Dual Position Relationship Transformer for Image Captioning.

Wang, Yaohan; Qian, Wenhua; Nie, Rencan; Xu, Dan; Cao, Jinde; Kim, Pyoungwon

Wang, Yaohan; Qian, Wenhua; Nie, Rencan; Xu, Dan; Cao, Jinde; Kim, Pyoungwon.

Afiliação

Wang Y; Department of Information Science and Engineering, Yunnan University, Kunming, China.
Qian W; Department of Information Science and Engineering, Yunnan University, Kunming, China.
Nie R; Department of Automation, Southeast University, Nanjing, China.
Xu D; Department of Information Science and Engineering, Yunnan University, Kunming, China.
Cao J; Department of Automation, Southeast University, Nanjing, China.
Kim P; Department of Information Science and Engineering, Yunnan University, Kunming, China.

Big Data ; 10(6): 515-527, 2022 12.

Article em En | MEDLINE | ID: mdl-34981961

Assuntos

Armazenamento e Recuperação da Informação; Redes Neurais de Computação

Palavras-chave

attention mechanism; faster R-CNN; image captioning; position relationship; transformer

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Armazenamento e Recuperação da Informação / Redes Neurais de Computação Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google