The CLIP - GPT Image Captioning Model Integrated with Global Semantics

Image captioning is a method for automatically generating language descriptions for images. Cross-modal semantic consistency is the core issue of shared subspace embedding when bridging pre-training models in the fields of computer vision and natural language processing to construct image captio...

ver descrição completa

Detalhes bibliográficos

Principais autores:	TAO Rui, REN Honge, CAO Haiyan
Formato:	Artigo
Idioma:	Chinês
Publicado em:	Harbin University of Science and Technology Publications 2024-04-01
coleção:	Journal of Harbin University of Science and Technology
Assuntos:	cross-modal image captioning pre-training model shared subspace semantic alignment
Acesso em linha:	https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2307
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!