AI Paper Atlas

Research map / Detection and segmentation / CNN features

Towards End-to-End Text Spotting in Natural Scenes

Peng Wang, Hui Li, Chunhua Shen

TPAMI 2021 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 42 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 joint training of detection and recognition (ablation)Ours (sep) · ICDAR2015 End-to-End StrongF-measure (%): 79.86 -> 82.21Improved
add joint training (ablation)Ours (sep) · Total-Text End-to-EndF-measure (%): 57.82 -> 58.72Improved
use varying-size RoI pooling instead of fixed 4x20 (ablation)Ours · ICDAR2015 End-to-End StrongF-measure (%): 82.12 -> 82.21Improved
use varying-size RoI pooling instead of fixed 7x7 (ablation)Ours · Total-Text End-to-EndF-measure (%): 50.82 -> 58.72Improved
use varying-size instead of fixed 4x30 RoI pooling (ablation)Ours · ICDAR2015 End-to-End StrongF-measure (%): 81.72 -> 82.21Improved
use LSTM RoI encoding instead of average pooling (ablation)Ours · Total-Text End-to-EndF-measure (%): 55.95 -> 58.72Improved
add FC layer after average pooling (ablation)Ours (AP) · Total-Text End-to-EndF-measure (%): 55.95 -> 57.06Improved
use 2D attention instead of 1D attention (ablation)Ours (1D) · ICDAR2015 End-to-End StrongF-measure (%): 77.40 -> 78.75Improved
add box refinement (ablation)Ours (2D) · Total-Text End-to-EndF-measure (%): 50.39 -> 58.20Improved
add box refinement (ablation)Ours (2D) · ICDAR2013 End-to-End StrongF-measure (%): 92.61 -> 92.61No clear effect
fit 6-point polygons instead of quadrangles (ablation)Ours_Quad · Total-Text End-to-EndF-measure (%): 58.72 -> 59.11Improved
separate LSTM encoders for detection and recognition instead of sharing (ablation)Ours (Shr) · ICDAR2015 End-to-End StrongF-measure (%): 82.43 -> 82.21No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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