Codesota · Models · CRAFTUnknown21 results · 7 benchmarks
Model card

CRAFT.

UnknownunknownUnknown paramsUnknown

Imported from Papers With Code

§ 01 · Benchmarks

Every benchmark CRAFT has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01icdar-2013Computer Vision · Scene Text Detectionh-mean95.2%#1/12019-04-03source ↗
02icdar-2013Computer Vision · Scene Text Detectionprecision97.4%#1/142019-04-03source ↗
03icdar-2013Computer Vision · Scene Text Detectionrecall93.1%#1/142019-04-03source ↗
04icdar-2017-mltComputer Vision · Scene Text Detectionh-mean73.9%#1/12019-04-03source ↗
05CTW1500Computer Vision · Scene Text Detectionf-measure83.5%#5/62019-04-03source ↗
06CTW1500Computer Vision · Scene Text Detectionprecision86.0%#5/62019-04-03source ↗
07CTW1500Computer Vision · Scene Text Detectionrecall81.1%#5/62019-04-03source ↗
08icdar-2017-mltComputer Vision · Scene Text Detectionprecision80.6%#10/182019-04-03source ↗
09icdar-2017-mltComputer Vision · Scene Text Detectionrecall68.2%#12/182019-04-03source ↗
10scut-ctw1500Computer Vision · Optical Character Recognitionprecision86.0%#12/182019-04-03source ↗
11scut-ctw1500Computer Vision · Optical Character Recognitionrecall81.1%#12/182019-04-03source ↗
12scut-ctw1500Computer Vision · Optical Character Recognitionf-measure83.5%#12/192019-04-03source ↗
13msra-td500Computer Vision · Scene Text Detectionprecision88.2%#14/232019-04-03source ↗
14msra-td500Computer Vision · Scene Text Detectionf-measure82.9%#16/242019-04-03source ↗
15msra-td500Computer Vision · Scene Text Detectionrecall78.2%#16/242019-04-03source ↗
16ICDAR 2015Computer Vision · Scene Text Detectionrecall84.3%#18/412019-04-03source ↗
17ICDAR 2015Computer Vision · Scene Text Detectionprecision89.8%#18/412019-04-03source ↗
18ICDAR 2015Computer Vision · Scene Text Detectionf-measure86.9%#20/432019-04-03source ↗
19Total-TextComputer Vision · Scene Text Detectionprecision87.6%#20/302019-04-03source ↗
20Total-TextComputer Vision · Scene Text Detectionrecall79.9%#21/302019-04-03source ↗
21Total-TextComputer Vision · Scene Text Detectionf-measure83.6%#23/332019-04-03source ↗
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 CRAFT actually performs.

Computer Vision
7
benchmarks
avg rank #11.6
§ 03 · Papers

2 papers with results for CRAFT.

  1. 2019-04-03· Computer Vision· 3 results

    Character Region Awareness for Text Detection

  2. 2019-04-03· Computer Vision· 18 results

    Character Region Awareness for Text Detection

§ 04 · Related models

Other Unknown models scored on Codesota.

fglihai
Unknown params · 6 results · 1 SOTA
CLIP4STR-L
Unknown params · 1 result · 1 SOTA
USYD NLP_CS29-2
Unknown params · 6 results
Corner-based Region Proposals
Unknown params · 3 results
EAST + VGG16
Unknown params · 3 results
SSTD
Unknown params · 3 results
TextBoxes++_MS
Unknown params · 3 results
WordSup (VGG16-synth-coco)
Unknown params · 3 results
§ 05 · Sources & freshness

Where these numbers come from.

papers-with-code
18
results
arxiv
3
results
21 of 21 rows marked verified.