# Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion

arXiv: https://arxiv.org/abs/2404.13993 · HTML: https://mlsanity.com/paper/2404.13993/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Towards Fully Automated Manga Translation](https://mlsanity.com/paper/2012.14271/) (2020)
- [Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection](https://mlsanity.com/paper/2306.17469/) (2023)
- [Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering](https://mlsanity.com/paper/2204.04621/) (2022)

## Built on by (most cited first, 9 of 9)

- [CHIRON: Rich Character Representations in Long-Form Narratives](https://mlsanity.com/paper/2406.10190/) (2024)
- [MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding](https://mlsanity.com/paper/2505.20298/) (2025)
- [From Panels to Prose: Generating Literary Narratives from Comics](https://mlsanity.com/paper/2503.23344/) (2025)
- [Toward accessible comics for blind and low vision readers](https://mlsanity.com/paper/2407.08248/) (2024)
- [Generating Visual Stories with Grounded and Coreferent Characters](https://mlsanity.com/paper/2409.13555/) (2024)
- [Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation](https://mlsanity.com/paper/2504.14249/) (2025)
- [ComicScene154: A Scene Dataset for Comic Analysis](https://mlsanity.com/paper/2508.16190/) (2025)
- [Emotion-Aware Speech Generation with Character-Specific Voices for Comics](https://mlsanity.com/paper/2509.15253/) (2025)
- [Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga](https://mlsanity.com/paper/2610.13840/) (2026)

## Abstract (arXiv)

Recognizing characters and predicting speakers of dialogue are critical for comic processing tasks, such as voice generation or translation. However, because characters vary by comic title, supervised learning approaches like training character classifiers which require specific annotations for each comic title are infeasible. This motivates us to propose a novel zero-shot approach, allowing machines to identify characters and predict speaker names based solely on unannotated comic images. In spite of their importance in real-world applications, these task have largely remained unexplored due to challenges in story comprehension and multimodal integration. Recent large language models (LLMs) have shown great capability for text understanding and reasoning, while their application to multimodal content analysis is still an open problem. To address this problem, we propose an iterative multimodal framework, the first to employ multimodal information for both character identification and speaker prediction tasks. Our experiments demonstrate the effectiveness of the proposed framework, establishing a robust baseline for these tasks. Furthermore, since our method requires no training data or annotations, it can be used as-is on any comic series.