atlas

Research map / Detection and segmentation / CNN features

Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

CVPR 2018 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 395 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use corner localization and position-sensitive segmentation instead of direct text-box regressionScene text detection on ICDAR2015 · ICDAR2015F-measure: 53.3 vs 80.7Helped
Use multi-scale inputsThe proposed detector · ICDAR2015F-measure: 80.7 -> 84.3Helped
Use multi-scale inputsThe proposed detector · ICDAR2013F-measure: 85.8 -> 88.0Helped
Use multi-scale inputsThe proposed detector · MLTF-measure: 66.8 -> 72.4Helped
Use multi-scale inputsThe proposed detector · COCO-Text V1.1F-measure: 38.1 -> 42.5Helped
Use multi-scale inputsThe proposed detector · COCO-Text Challenge IoU 0.5F-measure: 61.1 -> 62.6Helped
Use multi-scale inputsThe proposed detector · COCO-Text Challenge IoU 0.75F-measure: 34.6 -> 34.9Helped

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