AI Paper Atlas

Research map / Detection and segmentation / CNN features

AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting

Wenhai Wang, Xuebo Liu, Xiaozhong Ji, Enze Xie, Ding Liang, ZhiBo Yang, Tong Lu, Chunhua Shen, Ping Luo

ECCV 2020 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 23 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 the language module to re-score candidate text lines (ablation)AE TextSpotter · TDA-ReCTSF-measure: 77.93 -> 81.39Improved
add the language module to re-score candidate text lines (ablation)AE TextSpotter · TDA-ReCTS1-NED: 47.74 -> 51.32Improved
add the language module to re-score candidate text lines (ablation)AE TextSpotter · IC19-ReCTS testF-measure: 91.16 -> 91.80Improved
add the language module to re-score candidate text lines (ablation)AE TextSpotter · IC19-ReCTS test1-NED: 70.95 -> 71.81Improved
add the CRM-based recognition and visual-only scoring on top of detection only (ablation)AE TextSpotter w/o LM · TDA-ReCTSF-measure: 77.19 -> 77.93Improved
enlarge input short side from 800 to 1000AE TextSpotter · IC19-ReCTS testF-measure: 91.80 -> 91.86Improved
enlarge input short side from 800 to 1000AE TextSpotter · IC19-ReCTS test1-NED: 71.81 -> 73.12Improved
use loose TDM thresholds (score 0.01, NMS 0.9) instead of common ones (0.5, 0.5) (ablation)Text detection module · TDA-ReCTSrecall: 0.852 -> 0.969Improved
loosen thresholds from (0.01, 0.9) to (0.0, 1.0) (ablation)Text detection module · TDA-ReCTSrecall: 0.969 -> 0.971No clear effect
replace CRNN with the character-based recognition module (ablation)AE TextSpotter recognition · IC19-ReCTS testrecognition time per image (ms): 966.7 -> 122.3Improved
replace ASTER with the character-based recognition module (ablation)AE TextSpotter recognition · IC19-ReCTS testrecognition time per image (ms): 4828.2 -> 122.3Improved

Later papers that compared with this method

1 later accepted paper reports AE TextSpotter as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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