{"id":1022,"date":"2022-08-20T17:09:03","date_gmt":"2022-08-20T17:09:03","guid":{"rendered":"https:\/\/faculty.eng.ufl.edu\/jain\/?page_id=1022"},"modified":"2026-06-23T13:01:36","modified_gmt":"2026-06-23T17:01:36","slug":"eyetracking-and-comics","status":"publish","type":"page","link":"https:\/\/faculty.eng.ufl.edu\/jain\/research\/completed-projects\/eyetracking-and-comics\/","title":{"rendered":"Eyetracking and Comics"},"content":{"rendered":"<h3 class=\"page-header\">Eyetracking and Comics<\/h3>\n<div class=\"panel panel-default\">\n<div class=\"panel-heading\">\n<h4 class=\"panel-title\">Abstract<\/h4>\n<\/div>\n<div class=\"panel-body\">\n<p>Comic artists put in a lot of effort into directing the viewer&#8217;s attention. We collected eyetracking data on a variety of legacy comic book panels, and used this corpus to study viewer gaze behavior, as well as, drive computational algorithms.<\/p>\n<\/div>\n<\/div>\n<h4 class=\"page-header\">Projects<\/h4>\n<div id=\"creating-segments-and\" class=\"panel panel-default\">\n<div class=\"panel-body\">\n<h5 class=\"page-title text-center\">Creating Segments and Effects on Comics by Clustering Gaze Data<\/h5>\n<div class=\"embed-responsive embed-responsive-16by9\">\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"656\" height=\"223\" class=\"wp-image-2835 aligncenter\" src=\"https:\/\/faculty.eng.ufl.edu\/jain\/wp-content\/uploads\/sites\/745\/2026\/06\/comic.webp\" alt=\"Our method reassembles superpixels into segments.\" srcset=\"https:\/\/faculty.eng.ufl.edu\/jain\/wp-content\/uploads\/sites\/745\/2026\/06\/comic.webp 656w, https:\/\/faculty.eng.ufl.edu\/jain\/wp-content\/uploads\/sites\/745\/2026\/06\/comic-300x102.webp 300w\" sizes=\"auto, (max-width: 656px) 100vw, 656px\" \/><\/figure>\n<\/div>\n<p>&#8220;Creating Segments and Effects on Comics by Clustering Gaze Data&#8221;, Ishwarya Thirunarayanan, Khimya Khetarpal, Sanjeev Koppal, Olivier Le Meur, John Shea and Eakta Jain<em>, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 2017.<\/em><\/p>\n<ul>\n<li><a href=\"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3078836\" target=\"_blank\" rel=\"noopener\">Paper<\/a><\/li>\n<li>Bibtex entry:<br \/>\n@article{thirunarayanan2017,<br \/>\ntitle = {Creating Segments and Effects on Comics by Clustering Gaze Data},<br \/>\nauthor = {Thirunarayanan, Ishwarya and Khetarpal, Khimya and Koppal, Sanjeev and Le Meur, Olivier and Shea, John and Jain, Eakta},<br \/>\njournal = {ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)},<br \/>\npages = {24:1&#8211;24:23}<br \/>\nnumpages = {23}<br \/>\ndoi = {10.1145\/3078836}<br \/>\nyear = {2017},<br \/>\npublisher = {ACM},<br \/>\n}<\/li>\n<\/ul>\n\n\n\n<div id=\"predicting-moves-on-stills-for\" class=\"panel panel-default\">\n<div class=\"panel-body\">\n<h5 class=\"page-title text-center\">Predicting Moves-on-Stills for Comic Art using Viewer Gaze Data<\/h5>\n<\/div>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"820\" height=\"322\" class=\"wp-image-2841 aligncenter\" src=\"https:\/\/faculty.eng.ufl.edu\/jain\/wp-content\/uploads\/sites\/745\/2026\/06\/7535123-fig-1-source-large.gif\" alt=\"Move-on-stills technique. (a) A move-on-still moves a viewport (1.33:1, for example) over original artwork (1:1.37, for example) to best display the art. (b) The proposed method uses viewer gaze data as input. Fixation points are clustered based on their locations (green and blue dots). (c) The move-on-still predicted by our algorithm starts at the dotted rectangle