3 papers
cs.CV2026
TiCLS : Tightly Coupled Language Text Spotter
Leeje Jang, Yijun Lin, Yao-Yi Chiang +1
Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on v…
cs.CV2025
LIGHT: Multi-Modal Text Linking on Historical Maps
Yijun Lin, Rhett Olson, Junhan Wu +2
Text on historical maps provides valuable information for studies in history, economics, geography, and other related fields. Unlike structured or semi-structured documents, text o…
cs.CV2025
Hyper-Local Deformable Transformers for Text Spotting on Historical Maps
Yijun Lin, Yao-Yi Chiang
Text on historical maps contains valuable information providing georeferenced historical, political, and cultural contexts. However, text extraction from historical maps is challen…