AI Paper Atlas

Research map / Detection and segmentation / CNN features

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

Mingxin Huang, Jiaxin Zhang, Dezhi Peng, Hao Lu, Can Huang, Yuliang Liu, Xiang Bai, Lianwen Jin

ICCV 2023 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 52 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 explicit synergy (task-aware queries) in the decoder (ablation)ESTextSpotter baseline · Total-Textend-to-end (None): 68.2 -> 70.4Improved
use implicit synergy (shared query) instead of explicit (ablation)ESTextSpotter baseline · Total-Textdetection F: 87.1 -> 84.1Hurt
add explicit synergy over implicit synergy (ablation)ESTextSpotter baseline · Total-Textdetection F: 84.1 -> 87.7Improved
add task-aware query initialization (TAQI) (ablation)ESTextSpotter · Total-Textend-to-end (None): 70.4 -> 70.7Improved
add vision-language communication module (ablation)ESTextSpotter · Total-Textend-to-end (None): 70.7 -> 72.0Improved
add receptive enhancement module (ablation)ESTextSpotter · Total-Textend-to-end (None): 72.0 -> 72.7Improved
add task-aware denoising training (ablation)ESTextSpotter · Total-Textend-to-end (None): 72.7 -> 73.8Improved
add REM to model (ablation)ESTextSpotter · Total-Textdetection F: 88.3 -> 88.2No clear effect
ESTextSpotter vs DeepSolo inference speedESTextSpotter · Total-TextFPS: 17.0 -> 4.3Hurt

Later papers that compared with this method

3 later accepted papers report ESTextSpotter as a baseline in their results tables; 2 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 3 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