Codesota · Models · BPDOZheng et al.3 results · 1 benchmarks
Model card

BPDO.

Zheng et al.open-sourceUnknown paramsResNet-50 + FPN + DCN + Text-Aware Module + Dynamic Optimization Module

Boundary Points Dynamic Optimization for arbitrary shape scene text detection. Uses text-aware module (TAM) and dynamic optimization module (DOM). ICASSP 2024. arxiv:2401.09997.

§ 01 · Benchmarks

Every benchmark BPDO has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01msra-td500Computer Vision · Scene Text Detectionf-measure91.5%#1/242024-01-18source ↗
02msra-td500Computer Vision · Scene Text Detectionprecision94.7%#1/232024-01-18source ↗
03msra-td500Computer Vision · Scene Text Detectionrecall88.5%#1/242024-01-18source ↗
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 BPDO actually performs.

Computer Vision
1
benchmark
avg rank #1.0
§ 03 · Papers

1 paper with results for BPDO.

  1. 2024-01-18· Computer Vision· 3 results

    BPDO: Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection

§ 04 · Related models

Other Zheng et al. models scored on Codesota.

RMIPN
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.