AI Paper Atlas

Research map / Detection and segmentation / CNN features

LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting

Yuchen Su, Zhineng Chen, Yongkun Du, Zuxuan Wu, Hongtao Xie, Yu–Gang Jiang

TPAMI 2026 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 3 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
use contour-driven instead of mask-driven representation (ablation)LRA · CTW1500E2E F-measure: 65.1 -> 67.7Improved
use contour-driven instead of side-driven representation (ablation)LRA · CTW1500E2E F-measure: 67.3 -> 67.7Improved
increase orthanchor dimension from 10 to 14 (ablation)LRANet++ · CTW1500IoU: 95.8 -> 98.1Improved
increase orthanchor dimension from 14 to 18 (ablation)LRANet++ · CTW1500detection F-measure: 87.2 -> 87.1No clear effect
use FMS instead of SVD under 20% label noise (ablation)LRA projection · CTW1500IoU: 93.6 -> 97.2Improved
use FMS instead of SVD at dimension 6 (ablation)LRA projection · CTW1500 curved subsetIoU: 85.3 -> 87.8Improved
use FMS instead of SVD at dimension 22 (ablation)LRA projection · CTW1500 curved subsetdetection F-measure: 84.3 -> 84.4No clear effect
use triple assignment instead of single sparse (ablation)detection head · Total-TextE2E F-measure: 81.1 -> 82.2Improved
use triple assignment instead of dual assignment (ablation)detection head · Total-Textinference time (ms): 6.5 -> 3.2Improved
use CTC decoding instead of autoregressive (ablation)recognition head · CTW1500inference time (ms): 33.2 -> 15.1Mixed
use proposed recognition head instead of ABCNet v2 head (ablation)LRANet++ · CTW1500E2E F-measure: 65.1 -> 67.7Improved
use large-ratio image scaling augmentation [0.1, 3] (ablation)LRANet++ · Total-TextE2E F-measure: 80.3 -> 82.2Improved

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