Codesota · Models · PARSeqResearch7 results · 6 benchmarks
Model card

PARSeq.

Researchopen-sourceUnknown paramsScene Text Recognition with Permuted Autoregressive Sequence Models

Scene text recognition with permutation language modeling. ECCV 2022.

§ 01 · Benchmarks

Every benchmark PARSeq has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Union14MComputer Vision · Scene Text Detectionaccuracy67.8%#2/8source ↗
02Union14MComputer Vision · Scene Text Detectionaccuracy63.8%#5/8source ↗
03svtpComputer Vision · Scene Text Recognitionaccuracy96.9%#6/192022-07-14source ↗
04cute80Computer Vision · Scene Text Recognitionaccuracy98.6%#7/202022-07-14source ↗
05iiit5kComputer Vision · Scene Text Recognitionaccuracy99.0%#7/212022-07-14source ↗
06svtComputer Vision · Scene Text Recognitionaccuracy97.8%#8/402022-07-14source ↗
07icdar-2013Computer Vision · Scene Text Detectionaccuracy98.1%#12/152022-07-14source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where PARSeq actually performs.

Computer Vision
6
benchmarks
avg rank #6.7
§ 03 · Papers

1 paper with results for PARSeq.

  1. 2022-07-14· Computer Vision· 5 results

    Scene Text Recognition with Permuted Autoregressive Sequence Models

§ 04 · Related models

Other Research models scored on Codesota.

DenseNet-121 (Chest X-ray)
8M params · 4 results · 2 SOTA
SimpleNet
2 results · 2 SOTA
DGN
1 result · 1 SOTA
DeepASD
1 result · 1 SOTA
DefectDet (ResNet)
1 result · 1 SOTA
PROXI
1 result · 1 SOTA
ASD-SWNet
2 results
ASDFormer
2 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
6
results
arxiv-paper
1
result
5 of 7 rows marked verified.