• 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:

Wu, Lifang (Wu, Lifang.) (学者:毋立芳) | Qi, Mingchao (Qi, Mingchao.) | Jian, Meng (Jian, Meng.) | Zhang, Heng (Zhang, Heng.)

收录:

EI Scopus SCIE

摘要:

With the development of visual social networks, the sentiment analysis of images has quickly emerged for opinion mining. Based on the observation that the sentiments conveyed by some images are related to salient objects in them, we propose a scheme for visual sentiment analysis that combines global and local information. First, the sentiment is predicted from the entire images. Second, it is judged whether there are salient objects in an image or not. If there are, sub-images are cropped from the entire image based on the detection window of the salient objects. Moreover, a CNN model is trained for the set of sub-images. Predictions of sentiments from entire images and sub-images are then fused together to obtain the final results. If no salient object is detected in the images, the sentiment predicted directly from entire images is used as the final result. The compared experimental results show that the proposed approach is superior to state-of-the-art algorithms. It also demonstrates that reasonably utilizing the local information could improve the performance for visual sentiment analysis.

关键词:

Global information Visual sentiment analysis Local information Salient objects

作者机构:

  • [ 1 ] [Wu, Lifang]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 2 ] [Qi, Mingchao]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 3 ] [Jian, Meng]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 4 ] [Zhang, Heng]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

通讯作者信息:

  • [Jian, Meng]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

NEURAL PROCESSING LETTERS

ISSN: 1370-4621

年份: 2020

期: 3

卷: 51

页码: 2063-2075

3 . 1 0 0

JCR@2022

ESI学科: COMPUTER SCIENCE;

ESI高被引阀值:132

被引次数:

WoS核心集被引频次: 40

SCOPUS被引频次: 39

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:272/4514275
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