亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

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

计算机科学 卷积(计算机科学) 模式识别(心理学) 图形 人工智能 群(周期表) 理论计算机科学 人工神经网络 化学 有机化学
作者
Zhenxi Zhao,Xinting Yang,Jintao Liu,Chao Zhou,Chunjiang Zhao
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:26: 1776-1789 被引量:3
标识
DOI:10.1109/tmm.2023.3287339
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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
hi_traffic完成签到,获得积分10
刚刚
刚刚
HXY完成签到,获得积分10
2秒前
3秒前
3秒前
6秒前
领导范儿应助linkman采纳,获得30
8秒前
eric888应助guozao采纳,获得150
9秒前
9秒前
小马甲应助科研通管家采纳,获得10
9秒前
towerman完成签到,获得积分10
9秒前
towerman发布了新的文献求助10
12秒前
Bizibili完成签到,获得积分10
22秒前
英俊的铭应助linkman采纳,获得10
28秒前
28秒前
29秒前
努力的淼淼完成签到 ,获得积分10
36秒前
39秒前
千寻完成签到,获得积分10
40秒前
团团完成签到 ,获得积分10
51秒前
Jasper应助linkman采纳,获得10
53秒前
天天快乐应助linkman采纳,获得30
1分钟前
黙宇循光完成签到 ,获得积分10
1分钟前
追三完成签到 ,获得积分10
1分钟前
温暖笑容发布了新的文献求助10
1分钟前
1分钟前
温暖笑容完成签到,获得积分10
1分钟前
wackykao完成签到 ,获得积分10
1分钟前
汉堡包应助linkman采纳,获得30
1分钟前
1分钟前
1分钟前
CC完成签到,获得积分10
1分钟前
CC发布了新的文献求助10
1分钟前
hilton完成签到,获得积分10
1分钟前
xiaoya完成签到,获得积分20
1分钟前
善学以致用应助CC采纳,获得10
1分钟前
1分钟前
xiaojia0501完成签到,获得积分10
1分钟前
xiaojia0501发布了新的文献求助10
1分钟前
脑洞疼应助松松果采纳,获得10
1分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3990012
求助须知:如何正确求助?哪些是违规求助? 3532049
关于积分的说明 11256153
捐赠科研通 3270925
什么是DOI,文献DOI怎么找? 1805123
邀请新用户注册赠送积分活动 882270
科研通“疑难数据库(出版商)”最低求助积分说明 809216