Codesota · Models · Davar-Lab-OCRHikvision Research Institute3 results · 1 benchmarks
Model card

Davar-Lab-OCR.

Hikvision Research Institutetable-recognition

ICDAR 2021 Scientific Literature Parsing Task B winner (1st place). Hierarchical encoder-decoder for table structure recognition on PubTabNet.

§ 01 · Benchmarks

Every benchmark Davar-Lab-OCR has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-all-samples96.4%#3/11source ↗
02table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-complex-samples94.8%#4/11source ↗
03table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-simple-samples97.9%#4/11source ↗
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 Davar-Lab-OCR actually performs.

Computer Vision
1
benchmark
avg rank #3.7
§ 05 · Sources & freshness

Where these numbers come from.

paper
3
results
0 of 3 rows marked verified.