Filters








51 Hits in 12.6 sec

Deep CNN-based Speech Balloon Detection and Segmentation for Comic Books [article]

David Dubray, Jochen Laubrock
2019 arXiv   pre-print
We develop a method for the automated detection and segmentation of speech balloons in comic books, including their carrier and tails.  ...  Our method is based on a deep convolutional neural network that was trained on annotated pages of the Graphic Narrative Corpus.  ...  [28] describe a multi-task learning model for comic book image analysis derived from on Mask R-CNN [14] that defines the current state-of-the-art in detection and segmentation of several object categories  ... 
arXiv:1902.08137v1 fatcat:mwpogbg2jfgozdu3qbwx5wyo4i

Deep learning for graphics recognition: document understanding and beyond

Jean-Christophe Burie, Alicia Fornés, K. C. Santosh, Muhammad Muzzamil Luqman
2021 International Journal on Document Analysis and Recognition  
The article "CNN based segmentation of speech balloons and narrative text boxes from comic book page images" by Arpita Dutta, Samit Biswas and Amit Kumar Das addresses the problem of segmentation of speech  ...  balloons and narrative text boxes in comics.  ... 
doi:10.1007/s10032-021-00372-6 fatcat:hc4v4eefdrfuxo7w3kg4cohcsi

The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives [article]

Mohit Iyyer, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daumé III, Larry Davis
2017 arXiv   pre-print
An in-depth analysis of COMICS demonstrates that neither text nor image alone can tell a comic book story, so a computer must understand both modalities to keep up with the plot.  ...  in comic book panels.  ...  Comics are not just visual: creators push their stories forward through text-speech balloons, thought clouds, and narrative boxes-which we identify and transcribe using optical character recognition (OCR  ... 
arXiv:1611.05118v2 fatcat:ip5xbrrmy5fq5jvcpu22biodhu

The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives

Mohit Iyyer, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daume, Larry Davis
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
An in-depth analysis of COMICS demonstrates that neither text nor image alone can tell a comic book story, so a computer must understand both modalities to keep up with the plot.  ...  in comic book panels.  ...  Comics are not just visual: creators push their stories forward through text-speech balloons, thought clouds, and narrative boxes-which we identify and transcribe using optical character recognition (OCR  ... 
doi:10.1109/cvpr.2017.686 dblp:conf/cvpr/IyyerMGVBDD17 fatcat:genohljcvncphbyy5x4awk3the

Video Analysis and Summarization at Structural and Semantic Levels [chapter]

Hari Sundaram, Shih-Fu Chang
2003 Signals and Communication Technology  
The segmentation of video data into manageable chunks is complicated by the presence of complex interactions between audio and video data (e.g. films).  ...  Domain dependent syntactical elements (e.g. dialogs) further complicate the segmentation task. There has been prior work on video scene segmentation using image data alone [24] [59].  ...  Acknowledgements We would like to sincerely appreciate the help and valuable input provided by Ana Benitez, Shahram Ebadollahi, Alejandro Jaimes, and Lexing Xie.  ... 
doi:10.1007/978-3-662-05300-3_4 fatcat:d7wgof37ofhlpezr6mco2a3b7i

Manga vision: cultural and communicative perspectives

Bounthavy Suvilay
2017 Journal of Graphic Novels and Comics  
Irving, Erica Koh and James Rampant of the Monash University Japanese Studies Centre Manga Library.  ...  Appendix: Manga Panel Layout faCtoRs infLuenCing non-natiVe ReaDeRs' sequenCing of jaPanese Manga PaneLs Acknowledgements Data entry for this project was greatly assisted by Katherine Pickhaver, Rebecca  ...  This results in a slightly mismatched narrative flow. Most publishers leave the word bubbles (also known as speech balloons) untouched visually, and translate only the text inside the balloons.  ... 
doi:10.1080/21504857.2017.1403340 fatcat:cdwrh63zyndndng2gbjppnm24a

Disappear here: violence after Generation X

2015 ChoiceReviews  
Though the song is not identified in the novel, Baelo-Allué suggests that Clay is referring to "Los Angeles" from the 1980 album by the punk rock band X (60).  ...  We are cooks and taxi drivers. We are everyone you come into contact with on a daily bases. We know everything about you. We process your insurance claims and credit card charges.  ...  We control every part of your life . Together we  ... 
doi:10.5860/choice.194366 fatcat:3lgcnbvj4ng53hhqvrf3lje2ny

Truth & Beauty Bombs: The personal/political/poetics of online communication in #archaeology. #PATC Keynote, April 27th 2017

Colleen Morgan
2017 Epoiesen: A Journal for Creative Engagement in History and Archaeology  
CNNS web pages contain audio and video clips from the same feeds available to their television network; the front page and the web site of USA Today are similar in style and content ( fig. 1.6 and 1.7  ...  FANTASY AND ALLEGORY Digital art often refashions popular illustrarion-above all, science fiction and fantasy illustration from comic books and pulp-fiction book covers.  ...  It is true thilr virtual reality depends on a mathemarization of space that derives from Descartes and from technologies of representation like linear perspective.  ... 
doi:10.22215/epoiesen/2017.12 fatcat:imta2rayurctllvmv4gelwai2u

