您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

GCVC: Graph Convolution Vector Distribution Calibration for Fish Group Activity Recognition

文献类型： 外文期刊

作者： Zhao, Zhenxi 1 ; Yang, Xinting 2 ; Liu, Jintao 5 ; Zhou, Chao 2 ; Zhao, Chunjiang 1 ;

作者机构： 1.NorthWest A&F Univ, Coll Informat Engn, Yangling 712100, Peoples R China

2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

3.Beijing Acad Agr & Forestry Sci, Res Ctr Informat Technol, Beijing 100097, Peoples R China

4.Natl Engn Lab Agriprod Qual Traceabil, Beijing 100097, Peoples R China

5.Univ Almeria, Sch Engn, Almeria 04120, Spain

关键词： Fish; Feature extraction; Activity recognition; Calibration; Adhesives; Training; Convolution; Graph convolution vector calibration; fish group activity; activity feature vector calibration; fish activity dataset

期刊名称：IEEE TRANSACTIONS ON MULTIMEDIA （ 影响因子：7.3； 五年影响因子：7.3 ）

ISSN： 1520-9210

年卷期： 2024 年 26 卷

页码：

收录情况： SCI

摘要： Only a few key fish individuals can play a dominant role in actual fish group, therefore, it is reasonable to infer group activities from the relationship between individual actions. However, the complex underwater environment, rapid and similar fish individual movements are likely to cause the indistinct action characteristics, as well as adhesion of data distribution, and it is difficult to infer the relationship between individual actions directly by using graph convolutional network (GCN). Therefore, this article proposes a graph convolution vector calibration (GCVC) network for fish group activity recognition through individual action relationship reasoning. By improving reasoning ability of GCN, an activity feature vector calibration module is designed to solve the data adhesion and mismatch between the estimated and true distribution. The idea is to first count the distribution of the original data, and make each dimension of its active feature vector follow the Gaussian distribution, so as to generate a better similar category distribution. In addition, we also produced a fish activity dataset to verify the performance of the proposed algorithm. The experimental results show that the GCVC achieves a group activity recognition accuracy of 93.33%, and the Macro-F1 is 93.25%, which is 19.21% and 24.2% higher than before, respectively. By using GCVC, the corrected activity feature vector distribution is more consistent, and the data adhesion is reduced, the model can achieve more fully supervised learning.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台