AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

ST-SAM: Multimodal Scene Text Segmentation with Dense Visual and Sparse Textual Prompts via SAM

Jin Wei, Yaqiang Wu, Jiayi Yan, Zeng Li, Zhen Xu, Yu Zhou, Lingling Zhang, QianYing Wang

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adapters to SAM ViT encoder (ablation)SAM-B · ICDAR13 FSTfgIoU: 65.70 -> 68.18Improved
add dense visual prompts (ablation)ST-SAM-B (adapter only) · ICDAR13 FSTfgIoU: 68.18 -> 69.52Improved
add dense visual prompts (ablation)ST-SAM-B with text prompts · ICDAR13 FSTfgIoU: 69.48 -> 71.18Improved
generate text prompts with GPT-4 instead of plain 'Text' (ablation)ST-SAM-B · ICDAR13 FSTfgIoU: 70.10 -> 71.18Improved
replace concatenation of text prompts with cross-modal alignment (ablation)ST-SAM-B · ICDAR13 FSTfgIoU: 68.49 -> 71.18Improved
add concatenation of text prompts instead of alignment (ablation)ST-SAM-B visual prompt model · ICDAR13 FSTfgIoU: 69.52 -> 68.49Hurt
add learnable scenario-specific prompt to LLM prompts (ablation)ST-SAM-B · ICDAR13 FSTfgIoU: 71.18 -> 72.62Improved
add LLM-generated prompts to scenario-specific prompt (ablation)ST-SAM-B · ICDAR13 FSTfgIoU: 70.99 -> 72.62Improved
use ST-SAM-B instead of Hi-SAM-BSAM ViT-B · HierTextfgIoU: 73.39 -> 75.69Improved
ST-SAM-B vs Hi-SAM-B trained on TextSeg, tested on Total-TextSAM ViT-B · TextSeg to Total-TextF-score: 82.27 -> 86.56Improved
use ST-SAM-B instead of UPOCR on difficult casesSAM ViT-B · Total-Text difficult subsetfgIoU: 76.34 -> 80.67Improved
ST-SAM-B vs EAFormer on Total-TextST-SAM-B · Total-TextfgIoU: 82.73 -> 82.36No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy