Feature visualization in comic artist classification using deep neural networks

Kim, Young‐Min

doi:10.1186/s40537-019-0222-3

Cited by 16 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each chapter in the comic features panels, balloons, and narration to explain the conditions on the panel, and a gutter serves as a divider between panels (Beard & Rhodes, 2002). Components in comics are the most significant aspects for describing events and allowing comic readers to envision themselves as if they were personally participating in the comic tale (Young-Min, 2019). Word balloons come in various shapes and may express the intonation of voice in each comic character so that every event can be portrayed on comic balloons, and intonation that appears to be removed from a comedy character can be depicted using word balloons (Seko & Kikuchi, 2021).…”

Section: The Results Of Observing the Completeness Of Comic Elementsmentioning

confidence: 99%

Manga versus webtoon: Alternative science learning module based on Dr Stone

Septaria

2022

jipi

View full text Add to dashboard Cite

Reading activities for junior high school students in Indonesia are carried out at school when the instructor requests that they study the learning topic being taught, therefore learners may become bored due to the thickness of the available books. Indonesian students are more likely to read when they encounter visualizations in the form of images and a small amount of text, which are commonly referred to as comics. There are numerous popular comics that students like reading, such as manga and webtoons, but it is extremely uncommon to discover a popular comic that teaches the subject of a certain discipline, particularly natural sciences, which has a tough scientific picture. The purpose of this study is to examine the many forms of manga comics and webtoons that may be utilized as alternative student learning modules when students study from home without regard for space or time constraints in the midst of the covid-19 epidemic. The descriptive qualitative research approach was applied. Manga comics, particularly Dr. Stone's manga, were shown to be more acceptable for use as alternative scientific learning modules in junior high schools, both in terms of completeness of module parts and learning contexts. Comic Dr. Stone is able to boost learners' cognitive and psychomotor skills by vividly seeing daily situations. This research is intended to be expanded by further researchers in order to give more alternative module alternatives for students and to aid teachers in educating Indonesian learners.

show abstract

Section: The Results Of Observing the Completeness Of Comic Elementsmentioning

confidence: 99%

Manga versus webtoon: Alternative science learning module based on Dr Stone

Septaria

2022

jipi

View full text Add to dashboard Cite

show abstract

“…Feature visualization has been widely studied in computer vision ( Zeiler and Fergus, 2014 ; Yosinski et al, 2015 ; Olah et al, 2017 ), but few studies have been conducted on sketches and drawings. Young-Min (2019) studied the visual characteristics involved in comic book page classification. First, they designed a model to classify comic book pages between several comic artists.…”

Section: Approaches In Deep Learning For Drawing(s) Analysismentioning

confidence: 99%

Deep learning for studying drawing behavior: A review

Beltzung

Péle²,

Renoult³

et al. 2023

Front. Psychol.

View full text Add to dashboard Cite

In recent years, computer science has made major advances in understanding drawing behavior. Artificial intelligence, and more precisely deep learning, has displayed unprecedented performance in the automatic recognition and classification of large databases of sketches and drawings collected through touchpad devices. Although deep learning can perform these tasks with high accuracy, the way they are performed by the algorithms remains largely unexplored. Improving the interpretability of deep neural networks is a very active research area, with promising recent advances in understanding human cognition. Deep learning thus offers a powerful framework to study drawing behavior and the underlying cognitive processes, particularly in children and non-human animals, on whom knowledge is incomplete. In this literature review, we first explore the history of deep learning as applied to the study of drawing along with the main discoveries in this area, while proposing open challenges. Second, multiple ideas are discussed to understand the inherent structure of deep learning models. A non-exhaustive list of drawing datasets relevant to deep learning approaches is further provided. Finally, the potential benefits of coupling deep learning with comparative cultural analyses are discussed.

show abstract

“…Accelerated by the large-scale digitization efforts of cultural institutions, increasing attention is given to the development of multimedia methods for cultural heritage material [8, 16-18, 20, 21]. However, the majority of these works consider the analysis of still images such as paintings and drawings [18,20], scanned newspaper pages [21], and to a lesser extent comic books [22]. Nonetheless, these relate to ours in that they explore how and to what extent approaches developed and trained on contemporary material can be re-purposed for historical material or material which is visually distinct from typical training data.…”

Section: Visual Cultural Heritage Analysismentioning

confidence: 99%