Inferring artistic intention in comic art through viewer gaze

Jain, Eakta; Sheikh, Yaser; Hodgins, Jessica K.

doi:10.1145/2338676.2338688

Cited by 22 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Use of eyetracking data is consistent with other multimedia learning studies (e.g., [100]). Our study confirms prior comic eye-tracking studies [57,81] 21 two-part interviews were audio recorded and transcribed verbatim by the experimenter. Data was coded using the online data analysis application Dedoose [28].…”

Section: Interview and Eye-tracking Study Of The Password Comicsupporting

confidence: 84%

Improving Mental Models of Computer Security Through Information Graphics

Zhang-Kennedy¹

View full text Add to dashboard Cite

Many users have difficulties making effective security decisions. Education is one way to improve users' mental models of computer security, but a common challenge is that users are not motivated to learn about security. We propose that a visual approach to education can improve comprehension and engagement with security information. This thesis examines whether information graphics form an effective, memorable, and persuasive method of communication to increase computer security understanding and improve user behaviour. Guided by visual-textual strategies developed in education literature, we designed seven pieces of instructional materials that help end-users learn about password guessing attacks and antivirus protection. These include five infographic posters and two online interactive comics. Five one-week user studies with a total of 145 participants show that information graphics led to superior learning outcomes and a better user experience than existing text-alone approaches. Participants showed an increase of comprehension, retention, and improved behaviour after one week. First and foremost, I would like to express my gratitude to my supervisors. Without their encouragement and guidance this thesis would not have materialized. I would like to thank Sonia Chiasson for her extraordinary dedication to her students. You helped me in my journey to complete a Masters degree in every way possible, and I can't say thank you enough for your tremendous support and help. I would like to thank Robert Biddle for sharing his inspiration, insight, and passion for research. Your wisdom and the advice you gave me kept me on the right track throughout my degree. Many thanks to the members of my committee, Ali Arya, David Mould, and Dwight Deugo, for your time and feedback. I would like to thank my parents for their love and support in pursuing all of my life's passions and interests. Lastly, I would like to thank my husband Matt, who turned out to be an excellent unofficial graduate guidance counsellor. Thank you for believing in me. I cherish your love and continuous support. iii

show abstract

Section: Interview and Eye-tracking Study Of The Password Comicsupporting

confidence: 84%

Improving Mental Models of Computer Security Through Information Graphics

Zhang-Kennedy¹

View full text Add to dashboard Cite

show abstract

“…Omori et al [2004] investigated factors that may guide eye movements during manga reading, and found that there is a strong link between eye movements and balloon positions. Jain et al [2012] experimentally confirmed that comic artists direct viewer attention through element composition, by measuring the consistency of eye movements across different viewers. However, none of these works present a model or algorithm for composing subjects and balloons.…”

Section: Related Workmentioning

confidence: 70%

“…We recorded the eye movements of 10 participants on the 11 pairs of compositions used in the visual perception study, with 5 on our results and another 5 on the results by the heuristic method. Following Jain et al [2012], we measure the consistency in both unordered and ordered eye fixations across different viewers.…”

Section: Comparison To Heuristic Methodsmentioning

confidence: 99%

Look over here

2014

View full text Add to dashboard Cite

Picture subjects and text balloons are basic elements in comics, working together to propel the story forward. Japanese comics artists often leverage a carefully designed composition of subjects and balloons (generally referred to as panel elements ) to provide a continuous and fluid reading experience. However, such a composition is hard to produce for people without the required experience and knowledge. In this paper, we propose an approach for novices to synthesize a composition of panel elements that can effectively guide the reader's attention to convey the story. Our primary contribution is a probabilistic graphical model that describes the relationships among the artist's guiding path, the panel elements, and the viewer attention, which can be effectively learned from a small set of existing manga pages. We show that the proposed approach can measurably improve the readability, visual appeal, and communication of the story of the resulting pages, as compared to an existing method. We also demonstrate that the proposed approach enables novice users to create higher-quality compositions with less time, compared with commercially available programs.

show abstract

“…Jain et al () compared the similarity of different viewers' scanpaths between comics, amateur snapshots, and robot pictures, finding the most coherent viewing behavior for comics. They conclude that artists are successful in guiding their readers' attention.…”

Section: Reading Of Comicsmentioning

confidence: 99%

Computational Approaches to Comics Analysis

Laubrock

Dunst

2019

Topics in Cognitive Science

View full text Add to dashboard Cite

Comics are complex documents whose reception engages cognitive processes such as scene perception, language processing, and narrative understanding. Possibly because of their complexity, they have rarely been studied in cognitive science. Modeling the stimulus ideally requires a formal description, which can be provided by feature descriptors from computer vision and computational linguistics. With a focus on document analysis, here we review work on the computational modeling of comics. We argue that the development of modern feature descriptors based on deep learning techniques has made sufficient progress to allow the investigation of complex material such as comics for reception studies, including experimentation and computational modeling of cognitive processes.

show abstract

Inferring artistic intention in comic art through viewer gaze

Cited by 22 publications

References 21 publications

Improving Mental Models of Computer Security Through Information Graphics

Improving Mental Models of Computer Security Through Information Graphics

Look over here

Computational Approaches to Comics Analysis

Contact Info

Product

Resources

About