CCDPlus : Towards Accurate Character to Character Distillation for Text Recognition

Existing scene text recognition methods leverage large-scale labeled synthetic data (LSD) to reduce reliance on labor-intensive annotation tasks and improve recognition capability in real-world scenarios. However, the emergence of a synth-to-real domain gap still limits their efficiency and robustne...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 5 vom: 26. Mai, Seite 3546-3562
1. Verfasser: Guan, Tongkun (VerfasserIn)
Weitere Verfasser: Shen, Wei, Yang, Xiaokang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article