computer-vision-7

Hierarchical Text Segmentation

3260 papers • 126 benchmarks • 313 datasets

Segment strokes, words, text-lines, paragraphs (layout analysis) in images within a unified framework

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in hierarchical-text-segmentation-7

Trend

Dataset

Best Model

Actions

HierText

Libraries

i

Use these libraries to find hierarchical-text-segmentation-7 models and implementations

Datasets

HierText

Subtasks

No subtasks available.

Most implemented papers

Hierarchical Text Segmentation for Medieval Manuscripts

Dominique Stutzmann, Christopher Kermorvant, B. Daille, Amir Hazem, Louis Chevalier•Mon Dec 07 2020

It is shown that the main state-of-the-art segmentation methods are either inefficient or inapplicable for books of hours and a bottom-up greedy approach is proposed that considerably enhances the segmentation results.

8

Content

0

Paper Graph

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

Dacheng Tao, Bo Du, Maoyuan Ye, Jing Zhang, Juhua Liu, Chenyu Liu, Baocai Yin, Cong Liu•Tue Jan 30 2024

This paper first turns SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach, and uses this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset.

32 0

Paper Graph

Adding a benchmark result helps the community track progress.