AI Paper Atlas

Research map / Detection and segmentation / CNN features

Detection and Recognition of Text Embedded in Online Images via Neural Context Models

Chulmoo Kang, Gunhee Kim, Suk Yoo

AAAI 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 27 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 local neighbor-box context to text detection (ablation)CTSN · Instagramdetection F1: 29.2 -> 55.5Improved
add local neighbor-box context to text detection (ablation)CTSN · Flickrdetection F1: 34.0 -> 55.5Improved
add metadata topic bias (LDA) to word recognition (ablation)CTSN · Instagramcropped-word recognition accuracy: 87.3 -> 90.4Improved
add metadata topic bias (LDA) to word recognition (ablation)CTSN · Flickrcropped-word recognition accuracy: 90.3 -> 93.0Improved
add both detection and recognition context (ablation)CTSN · Instagramend-to-end F1: 18.9 -> 43.3Improved
add both detection and recognition context (ablation)CTSN · Flickrend-to-end F1: 20.0 -> 39.7Improved
use CTSN with context instead of best baseline TERtext detection · Instagramdetection F1: 46.3 -> 55.5Improved

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