AI Paper Atlas

Research map / Detection and segmentation / CNN features

COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa

ECCV 2022 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 31 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
train with polygon instead of bounding box annotation (ablation)ABCNet v2 · COO text detection (test)Hmean: 61.2 -> 66.0Improved
train with polygon instead of bounding box annotation (ablation)MTS v3 · COO text detection (test)Hmean: 62.5 -> 67.8Improved
use segmentation-based MTS v3 instead of regression-based ABCNet v2text detector · COO text detection (test)Hmean: 66.0 -> 67.8Improved
add rotation trick (ablation)TRBA · COO text recognition (test)word accuracy: 46.3 -> 49.8Improved
add SAR decoding alone (ablation)TRBA · COO text recognition (test)word accuracy: 46.3 -> 43.2Hurt
add SAR decoding on top of rotation trick (ablation)TRBA · COO text recognition (test)word accuracy: 49.8 -> 55.4Improved
add Hard RoI masking (ablation)TRBA + rotation + SAR · COO text recognition (test)word accuracy: 55.4 -> 63.5Improved
fill half of each mini-batch with original images with Hard RoI (ablation)TRBA + rotation + SAR · COO text recognition (test)word accuracy: 63.5 -> 67.9Improved
add 2D attention (input height 64) (ablation)TRBA · COO text recognition (test)word accuracy: 67.9 -> 78.5Improved
add 2D attention (input height 100) (ablation)TRBA · COO text recognition (test)word accuracy: 67.9 -> 81.0Improved
use M4C-COO instead of distance rule baselinelink prediction · COO link prediction (test)Hmean: 2.1 -> 72.7Improved
restrict to only five vocabularies instead of 11,640 (ablation)M4C-COO · COO link prediction (test)Hmean: 45.4 -> 72.7Improved

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