A duet of perception and reasoning: CLIP and LLM brainstorming for scene text recognition

Open Webpage

Zeguang Jia, Jianming Wang, Kehui Song, Zhilan Wang, Xiaohan Ma, Rize Jin

Published: 2026, Last Modified: 22 Jan 2026Neurocomputing 2026EveryoneRevisionsBibTeXCC BY-SA 4.0