Zhicheng He

Zhicheng He

he/him

First-year graduate student in the Department of Biomedical Engineering at the National University of Singapore (NUS).
Research interests: medical image analysis and multi-modal large language models.

SSSI: Self-prompted Segmentation of Scientific Illustrations

Published in International Conference on Document Analysis and Recognition (ICDAR), 2025

We propose a self-prompted segmentation of scientific illustrations (SSSI) framework, which automatically utilizes the geometric relationships between text and subregions to generate point and bounding box prompts suitable for SAM. SSSI employs a two-stage processing pipeline for segmenting complex flowcharts in scientific papers.

Recommended citation: Tuo Wang, Yixiao Zhou, Tongwei Zhang, Zhicheng He, Yumeng Zhao, Xiaoqing Lyu. (2025). "SSSI: Self-prompted Segmentation of Scientific Illustrations." International Conference on Document Analysis and Recognition, Pages 347-361.
Download Paper