Skip to main navigation Skip to search Skip to main content

M2C: Towards Automatic Multimodal Manga Complement

  • Hongcheng Guo
  • , Boyang Wang
  • , Jiaqi Bai
  • , Jiaheng Liu
  • , Jian Yang
  • , Zhoujun Li*
  • *Corresponding author for this work
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features, which has attracted considerable attention from both natural language processing and computer vision communities. Currently, most comics are hand-drawn and prone to problems such as missing pages, text contamination, and aging, resulting in missing comic text content and seriously hindering human comprehension. In other words, the Multimodal Manga Complement (M2C) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for vision and language understanding. To this end, we first propose the Multimodal Manga Complement task by establishing a new M2C benchmark dataset covering two languages. First, we design a manga argumentation method called MCoT to mine event knowledge in comics with large language models. Then, an effective baseline FVP-M2 using fine-grained visual prompts is proposed to support manga complement. Extensive experimental results show the effectiveness of FVP-M2 method for Multimodal Mange Complement.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationEMNLP 2023
PublisherAssociation for Computational Linguistics (ACL)
Pages9876-9882
Number of pages7
ISBN (Electronic)9798891760615
DOIs
StatePublished - 2023
Event2023 Findings of the Association for Computational Linguistics: EMNLP 2023 - Hybrid, Singapore
Duration: 6 Dec 202310 Dec 2023

Publication series

NameFindings of the Association for Computational Linguistics: EMNLP 2023

Conference

Conference2023 Findings of the Association for Computational Linguistics: EMNLP 2023
Country/TerritorySingapore
CityHybrid
Period6/12/2310/12/23

Fingerprint

Dive into the research topics of 'M2C: Towards Automatic Multimodal Manga Complement'. Together they form a unique fingerprint.

Cite this