AI Paper Atlas

Research map / Detection and segmentation / CNN features

Back-Tracking from Clarity: Self-Learning to See Text from Afar

Duc Tri Tran, Phi Le Nguyen, Minh Hoai Nguyen

ECCV 2026 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 0 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 carrier-based tracking to point-based tracking (ablation)tracker · SceneText50AUC: 38.62 -> 44.71Improved
add carrier-based tracking to point-based tracking (ablation)tracker · SceneText50Precision@20px: 57.44 -> 74.62Improved
add point-based tracking to carrier-based tracking (ablation)tracker · SceneText50AUC: 34.68 -> 44.71Improved
use core polygon instead of convex hull (with RANSAC) (ablation)tracker · SceneText50AUC: 37.40 -> 44.71Improved
use core polygon instead of convex hull (with RANSAC) (ablation)tracker · SceneText50Precision@20px: 62.61 -> 74.62Improved
add RANSAC refinement to convex hull homography (ablation)tracker · SceneText50AUC: 37.30 -> 37.40No clear effect
increase polygon vertices from 4 to 16-20 (ablation)carrier tracker · SceneText50AUC: 32% -> 34.6%Improved
increase polygon vertices beyond 16 (ablation)carrier tracker · SceneText50AUCNo clear effect
train on tracked pseudo-labels instead of augmentationGrounding DINO · SceneText50Precision: 14.21 -> 34.03Improved
train on tracked pseudo-labels instead of augmentationGrounding DINO · SceneText50Recall: 29.77 -> 34.74Improved
train on tracked pseudo-labels instead of augmentationDPText-DETR · SceneText50Recall: 21.80 -> 23.12Improved
train on tracked pseudo-labels instead of augmentationDeepSolo · SceneText50Recall: 37.75 -> 40.27Improved

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