• 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:

Ma, Chunjie (Ma, Chunjie.) | Du, Lina (Du, Lina.) | Zhuo, Li (Zhuo, Li.) | Li, Jiafeng (Li, Jiafeng.)

收录:

EI Scopus SCIE

摘要:

Weakly Supervised Video Salient Object Detection (WSVSOD) only requires coarse-grained manual annotations, which can achieve a good trade-off between labeling efficiency and detection performance. In this paper, a Multiple Pseudo Label Aggregation Network (MPLA-Net) is proposed for WSVSOD. Firstly, the video frames that can obtain high-quality pseudo labels are selected to generate multiple pseudo labels, so as to avoid the prejudice of the single label. Moreover, the pseudo label with fine edge information is used to generate the Edge Information Map (EIM). Secondly, MPLA-Net is designed to adequately excavate and utilize the comprehensive saliency cues in multiple pseudo labels to improve the detection accuracy, in which ResNet-50 is adopted as the backbone network. Edge loss, pseudo label loss, self-supervised loss and fusion loss are exploited to jointly supervise and optimize the network training to obtain a robust detection model. Experimental results on five benchmark datasets demonstrate that, compared with existing weakly supervised methods, the proposed method can achieve state-of-the-art detection accuracy with less model parameters and higher detection speed. And the detected salient objects have fine boundaries.

关键词:

Annotations Task analysis pseudo label consistency evaluation Object detection Optical flow multiple pseudo label aggregation Weakly supervised video salient object detection Training Image edge detection video frame quality evaluation Feature extraction

作者机构:

  • [ 1 ] [Ma, Chunjie]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intelligen, Beijing 100124, Peoples R China
  • [ 2 ] [Zhuo, Li]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intelligen, Beijing 100124, Peoples R China
  • [ 3 ] [Li, Jiafeng]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intelligen, Beijing 100124, Peoples R China
  • [ 4 ] [Ma, Chunjie]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Zhuo, Li]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 6 ] [Li, Jiafeng]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 7 ] [Du, Lina]Shandong Jianzhu Univ, Sch Comp Sci & Technol, Jinan 250101, Peoples R China

通讯作者信息:

  • [Zhuo, Li]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intelligen, Beijing 100124, Peoples R China;;[Zhuo, Li]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;;

查看成果更多字段

相关关键词:

来源 :

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

ISSN: 1051-8215

年份: 2024

期: 5

卷: 34

页码: 3905-3918

8 . 4 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 6

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:341/4971726
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