• 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:

Long, Tianhang (Long, Tianhang.) | Sun, Yanfeng (Sun, Yanfeng.) | Gao, Junbin (Gao, Junbin.) | Hu, Yongli (Hu, Yongli.) | Yin, Baocai (Yin, Baocai.) (学者:尹宝才)

收录:

EI Scopus SCIE

摘要:

Domain adaptation is a fundamental research field, which focuses on transforming knowledge between different domains. With the massive growth of video data, the video domain adaptation problem becomes increasingly significant for practical tasks. Motivated by the excellent performance of Grassmann manifolds representation in video recognition tasks, we propose an optimal transport based video domain adaptation model on Grassmann manifolds. The proposed model reduces the discrepancy between different domains for the frame and video level features. First, the frame level discrepancy is reduced by extracting domain consistency features. At the video level, a fixed number of frame features are formed and represented as points on Grassmann manifolds. These points are fused with predicted labels to form fusion features. Finally, the video level discrepancy is reduced by minimizing the distribution discrepancy of the fusion features between two domains. Cross-domain video recognition experiments demonstrate the validity of the proposed model. The experimental results demonstrate the excellent performance of the proposed algorithm compared with the state-of-art video domain adaptation models. (C) 2022 Elsevier Inc. All rights reserved.

关键词:

Domain adaptation Grassmann manifolds Optimal transport problem

作者机构:

  • [ 1 ] [Long, Tianhang]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 2 ] [Sun, Yanfeng]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 3 ] [Hu, Yongli]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 4 ] [Yin, Baocai]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 5 ] [Gao, Junbin]Univ Sydney, Discipline Business Analyt, Sydney, NSW, Australia

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

INFORMATION SCIENCES

ISSN: 0020-0255

年份: 2022

卷: 594

页码: 151-162

8 . 1

JCR@2022

8 . 1 0 0

JCR@2022

ESI学科: COMPUTER SCIENCE;

ESI高被引阀值:46

JCR分区:1

中科院分区:1

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 8

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:228/4916679
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