Abstract: Text-driven medical image segmentation aims to accurately segment pathological regions in medical images based on textual descriptions. Existing methods face two major challenges: (a) The ...
🪓 wtpsplit is a Python package that offers training, inference, and evaluation of state-of-the-art Segment any Text (SaT) models for partitioning text into sentences. ️ wtpsplit-lite is a lightweight ...
Abstract: Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In ...
Chinese seals are widely used in various fields within Chinese society as a tool for certifying legal documents. However, recognizing text on these seals presents challenges due to background text, ...
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation. This is the official repository for Hi-SAM, a unified hierarchical text segmentation model. Refer to our paper for more ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results