Papers › SPTS: Single-Point Text Spotting

SPTS: Single-Point Text Spotting

15 Dec 2021arXiv:2112.07917archive 2025-07-28

Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Shenggao Zhu, Jing Li, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin

Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance. We propose an end-to-end scene text spotting method that tackles scene text spotting as a sequence prediction task. Given an image as input, we formulate the desired detection and recognition results as a sequence of discrete tokens and use an auto-regressive Transformer to predict the sequence. The proposed method is simple yet effective, which can achieve state-of-the-art results on widely used benchmarks. Most significantly, we show that the performance is not very sensitive to the positions of the point annotation, meaning that it can be much easier to be annotated or even be automatically generated than the bounding box that requires precise positions. We believe that such a pioneer attempt indicates a significant opportunity for scene text spotting applications of a much larger scale than previously possible. The code is available at https://github.com/shannanyinxiang/SPTS.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shannanyinxiang/spts officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModellingText DetectionText Spotting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Spotting ICDAR 2015 SPTS F-measure (%) - Generic Lexicon 65.8 #18 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 SPTS F-measure (%) - Strong Lexicon 77.5 #18 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 SPTS F-measure (%) - Weak Lexicon 70.2 #18 of 18 Archive leaderboard report
Text Spotting Inverse-Text SPTS F-measure (%) - Full Lexicon 46.2 #6 of 9 Archive leaderboard report
Text Spotting Inverse-Text SPTS F-measure (%) - No Lexicon 38.3 #6 of 9 Archive leaderboard report
Text Spotting SCUT-CTW1500 SPTS F-Measure (%) - Full Lexicon 83.8 #3 of 11 Archive leaderboard report
Text Spotting SCUT-CTW1500 SPTS F-measure (%) - No Lexicon 63.6 #3 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections