edit-sticky-header" tabindex="-1" data-event-name="wikitext-edit-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-wikiText mw-ui-icon-wikimedia-wikimedia-wikiText"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-ve-edit-sticky-header" tabindex="-1" data-event-name="ve-edit-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-edit mw-ui-icon-wikimedia-wikimedia-edit"></span> <span></span> </a> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only" id="ca-viewsource-sticky-header" tabindex="-1" data-event-name="ve-edit-protected-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-editLock mw-ui-icon-wikimedia-wikimedia-editLock"></span> <span></span> </a> </div> <div class="vector-sticky-header-buttons"> <button class="cdx-button cdx-button--weight-quiet mw-interlanguage-selector" id="p-lang-btn-sticky-header" tabindex="-1" data-event-name="ui.dropdown-p-lang-btn-sticky-header"><span class="vector-icon mw-ui-icon-wikimedia-language mw-ui-icon-wikimedia-wikimedia-language"></span> <span>5 languages</span> </button> <a href="#" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--action-progressive" id="ca-addsection-sticky-header" tabindex="-1" data-event-name="addsection-sticky-header"><span class="vector-icon mw-ui-icon-speechBubbleAdd-progressive mw-ui-icon-wikimedia-speechBubbleAdd-progressive"></span> <span>Add topic</span> </a> </div> <div class="vector-sticky-header-icon-end"> <div class="vector-user-links"> </div> </div> </div> </div> </div> <div class="vector-settings" id="p-dock-bottom"> <ul></ul> </div><script>(RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgHostname":"mw-web.codfw.main-846cfb8d5c-6pm72","wgBackendResponseTime":129,"wgPageParseReport":{"limitreport":{"cputime":"0.546","walltime":"0.640","ppvisitednodes":{"value":1872,"limit":1000000},"postexpandincludesize":{"value":112552,"limit":2097152},"templateargumentsize":{"value":1693,"limit":2097152},"expansiondepth":{"value":17,"limit":100},"expensivefunctioncount":{"value":5,"limit":500},"unstrip-depth":{"value":1,"limit":20},"unstrip-size":{"value":108690,"limit":5000000},"entityaccesscount":{"value":0,"limit":400},"timingprofile":["100.00% 568.583 1 -total"," 36.56% 207.869 39 Template:Cite_conference"," 25.24% 143.515 1 Template:Reflist"," 22.55% 128.213 3 Template:Cite_journal"," 18.16% 103.241 1 Template:Computer_vision"," 17.35% 98.650 2 Template:Navbox"," 17.11% 97.306 1 Template:Cleanup-section"," 15.68% 89.172 1 Template:Cleanup"," 10.55% 60.003 2 Template:Main_other"," 10.20% 57.985 1 Template:Ambox"]},"scribunto":{"limitreport-timeusage":{"value":"0.415","limit":"10.000"},"limitreport-memusage":{"value":5385561,"limit":52428800}},"cachereport":{"origin":"mw-api-ext.codfw.main-7bcd85664b-qkllg","timestamp":"20250210213658","ttl":2592000,"transientcontent":false}}});});</script> <script type="application/ld+json">{"@context":"https:\/\/schema.org","@type":"Article","name":"Automatic image annotation","url":"https:\/\/en.wikipedia.org\/wiki\/Automatic_image_annotation","sameAs":"http:\/\/www.wikidata.org\/entity\/Q2851778","mainEntity":"http:\/\/www.wikidata.org\/entity\/Q2851778","author":{"@type":"Organization","name":"Contributors to Wikimedia projects"},"publisher":{"@type":"Organization","name":"Wikimedia Foundation, Inc.","logo":{"@type":"ImageObject","url":"https:\/\/www.wikimedia.org\/static\/images\/wmf-hor-googpub.png"}},"datePublished":"2005-05-23T23:09:45Z","dateModified":"2025-02-10T21:36:57Z","image":"https:\/\/upload.wikimedia.org\/wikipedia\/commons\/a\/ae\/DenseCap_%28Johnson_et_al.%2C_2016%29_%28cropped%29.png","headline":"process which automatically assigns metadata in the form of captioning or keywords to a digital image"}</script> </body> </html>