Codesota · Benchmark · ICDAR 2019 ArTHome/Leaderboards/Vision & Documents/Scene Text Detection/ICDAR 2019 ArT
Unknown

ICDAR 2019 ArT.

Text in arbitrary shapes including curved and rotated text. 10,166 images total.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Only 4 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

F Measure

F Measure is the reported evaluation metric for ICDAR 2019 ArT. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for F Measureverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01pil_maskrcnn
Rank 1 at ICDAR 2019 ArT T1. H-mean IoU>0.5. Team: ICT CAS.
verified82.652019Paper ↗Looks wrong?
02NJU-ImagineLab
Rank 2 at ICDAR 2019 ArT T1. H-mean IoU>0.5. Team: Nanjing University.
verified80.242019Paper ↗Looks wrong?
03ArtDet-v2
Rank 3 at ICDAR 2019 ArT T1. H-mean IoU>0.5. Team: Sogou OCR.
verified79.482019Paper ↗Looks wrong?
04CUTeOCR
Rank 5 at ICDAR 2019 ArT T1. H-mean IoU>0.5. Team: CUHK/HIT.
verified78.362019Paper ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Scene Text Detection