Enabling High-Level Worker-Centric Semantic Understanding of Onsite Images Using Visual Language Models with Attention Mechanism and Beam Search Strategy.

Saved in:
Bibliographic Details
Title: Enabling High-Level Worker-Centric Semantic Understanding of Onsite Images Using Visual Language Models with Attention Mechanism and Beam Search Strategy.
Authors: Deng, Hui1, Fu, Kejie1,2, Yu, Binglin1,3, Li, Huimin1, Duan, Rui1,2, Deng, Yichuan1,2,3, ctycdeng@scut.edu.cn, Lin, Jia-rui3
Source: Buildings (2075-5309); Mar2025, Vol. 15 Issue 6, p959, 28p
Database: Applied Science & Technology Source
Full text is not displayed to guests.
Description
ISSN:20755309
DOI:10.3390/buildings15060959