atlas

Research map / Detection and segmentation / CNN features

Multi-Scale FCN With Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting in the Wild

CVPR 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 88 citations (OpenAlex)

Check 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 the cascaded text-block FCN and instance segmentation instead of tian[31]Scene text detection · ICDAR 2013F-measure: 88 -> 85Hurt
Use the cascaded text-block FCN and instance segmentation instead of tian[31]Scene text detection · ICDAR 2015F-measure: 61 -> 63Helped
Use the cascaded text-block FCN and instance segmentation instead of He [10]Scene text detection · SVTrecall: 75 -> 78Helped
Use the cascaded text-block FCN and instance segmentation instead of Risnumawan [26]Scene text detection · CUTE80recall: 68 -> 73Helped
Replace a single-branch FCN with a multi-scale, shared-net FCN (ablation)Text block detection · Text block detection examplestext detection qualityHelped
Add randomized variation to text-center-line training examples (ablation)IA-CNN · IA-CNN training examplesinstance segmentation qualityHelped
Use per-scale loss when training the multi-scale FCN (ablation)Multi-scale, shared-net FCN · Text block detectiontext detection performanceHelped

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