and ends at the solid rectangle, revealing the mouth of the gun. (d) This digital effect mimics the move-on-still traditionally created by a rostrum camera setup. (Original comic panels courtesy of marvel comics)\n\n\" \/><\/p>\n<div class=\"panel-body\">\n<div class=\"embed-responsive embed-responsive-16by9\">\u00a0<\/div>\n<p>&#8220;Predicting Moves-on-Stills for Comic Art using Viewer Gaze Data&#8221;, Eakta Jain, Yaser Sheikh, Jessica Hodgins<em>, IEEE CG&amp;A Special Issue on Quality Assessment and Perception in Computer Graphics 2016.<\/em><\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li><a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/7535123\" target=\"_blank\" rel=\"noopener\">Paper<\/a><\/li>\n<li>Bibtex entry:<br \/>@article{jain:2016,<br \/>author = {Jain, Eakta and Sheikh, Yaser and Hodgins, Jessica},<br \/>title = {Predicting Moves-on-Stills for Comic Art using Viewer Gaze Data},<br \/>journal = {IEEE CG&amp;A Special Issue on Quality Assessment and Perception in Computer Graphics},<br \/>year = {2016},<br \/>pages = {34 &#8211; 45},<br \/>numpages = {12},<br \/>doi = {10.1109\/MCG.2016.74},<br \/>volume =<br \/>number =<br \/>organization = {IEEE}<br \/>}<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>We thank MARVEL comics for permission to use comic images.<\/p>\n<\/div>\n<\/div>\n<div id=\"a-preliminary-benchmark\" class=\"panel panel-default\">\n<div class=\"panel-body\">\n<h5 class=\"page-title text-center\">A Preliminary Benchmark of Four Saliency Algorithms on Comic Art<\/h5>\n<p><\/p>\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"470\" height=\"550\" class=\"wp-image-2849 aligncenter\" src=\"https:\/\/faculty.eng.ufl.edu\/jain\/wp-content\/uploads\/sites\/745\/2026\/06\/salency.gif\" alt=\"Saliency maps generated from four different algorithms are depicted for chosen comic images. LSVM, GBVS show center bias, and similar regions are marked salient. VOCUS2 finds it difficult to detect multiple salient regions, whereas, RC marks complete regions as salient.\n\n\" \/><\/figure>\n<p><\/p>\n<\/div>\n<\/div>\n\n<p>&#8220;A Preliminary Benchmark of Four Saliency Algorithms on Comic Art&#8221;, Khimya Khetarpal, Eakta Jain<em>, IEEE International Conference on Multimedia and Expo MMArt Workshop 2016.<\/em><\/p>\n<ul>\n<li><a href=\"http:\/\/ieeexplore.ieee.org\/xpl\/conhome.jsp?punumber=1801805\" target=\"_blank\" rel=\"noopener\">Paper<\/a>\u00a0(IEEE Xplore)<\/li>\n<li>Bibtex entry:<br \/>@inproceedings{khetarpal2016comicart,<br \/>title = {A Preliminary Benchmark Of Four Saliency Algorithms On Comic Art},<br \/>author = {Khetarpal, Khimya and Jain, Eakta},<br \/>journal = {International Workshop on Multimedia Artworks Analysis (MMArt), IEEE ICME Workshops},<br \/>pages = {1&#8211;6},<br \/>numpages = {6},<br \/>doi = {10.1109\/ICMEW.2016.7574728},<br \/>year = {2016},<br \/>organization = {IEEE}<br \/>}<\/li>\n<\/ul>\n<div id=\"leveraging-gaze-data\" class=\"panel panel-default\">\n<div class=\"panel-body\">\n<h5 class=\"page-title text-center\">Leveraging Gaze Data for Segmentation and Effects on Comics<\/h5>\n<div class=\"embed-responsive embed-responsive-16by9\">\u00a0<\/div>\n<p>&#8220;Leveraging Gaze Data for Segmentation and Effects on Comics&#8221;, Ishwarya Thirunarayanan, Sanjeev Koppal, John Shea, Eakta Jain<em>, ACM Symposium on Applied Perception Poster 2016.