Reproduce “One missing piece in Vision and Language: A Survey on Comics Understanding” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Emanuele Vivoli, Mohamed Ali Souibgui, Andrey Barsky, Artemis LLabrés, Marco Bertini, Dimosthenis Karatzas
The paper presents LoCU, a Vision–Language taxonomy that organizes comics research by input and output modalities and by spatial and temporal scope. The survey maps 31 multimodal tasks into 10 groups across five layers, from image processing to higher-level understanding and generation. It clarifies dependencies and exposes sparse data and unresolved task-definition gaps, not system performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.