Datasets › SVT

SVT (Street View Text Dataset)

archive 2025-07-28

The Street View Text (SVT) dataset was harvested from Google Street View. Image text in this data exhibits high variability and often has low resolution. In dealing with outdoor street level imagery, we note two characteristics. (1) Image text often comes from business signage and (2) business names are easily available through geographic business searches. These factors make the SVT set uniquely suited for word spotting in the wild: given a street view image, the goal is to identify words from nearby businesses.

Note: the dataset has undergone revision since the time it was evaluated in this publication. Please consult the ICCV2011 paper for most up-to-date results.

Source: Street View Text Dataset

Image source: Street View Text Dataset

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Scene Text Recognition · SVT (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Scene Text Recognition SVT CLIP4STR-H (DFN-5B) Accuracy 99.1 CLIP4STR: A Simple Baseline for Scene Text Recognition... VamosC/CLIP4STR 37 Compare

Papers archive 2025-07-28

papers with a benchmark row: 32 · with a code link: 29 · where Syntology ran a sample: 5 (5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (5 of 32 with a benchmark row: 5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 32 of 32 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 35. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
An Empirical Study of Scaling Law for OCR 1 1 29 Dec 2023 not harvested
DTrOCR: Decoder-only Transformer for Optical Character Recognition 1 1 30 Aug 2023 not harvested
Context Perception Parallel Decoder for Scene Text Recognition 2 1 23 Jul 2023 not harvested
DiffusionSTR: Diffusion Model for Scene Text Recognition 0 1 29 Jun 2023 not harvested
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model 1 4 23 May 2023 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (2 pointer-only for licence)
TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition 1 1 9 May 2023 not harvested
Self-supervised Character-to-Character Distillation for Text Recognition 1 3 1 Nov 2022 not harvested
Multi-Granularity Prediction for Scene Text Recognition 3 1 8 Sep 2022 not harvested
Scene Text Recognition with Permuted Autoregressive Sequence Models 2 1 14 Jul 2022 official (archive's flag): 5 ran · 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result
Self-supervised Implicit Glyph Attention for Text Recognition 1 1 7 Mar 2022 not harvested
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss 1 1 1 Jan 2022 not harvested
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition 1 1 24 Dec 2021 not harvested
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features 3 1 30 Nov 2021 not harvested
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition 3 1 22 Nov 2021 not harvested
Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition 2 1 1 Aug 2021 not harvested
Why You Should Try the Real Data for the Scene Text Recognition 1 1 29 Jul 2021 not harvested
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition 1 1 13 Jun 2021 not harvested
Vision Transformer for Fast and Efficient Scene Text Recognition 3 1 18 May 2021 not harvested
Revisiting Classification Perspective on Scene Text Recognition 1 1 22 Feb 2021 not harvested
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition 3 1 22 May 2020 not harvested
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks 3 1 27 Mar 2020 not harvested
TextScanner: Reading Characters in Order for Robust Scene Text Recognition 0 1 28 Dec 2019 not harvested
Decoupled Attention Network for Text Recognition 5 1 21 Dec 2019 not harvested
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention 2 1 10 Oct 2019 not harvested
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis 13 1 3 Apr 2019 community repositories only · 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition 8 1 2 Nov 2018 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
Scene Text Recognition from Two-Dimensional Perspective 0 1 18 Sep 2018 not harvested
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification 4 1 25 Jun 2018 not harvested
Star-net: A spatial attention residue network for scene text recognition. 1 1 20 Sep 2016 not harvested
Robust Scene Text Recognition with Automatic Rectification 5 1 12 Mar 2016 not harvested
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition 85 1 21 Jul 2015 66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 where Syntology's instrument failed) · 15 unverified (17 pointer-only for licence)
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition 1 1 9 Jun 2014 not harvested

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • SVT

1 variant name, as the archive lists them.

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