MANPU 2024

The 6th International Workshop on
coMics ANalysis, Processing and Understanding

August 30, 2024
Grand Hyatt Hotel, Athens, Greece

organized in conjunction with ICDAR2024 The 18th International Conference on Document Analysis and Recognition, Grand Hyatt Hotel, Athens, Greece, August 30 - September 4, 2024

Important dates | Registration | Scope and Topics | Datasets | Keynote speech | Program | Organizers | Contact

Program is in public. (updated at July 2nd)

Why should we research on Comics?

Comics is a medium constituted of images combining text and graphics elements. This different visual information is used by the authors to narrate a story. Nowadays, comic books are a widespread cultural expression all over the world and especially in the United States, European countries, and Asian countries. So, the terms of Comics include several categories such as Mangas, American Comics, and Franco-Belgian “Bandes Dessinées”. Each category has its own graphic style. From the research point of view, comics images are attractive targets because the structure of a comics page includes various elements (such as panels, speech balloons, captions, leading characters, text, onomatopoeia, and so on). The design of these elements strongly depends on the creativity of the author and his graphic universe. Consequently, the drawings present a very large variability. Therefore, comics image analysis is not a trivial problem and is still immature compared with other areas of application of image analysis and pattern recognition. Comics offer many challenges for researchers. For example, the detection and recognition of the characters in a comics page are not trivial since the main character can be a human being, an animal, or even an imaginary character. In this context, the “pattern recognition” task is a tricky problem. Comics analysis has aroused interest among researchers. The number of scientific papers dealing with comics analysis has significantly increased in international conferences and journals during the last ten years. The original approaches proposed in these papers in the area of computer vision, pattern recognition, and machine learning, show that comics analysis and understanding can be considered as a research topic. Moreover, the drawings of some comics are very similar to the ones of cartoons. So, some approaches can be applied to both media.

return to top

Important Dates

Title and abstract submission due:   May 7th, 2024 (updated!)
Paper submission due:   May 7th, 2024 (updated!)
Notification of acceptance:   May 27th, 2024
Camera-ready paper due:   June 10th, 2024
Workshop:   August 30th, 2024
return to top


Registration should be done via the 18th International Conference on Document Analysis and Recognition (ICDAR 2024) website.
See detail on ICDAR 2024 registration.
The deadline of the early bird fee is June 1st.


return to top

Scope and Topics

The scope of this workshop includes, but is not limited to,
return to top


To evaluate the proposed works, participants will be able to use the following datasets that are publicly available. Researchers can request to download them at each website.

eBDtheque consists of 100 images with ground truth for panels, speech balloons, tails, text lines, leading characters.

Manga109 consists of over 20 thousand images of 109 volumes (21,142 images).

return to top

Paper Submissions

Submission and Review

All papers will have to be submitted through the EasyChair submission system on or before the submission deadline. Authors can update their papers before the submission deadline. MANPU 2024 will follow a single-blind review process. The accepted papers will be published in the "ICDAR pre-conference volume" edited by Springer in the Lecture Notes in Computer Science (LNCS) series.

Paper format and length

Papers should be formatted with the style files/details available at Information for Authors of Springer Computer Science Proceedings. The LaTeX template for LNCS can be downloaded here. It is also available on Overleaf. Only PDF files are accepted. A complete paper should be submitted in the proper format. Papers accepted for the workshop will be allocated up to 15 pages (usually not counting references) in the proceedings. Submissions are expected to be in the range of 10-15 pages.


Papers should describe original work on an MANPU-related topic. By submitting a manuscript to MANPU 2024, authors acknowledge that it has not been previously published or accepted for publication in substantially similar form in any peer-reviewed venue including journals or conferences. Also authors confirm that no paper substantially similar in content has been or will be submitted to another conference or workshop during the review period. The acceptance of a paper to MANPU 2024 requires that at least one of the authors registers for the workshop and presents the paper there. MANPU 2024 does not allow submission of any additional supplementary file.

Submission site

Paper submissions for MANPU2024 will be handled through the Easy Chair conference management system. Please visit

return to top

Keynote speech

The patterns of global comics
Neil Cohn (Tilburg University)

While sequential images are pervasive in society, from picture books to instruction manuals and storyboards, they appear most complex in comics around the world. Over the past two decades, an increasing focus on corpus analysis has begun to allow greater insights into how comics are structured and comprehended, across work blending manual and computational annotations. Here I will focus on the insights from two corpus projects: the Visual Language Research Corpus (360 comics, 9 countries, 48,000 panels) and the TINTIN Corpus (1,030 comics, 144 countries/territories, 76,000 panels). This analysis will highlight how the structures of comics change over time while interacting with the culture and languages of their authors, revealing distinctive “visual languages” that balance diverse and universal features, consistent with other linguistic systems.