<\/em><\/p>\n<ul>\n<li><a href=\"https:\/\/jainlab.cise.ufl.edu\/documents\/LeveragingGazeData_CR.pdf\" target=\"_blank\" rel=\"noopener\">Poster abstract<\/a>\u00a0(PDF &#8211; 2.7MB)<\/li>\n<li><a href=\"https:\/\/jainlab.cise.ufl.edu\/documents\/Poster_DraftVer2.pdf\" target=\"_blank\" rel=\"noopener\">Poster<\/a>\u00a0(PDF &#8211; 48.3MB)<\/li>\n<li><a href=\"https:\/\/jainlab.cise.ufl.edu\/documents\/REQGazeComicsPoster_Ppt.pptx\" target=\"_blank\" rel=\"noopener\">Presentation<\/a>\u00a0(PPTX &#8211; 5.6MB)<\/li>\n<li>Bibtex entry:<br \/>@refereedabstract{abstract,<br \/>author = {Thirunarayanan, Ishwarya and Koppal, Sanjeev and Shea, John and Jain, Eakta},<br \/>title = {Leveraging Gaze Data for Segmentation and Effects on Comics},<br \/>howpublished = {SAP Poster Abstract},<br \/>pages = {137&#8211;137},<br \/>numpages = {6},<br \/>doi = {10.1145\/2931002.2947703},<br \/>month = {6},<br \/>year = {2016},<br \/>}<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<div id=\"deepcomics:-saliency-estimation\" class=\"panel panel-default\">\n<div class=\"panel-body\">\n<h5 class=\"page-title text-center\">DeepComics: saliency estimation for comics<\/h5>\n<p>&#8220;DeepComics: saliency estimation for comics&#8221;, Kevin Bannier, Eakta Jain, Olivier Le Meur<em>, ACM Symposium on Eye Tracking Research &amp; Applications (ETRA) 2018.<\/em><\/p>\n<ul>\n<li><a href=\"http:\/\/people.irisa.fr\/Olivier.Le_Meur\/publi\/2018_ETRA\/index.html\" target=\"_blank\" rel=\"noopener\">Website<\/a><\/li>\n<li>Bibtex entry:<br \/>@inproceedings{Bannier2018,<br \/>Title = {DeepComics: Saliency estimation for comics},<br \/>Author = {Bannier, K\u00e9vin and Jain, Eakta and Le Meur, Olivier},<br \/>booktitle ={ACM Symposium on Eye Tracking Research and Applications},<br \/>numpages = {4},<br \/>year ={2018}<br \/>}<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<div class=\"panel panel-default\">\n<div class=\"panel-heading\">\n<h4 class=\"panel-title\">Copyright notice<\/h4>\n<\/div>\n<div class=\"panel-body\">\n<p>The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author&#8217;s copyright. These works may not be reposted without the explicit permission of the copyright holder.<\/p>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Eyetracking and Comics Abstract Comic artists put in a lot of effort into directing the viewer&#8217;s attention. We collected eyetracking data on a variety of legacy comic book panels, and used this corpus to study viewer gaze behavior, as well as, drive computational algorithms. Projects Creating Segments and Effects on Comics by Clustering Gaze Data [&hellip;]<\/p>\n","protected":false},"author":1299,"featured_media":0,"parent":912,"menu_order":4,"comment_status":"closed","ping_status":"closed","template":"page-templates\/page-section-nav.php","meta":{"_acf_changed":false,"inline_featured_image":false,"featured_post":"","footnotes":"","_links_to":"","_links_to_target":""},"class_list":["post-1022","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/pages\/1022","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/users\/1299"}],"replies":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/comments?post=1022"}],"version-history":[{"count":9,"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/pages\/1022\/revisions"}],"predecessor-version":[{"id":2869,"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/pages\/1022\/revisions\/2869"}],"up":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/pages\/912"}],"wp:attachment":[{"href":"https:\/\/faculty.eng.ufl.edu\/jain\/wp-json\/wp\/v2\/media?parent=1022"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}