AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks

Hui Li, Peng Wang, Chunhua Shen

ICCV 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 228 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 attention to the word decoder (ablation)Ours Atten+Fixed · ICDAR2015 End-to-End (Generic lexicon)F-measure (%): 79.18 -> 83.98Improved
add attention to the word decoder (ablation)Ours Atten+Fixed · SVT Word-Spotting (Strong lexicon)F-measure (%): 79.49 -> 81.80Improved
use varying-size RoI pooling instead of fixed 4x20 (ablation)Ours Atten+Vary · ICDAR2011 Word-Spotting (Generic lexicon)F-measure (%): 83.81 -> 87.70Improved
use varying-size RoI pooling instead of fixed 4x20 (ablation)Ours Atten+Vary · SVT Word-Spotting (Strong lexicon)F-measure (%): 81.80 -> 84.91Improved
use varying-size RoI pooling instead of fixed 4x20 (ablation)Ours Atten+Vary · ICDAR2015 Word-Spotting (Strong lexicon)F-measure (%): 93.33 -> 94.16Improved
train detection and recognition jointly instead of two separate stages (ablation)Ours Atten+Vary · ICDAR2015 End-to-End (Strong lexicon)F-measure (%): 88.20 -> 91.08Improved
train detection and recognition jointly instead of two separate stages (ablation)Ours Atten+Vary · ICDAR2011 Word-Spotting (Generic lexicon)F-measure (%): 82.86 -> 87.70Improved
add recognition loss to detector training (joint multi-task) (ablation)Ours Atten+Vary · ICDAR2015 text detectionF-measure (%): 83.4 -> 85.6Improved
add recognition loss to detector training (joint multi-task) (ablation)Ours Atten+Vary · ICDAR2011 text detectionF-measure (%): 83.5 -> 85.1Improved
share convolutional features between detection and recognition (ablation)Ours Atten+Vary · 600x800 image, M40 GPUrecognition time: 0.45s -> 0.15sImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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