• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Liu, Lei (Liu, Lei.) | Jiao, Yidi (Jiao, Yidi.) | Li, Xiaoran (Li, Xiaoran.) | Li, Jing (Li, Jing.) | Wang, Haitao (Wang, Haitao.) | Cao, Xinyu (Cao, Xinyu.)

收录:

EI Scopus

摘要:

The objective of image captioning involves empowering computers to autonomously produce human-like sentences that depict a provided image. To address the issues of insufficient accuracy in image feature extraction and underutilization of visual information, we propose a Swin Transformer-based image captioning model with feature enhancement and multi-stage fusion. First, the Swin Transformer is employed in the capacity of an encoder for the purpose of extracting image features, and feature enhancement is adopted to capture more information about image features. Then, a multi-stage image and semantic fusion module is constructed to utilize the semantic information from past time steps. Finally, LSTM is used to decode the semantic and image information and generate captions. The proposed model achieves better results in baseline tests on the public datasets Flickr8K and Flickr30K. © 2023 IEEE.

关键词:

Semantics Long short-term memory Image enhancement Image fusion

作者机构:

  • [ 1 ] [Liu, Lei]Beijing University of Technology, Faculty of Science, Beijing, China
  • [ 2 ] [Liu, Lei]Beijing Institute for Scientific and Engineering Computing, Beijing University of Technology, Beijing, China
  • [ 3 ] [Jiao, Yidi]Beijing University of Technology, Faculty of Science, Beijing, China
  • [ 4 ] [Li, Xiaoran]Beijing University of Technology, Faculty of Science, Beijing, China
  • [ 5 ] [Li, Jing]Beijing University of Technology, Faculty of Science, Beijing, China
  • [ 6 ] [Wang, Haitao]China National Institute of Standardization, Fundamental Standardization, Beijing, China
  • [ 7 ] [Cao, Xinyu]China National Institute of Standardization, Fundamental Standardization, Beijing, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2023

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 1

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:684/4960496
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司