AI Paper Atlas

Research map / Detection and segmentation / CNN features

SPTS v2: Single-Point Scene Text Spotting

Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin

TPAMI 2023 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 70 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
share parameters between IAD and PRD (ablation)SPTS v2 · Total-Text Full lexiconend-to-end accuracy: 80.0 -> 81.4Improved
integrate token and feature in information transmission (ablation)SPTS v2 · Total-Text Full lexiconend-to-end accuracy: 78.4 -> 81.4Improved
add location feature to information transmission (token alone vs both) (ablation)SPTS v2 · Total-Text lexicon-freeend-to-end accuracy: 66.4 -> 68.5Improved
use central point instead of top-left corner (ablation)SPTS · Total-Text lexicon-freeend-to-end accuracy: 71.6 -> 74.2Improved
use central point instead of random point (ablation)SPTS · Total-Text lexicon-freeend-to-end accuracy: 73.2 -> 74.2Improved
single point instead of Bezier box (ablation)SPTS v2 · Total-Text lexicon-freeend-to-end accuracy: 63.2 -> 75.5Improved
single point instead of rectangle box (ablation)SPTS v2 · SCUT-CTW1500 lexicon-freeend-to-end accuracy: 55.0 -> 63.6Improved
double training schedule for Bezier representation (ablation)SPTS-Bezier · SCUT-CTW1500 lexicon-freeend-to-end accuracy: 52.6 -> 51.1Hurt
random instance order instead of area order (ablation)SPTS · SCUT-CTW1500 Full lexiconend-to-end accuracy: 75.3 -> 83.8Improved
deeper decoder (6 layers instead of 1) (ablation)SPTS v2 R50 · Total-Text lexicon-freeend-to-end accuracy: 53.7 -> 68.5Improved
larger backbone ResNet-34 instead of ResNet-18 (ablation)SPTS v2 · Total-Text lexicon-freeend-to-end accuracy: 60.6 -> 64.7Improved
larger backbone ResNet-50 instead of ResNet-34 (ablation)SPTS v2 · Total-Text lexicon-freeend-to-end accuracy: 64.7 -> 68.5Improved

Later papers that compared with this method

2 later accepted papers report SPTS v2 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 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