Open access
Sep 2026
Investigation of Word Recognition Methods for Japanese Fingerspelling Using Large Language Models
A visual-language integration framework that combines dynamic visual representations derived from a single RGB video stream with the lexical knowledge of Large Language Models (LLMs), allowing the language model to compensate for uncertainty or errors in the visual representation.
You-Sun Kang, Renta Kuzuyama, Naoto Tsuta et al.
· Italian National Conference... · 0 citations