The construction of 'Nature' in the virtual worldSecond Life

Joseph S. Clark
2015 Environmental Education Research  
A charmed circle of warm, friendly, funny, and smart graduate students shared the journey with me and accepted this mid-lifer as one of their own. Faculty in FSU'  ...  ACKNOWLEDGMENTS My doctoral advisor Andy Opel green-lit the genesis of this project in 2007 while I was taking his class in Media and the Environment.  ...  Unfortunately, the only Second Life narrative that has seemed to gain any traction is one of sensationalistic sex and violence, not unlike the usual moral panics over new media (everything from comic books  ... 
doi:10.1080/13504622.2015.1118754 fatcat:ohecewoajrgrfoc5lai23afbn4

Turning The Page: Fandoms, Multimodality, And The Transformation Of The ' comic Book' Superhero Recommended Citation

Matthew Cicci, Matthew Cicci, Alan, Matthew Cicci Dissertation
2015 unpublished
mediums] that it can from comic books" (16) And, while invariably true, the narrative medium of entertainment that presented superheroes was the comic book.  ...  As it operates on a screen, there is no real page which has long been an evident and thus useful narrative divide for comic books.  ...  adaptations, from 1998 on, have not only caused the filmic superhero to eclipse the comic one, it has inevitably led to a rewriting of superhero comic book form and narrative canon to capitalize on the  ... 
fatcat:g7th6nnaozcvhkkcatvxay6fai

Abstracts of the 20th European Conference on Eye Movements, 18-22 August 2019, in Alicante (Spain)

Susana Martinez-Conde, Luis Martinez-Otero, Albert Compte, Rudolf Groner
2019 Journal of Eye Movement Research  
This document contains all abstracts of the 20th European Conference on Eye Movements, August 18-22, 2019, in Alicante, Spain Video stream "Glimpses at 20th ECEM": https://vimeo.com/user43478756.  ...  Reward was calculated as a fraction of the maximum depending on the performance (accuracy and speed).  ...  Both tasks involved three incentive levels indicated by an auditory cue before the start of each saccade.  ... 
doi:10.16910/jemr.12.7.1 pmid:33828763 pmcid:PMC7917478 fatcat:wqzwn552cndsnablyikzx3og5e

Multi-view representation learning for natural language processing applications [article]

Nikolaos Papasarantopoulos, University Of Edinburgh, University Of Edinburgh, Shay Cohen, Stephen Renals
2020
Examples include, but are not restricted to, multimodal datasets, where data may consist of audio, image and/or text.  ...  This thesis argues that more complex downstream applications could benefit from such representations and describes a multi-view contemplation of a range of tasks, from static, two-view, unimodal to dynamic  ...  The three modalities included are text scripts (dialogue subtitles and background scene descriptions), image snapshots from the video and audio segments.  ... 
doi:10.7488/era/267 fatcat:f7tjkwf6prc3zb74oh653zav5a

In 2016 – How it felt to live in the Arab World five years after the "Arab Spring"

Albrecht Hofheinz (ed.), Stephan Guth (ed.)
2022 Journal of Arabic and Islamic studies  
Results of a research project, carried out between 2015 and 2018 at the Dept. of Culture Studies and Oriental Languages (IKOS), University of Oslo, Norway, funded by the Research Council of Norway (RCN  ...  Arrays, Codes, and Collapsed Codes of Egyptian and Tunisian lifeworlds five years after the so-called "Arab Spring".  ...  distinguish the narrative of this movie from the narrative of the propaganda?"  ... 
doi:10.5617/jais.9464 fatcat:foviyqo24bhivdnjfhhamkzwgq

The Mass Media in Vietnam

John A. Lent, David G. Marr
2002 Journal of Asian Studies  
Even in Hue, a city noted for its cultural heritage and pride, the three or four small bookshops contain mostly public school texts, fiction, popularized history, comic books and a smattering of titles  ...  Such ideological text continues to mark Vietnamese media literature whether it is in the form of a training manual for journalists or historical narratives about the development of the press.  ...  developing country undergoing rapid social change as it attempts to catch up with the rest of the world.  ... 
doi:10.2307/2700371 fatcat:vmwgzqc37bcj3nccndmu4ckjam

Reading Bodies: Disability And American Literary History, 1789-1889

Amanda Stuckey
2017
Individuals and communities reading, writing, and responding to the genres of seduction, historical fiction, slave narrative, Civil War poetry, and children's literature both deployed and challenged formal  ...  "Reading Bodies" intervenes in these fields with the claim that the book in a variety of formats, publications, and circulations acts as a disciplinary tool that seeks to arrange physical and mental characteristics  ...  Before the description, however, comes an image that fills the remainder of the page: an imposing, horse-powered machine with menacing boxes and screws, from which one person is suspended while another  ... 
doi:10.21220/s2436m fatcat:b7qtf3xywve57gclfauwuq6goe
« Previous Showing results 1 — 15 out of 51 results