Research on visual question answering based on dynamic memory network model of multiple attention mechanisms

Since the existing visual question answering model lacks long-term memory modules for answering complex questions, it is easy to cause the loss of effective information. In order to further improve the accuracy of the visual question answering model, this paper applies the multiple attention mechani...

Descripción completa

Detalles Bibliográficos
Autores principales: Miao, Yalin, He, Shuyun, Cheng, WenFang, Li, Guodong, Tong, Meng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9537137/
https://www.ncbi.nlm.nih.gov/pubmed/36202900
http://dx.doi.org/10.1038/s41598-022-21149-9

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9537137/
https://www.ncbi.nlm.nih.gov/pubmed/36202900
http://dx.doi.org/10.1038/s41598-022-21149-9

Ejemplares similares