Keynote speaker's Bio

Neil Cohn is an American cognitive scientist best known for his pioneering research on the overlap in cognition between graphic communication and language. He is the author of 2 graphic novels, over 100 academic papers, and 5 academic books, including his most recent, The Patterns of Comics (2024) and A Multimodal Language Faculty (2024). He is an Associate Professor at the Department of Cognition and Communication at Tilburg University in The Netherlands. His work can be found online at

return to top


The workshop time slot is 9:00-17:30 EEST.
Presentation : 20 minutes / Question : 8 minutes.

9:00 - 9:15
Keynote speech
9:15 - 10:45
    The patterns of global comics
Neil Cohn (Tilburg University, Netherlands)
Coffee break
10:45 - 11:15
Oral Session 1 : Comic Understanding
11:15 - 12:45
ComicBERT: A Transformer Model and Pre-training Strategy for Contextual Understanding in Comics
Gürkan Soykan, Deniz Yuret and Tevfik Metin Sezgin (Koç University, Türkiye),
Investigating Neural Networks and Transformer Models for Enhanced Comic Decoding
Eleanna Kouletou (National Kapodistrian University of Athens, Greece), Vassilis Papavassiliou and Vassilis Katsouros (Athena Research Center, Greece),
Spatially Augmented Speech Bubble to Character Association via Comic Multi-Task Learning
Gürkan Soykan, Deniz Yuret and Tevfik Metin Sezgin (Koç University, Türkiye),
12:45 - 13:15
Lunch break
13:15 - 14:15
Oral Session 2 : Comic Utilization
14:15 - 15:45
Comics Datasets Framework: Mix of Comics datasets for detection benchmarking
Emanuele Vivoli (Computer Vision Center, UAB, Spain), Irene Campaioli, Mariateresa Nardoni, Niccolò Biondi, Marco Bertini (MICC, University of Florence, Italy) and Dimosthenis Karatzas (Computer Vision Center, UAB, Spain)
Toward accessible comics for blind and low vision readers
Christophe Rigaud, Jean-Christophe Burie (L3i Laboratory, La Rochelle, France) and Samuel Petit (Comix AI, France)
Quantitative evaluation based on CLIP for methods inhibiting imitation of painting styles
Motoi Iwata, Keito Okamoto and Koichi Kise (Osaka Metropolitan University, Japan)
Coffee break
15:45 - 16:15
Oral Session 3 : Text Detection, Recognition and Analysis
16:15 - 17:15
A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition
Gürkan Soykan, Deniz Yuret and Tevfik Metin Sezgin (Koç University, Türkiye),
Retrieving and Analyzing Translations of American Newspaper Comics with Visual Evidence
Jacob Murel and David Smith (Northeastern University, USA)
Conclusion & Closing
17:15 - 17:30

return to top


General Co-Chairs
Jean-Christophe Burie             University of La Rochelle, France
Motoi Iwata             Osaka Metropolitan University, Japan
Yusuke Matsui     The University of Tokyo, Japan

Program Co-Chairs
Rita Hartel                 Paderborn University, Germany
Tien-Tsin Wong           The Chinese University of Hong Kong, Hong Kong
Ryosuke Yamanishi           Kansai University, Japan

Advisory Board
Kiyoharu Aizawa                 The University of Tokyo, Japan
Koichi Kise                 Osaka Metropolitan University, Japan
Jean-Marc Ogier                 University of La Rochelle, France
Toshihiko Yamasaki             The University of Tokyo, Japan

Program Committee
Olivier Augerau     Ecole nationale d’ingénieurs de Brest, France
John Bateman     University of Bremen, Germany
Ying Cao     ShanghaiTech University, China
Wei-Ta Chu     National Chung Cheng University, Taiwan
Alexander Dunst     TU Dortmund University, Germany
Felix Giesa     Goethe University Frankfurt, Germany
Seiji Hotta     Tokyo University of Agriculture and Technology, Japan
Rynson W. H. Lau     City University of Hong Kong, Hong Kong
Jochen Laubrock     University of Potsdam, Germany
Tong-Yee Lee     National Cheng-Kung University, Taiwan
Chengze Li     St. Francis University, Hong Kong
Xueting Liu     The Chinese University of Hong Kong, Hong Kong
Muhammad Muzzamil Luqman     University of La Rochelle, France
Mitsunori Matsushita     Kansai University, Japan
Naoki Mori     Osaka Metropolitan University, Japan
Mitsuharu Nagamori     University of Tsukuba, Japan
Satoshi Nakamura     Meiji University, Japan
Frédéric Rayar     Tours University, France
Christophe Rigaud     University of La Rochelle, France
Yasuyuki Sumi     Future University Hakodate, Japan
Miki Ueno     The Kyoto College of Graduate Studies for Informatics, Japan
Emanuele Vivoli     CVC, Autonomous University of Barcelona, Spain
John Walsh     Indiana University, USA
Minshan Xie     The Chinese University of Hong Kong, Hong Kong
Lvmin Zhang     Stanford University, USA

return to top


Workshop Secretariat:
i-m-manpu2024-inquiry [at]
[at] -> @
return to top