Oct 8, 2024 · Artificial Intelligence

ICDAR 2024 Historical Map Text Recognition Competition: DNTextSpotter Methodology and Results

The ICDAR 2024 Historical Map Text Recognition competition was won by Bilibili’s DNTextSpotter, a Transformer‑based model built on DeepSolo and ViTAE‑v2 that uses deformable self‑attention, dual‑query decoding and denoising training, combined with mixed‑vocabulary fine‑tuning, advanced loss functions and strict PDQ/PWQ/PCQ metrics to achieve state‑of‑the‑art dense, rotated, arbitrary‑shaped text detection and recognition on historical maps and real‑world multimedia.

DNTextSpotterDeep LearningEvaluation Metrics

0 likes · 17 min read

ICDAR 2024 Historical Map Text Recognition Competition: DNTextSpotter Methodology and Results

Meituan Technology Team

Sep 26, 2019 · Artificial Intelligence

Efficient Scene Text Detection Framework with Feature Pyramid and Expanded High-Level Feature Maps

The paper presents an efficient scene‑text detector that expands high‑level SSD feature maps and integrates a feature‑pyramid network, using direction‑aware segment‑and‑link predictions to reconstruct arbitrarily long, rotated text, achieving higher recall and precision with real‑time speed and outperforming recent methods on ICDAR benchmarks and a menu‑recognition test.

Computer VisionDeep LearningICDAR

0 likes · 12 min read

Efficient Scene Text Detection Framework with Feature Pyramid and Expanded High-Level Feature Maps