CLIP-Llama: A New Approach for Scene Text Recognition with a Pre-Trained Vision-Language Model and a Pre-Trained Language Model

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 22; p. 7371
• Main Authors: Zhao, Xiaoqing, Xu, Miaomiao, Silamu, Wushour, Li, Yanbing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 19.11.2024; MDPI
• Subjects: Artificial intelligence; Computer vision; Deep learning; Image retrieval; Language; Llamas; Natural language processing; pre-trained language model; scene text recognition; Semantics; vision-language model; vision-language model; pre-trained language model; scene text recognition

This study focuses on Scene Text Recognition (STR), which plays a crucial role in various applications of artificial intelligence such as image retrieval, office automation, and intelligent transportation systems. Currently, pre-trained vision-language models have become the foundation for various d...