[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-157985-105":59,"doc-detail-157985-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-computational-model-of-comprehension-in-manga-style-visual-narratives","A Computational Model of Comprehension in Manga Style Visual Narratives","","Comprehending manga- and comic-style image sequences requires tracking not only moment-to-moment content but also omissions, transitions, and out-of-frame changes that drive an inferred world state. This paper analyzes stylistic differences between western comics and Japanese manga across screening, ballooning, layout, language, and reading order using an annotated dataset. The work adds a new feature set, trains and evaluates a computational multimodal comprehension model, and measures predictive accuracy on unseen next frames with a cloze test, yielding benchmarks and insights for language-and-vision narrative understanding.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-computational-model-of-comprehension-in-manga-style-visual-narratives/157985/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-computational-model-of-comprehension-in-manga-style-visual-narratives/157985.png","ImageObject",300,407,{"name":92,"@type":93},"Finn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-08-29",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is understanding a manga or comic sequence of images challenging?","Question",{"text":112,"@type":113},"It requires inferring what has changed or been omitted between frames in addition to interpreting the content shown at each moment. These inferences depend on transitions and out-of-frame information.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What differences between western comics and Japanese manga does the paper analyze?",{"text":117,"@type":113},"It compares stylistic differences including screening, ballooning, layout, language, and reading order, supported by an annotated dataset.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the computational model evaluated?",{"text":121,"@type":113},"The paper evaluates it using cloze tests that measure how accurately the model predicts unseen next frames from the prior frames in a sequence.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},157985,1787993276,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143,"preview_page_count":4},34359740700684,"https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487","A Computational Model of Comprehension in Manga Style Visual Narratives  \nYi-Chun Chen and Arnav Jhala  \nDepartment of Computer Science  \nNorth Carolina State University  \nRaleigh, NC 27695  \n[f](f ychen74 j ahjhala g@ncsu.edu)[ ychen74](f ychen74 j ahjhala g@ncsu.edu)[ j](f ychen74 j ahjhala g@ncsu.edu)[ ahjhala](f ychen74 j ahjhala g@ncsu.edu)[ g](f ychen74 j ahjhala g@ncsu.edu)[@ncsu.edu](f ychen74 j ahjhala g@ncsu.edu)  \nAbstract  \nUnderstanding a sequence of images as a visual narrative is challenging because it requires not only the understanding of what is shown at a particular moment but also what has changed, been omitted or is out of frame. The human cognitive system makes inferences about the state of the world based on transitions between sequential frames. In this paper, we present a principled analysis of the stylistic differences between two dominant styles of multi-modal narratives, western comics and manga. These two styles differ in terms of screening, ballooning, layout, language, and reading order. We first provide a systematic account of these differences based on an annotated dataset consisting of both comics and manga. We then annotate these datasets with a new feature set and evaluate the contributions of these features through development of a computational model of multi-modal comprehension. The model evaluation is presented through the cloze test that measures the accuracy of the model in predicting unseen next frames given the prior frames in a sequence. Our results provide initial benchmarks and insight into the fundamental challenges that the multi-modal narrative understanding task presents for computational models both for language and vision.  \nKeywords: visual narrative understanding; Japanese manga; comprehension;  \nIntroduction  \nFigure 1: The layout of western comics is mainly on a grid layout and is consistent across the entire story. Manga has more variety of panel arrangements across pages even within the same story.(Examples from \\#446   13, \\#446   17 in COMICS, AosugiruHaru ©Woquda in Manga109)  \nUsing a sequence of images to narrate ideas has a longstanding history in human expression. They occur in different forms which range from ancient cave paintings to modernday comic books (McCloud, 1993) . While a sequence of images generally serves as a visual mode of communicating a  \nnarrative, each culture has its own language that is used in interpretation of the story content. Currently, western comics and Japanese manga are among the more popular sequential visual narratives. They share some common characteristics such as the combination of images and texts, the balance between explicit information and omissions, the exaggerated expressions of emotions and effects, and so on. On the other hand, they also have a number of differences in art style, composition, symbol usages, language etc.  \nThrough the recognition of the content of images, understanding the links between changes, and figuring out causal relations inside comic/manga panels, humans develop a mental model of the story told by the images through the comprehension process. A number of theories have been proposed in cognitive science and media studies ranging from perceptually motivated to higher level discourse understanding motivated. The perceptually motivated ones, such as the Scene Perception and Event Cognition Theory(SPECT), focus on frame-level attentional features such as movement of eyegaze to identify the salient focal points of the frame (Loschkyet al., 2020) . On the other hand, Parallel Interfacing Narrative Semantics(PINS) focuses on overlaying a cognitive model of an event structure in the reader's mind for story understanding at the semantic level (Cohn, 2019) . There is a gap between these models that misses the interpretation that happens in areader's mind due to the changes in frame-level features between consecutive framesFor the understanding of a sequence of images, McCloud provides a discussion of several","cbCaive6BBzuLbNG","https://ap.wps.com/l/cbCaive6BBzuLbNG","pdf",5635768,"English","# Abstract\n# Keywords\n# Introduction\n## Visual syntax differences between comics and manga\n## Cognitive and media theories for narrative comprehension\n## Computational model and dataset contributions\n## Cloze test evaluation setup","[{\"question\":\"Why is understanding a manga or comic sequence of images challenging?\",\"answer\":\"It requires inferring what has changed or been omitted between frames in addition to interpreting the content shown at each moment. These inferences depend on transitions and out-of-frame information.\"},{\"question\":\"What differences between western comics and Japanese manga does the paper analyze?\",\"answer\":\"It compares stylistic differences including screening, ballooning, layout, language, and reading order, supported by an annotated dataset.\"},{\"question\":\"How is the computational model evaluated?\",\"answer\":\"The paper evaluates it using cloze tests that measure how accurately the model predicts unseen next frames from the prior frames in a sequence.\"}]","A Computational Model of Comprehension in Manga Style Visual Narratives | PDF",15]