Bilibili Tech
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.
DNTextSpotterHistorical Map OCRICDAR
0 likes · 17 min read