Enregistré dans:
Détails bibliographiques
Auteurs principaux: Morin, Lucas, Weber, Valéry, Nassar, Ahmed, Meijer, Gerhard Ingmar, Van Gool, Luc, Li, Yawei, Staar, Peter
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.16096
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912635314765824
author Morin, Lucas
Weber, Valéry
Nassar, Ahmed
Meijer, Gerhard Ingmar
Van Gool, Luc
Li, Yawei
Staar, Peter
author_facet Morin, Lucas
Weber, Valéry
Nassar, Ahmed
Meijer, Gerhard Ingmar
Van Gool, Luc
Li, Yawei
Staar, Peter
contents The automated analysis of chemical literature holds promise to accelerate discovery in fields such as material science and drug development. In particular, search capabilities for chemical structures and Markush structures (chemical structure templates) within patent documents are valuable, e.g., for prior-art search. Advancements have been made in the automatic extraction of chemical structures from text and images, yet the Markush structures remain largely unexplored due to their complex multi-modal nature. In this work, we present MarkushGrapher, a multi-modal approach for recognizing Markush structures in documents. Our method jointly encodes text, image, and layout information through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. These representations are merged and used to auto-regressively generate a sequential graph representation of the Markush structure along with a table defining its variable groups. To overcome the lack of real-world training data, we propose a synthetic data generation pipeline that produces a wide range of realistic Markush structures. Additionally, we present M2S, the first annotated benchmark of real-world Markush structures, to advance research on this challenging task. Extensive experiments demonstrate that our approach outperforms state-of-the-art chemistry-specific and general-purpose vision-language models in most evaluation settings. Code, models, and datasets will be available.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16096
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures
Morin, Lucas
Weber, Valéry
Nassar, Ahmed
Meijer, Gerhard Ingmar
Van Gool, Luc
Li, Yawei
Staar, Peter
Computer Vision and Pattern Recognition
The automated analysis of chemical literature holds promise to accelerate discovery in fields such as material science and drug development. In particular, search capabilities for chemical structures and Markush structures (chemical structure templates) within patent documents are valuable, e.g., for prior-art search. Advancements have been made in the automatic extraction of chemical structures from text and images, yet the Markush structures remain largely unexplored due to their complex multi-modal nature. In this work, we present MarkushGrapher, a multi-modal approach for recognizing Markush structures in documents. Our method jointly encodes text, image, and layout information through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. These representations are merged and used to auto-regressively generate a sequential graph representation of the Markush structure along with a table defining its variable groups. To overcome the lack of real-world training data, we propose a synthetic data generation pipeline that produces a wide range of realistic Markush structures. Additionally, we present M2S, the first annotated benchmark of real-world Markush structures, to advance research on this challenging task. Extensive experiments demonstrate that our approach outperforms state-of-the-art chemistry-specific and general-purpose vision-language models in most evaluation settings. Code, models, and datasets will be available.
title MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16096