GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi

计算机科学 残余物 混叠 人工智能 无线 块(置换群论) Gabor变换 动作识别 模式识别(心理学) 计算机视觉 时频分析 电信 欠采样 滤波器(信号处理) 几何学 数学 算法 班级(哲学)
作者
Yong Hao,Zhiyuan Shi,Xidong Mu,Yuanwei Liu
标识
DOI:10.1109/icpr56361.2022.9956179
摘要

WiFi-based human action recognition (HAR) has been regarded as a promising solution in applications such as smart living and remote monitoring due to the pervasive and unobtrusive nature of WiFi signals. However, the efficacy of WiFi signals is prone to be influenced by the change in the ambient environment and varies over different sub-carriers. To remedy this issue, we propose an end-to-end Gabor residual anti-aliasing sensing network (GraSens) to directly recognize the actions using the WiFi signals from the wireless devices in diverse scenarios. In particular, a new Gabor residual block is designed to address the impact of the changing surrounding environment with a focus on learning reliable and robust temporal-frequency representations of WiFi signals. In each block, the Gabor layer is integrated with the anti-aliasing layer in a residual manner to gain the shift-invariant features. Furthermore, fractal temporal and frequency self-attention are proposed in a joint effort to explicitly concentrate on the efficacy of WiFi signals and thus enhance the quality of output features scattered in different subcarriers. Experimental results throughout our wireless-vision action recognition dataset (WVAR) and three public datasets demonstrate that our proposed GraSens scheme outperforms state-of-the-art methods with respect to recognition accuracy.
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
零琳完成签到 ,获得积分10
1秒前
1秒前
陈曦完成签到,获得积分10
1秒前
1秒前
隐形曼青应助安安采纳,获得10
1秒前
li完成签到,获得积分10
2秒前
2秒前
Ava应助温婉的念文采纳,获得10
2秒前
2秒前
lxcy0612发布了新的文献求助10
2秒前
3秒前
慕青应助透视眼采纳,获得10
4秒前
消摇发布了新的文献求助10
4秒前
CipherSage应助小野猫采纳,获得30
4秒前
科研通AI6应助现代友桃采纳,获得10
4秒前
赵远航发布了新的文献求助10
5秒前
星辰大海应助椰子采纳,获得10
5秒前
6秒前
笛恰儿发布了新的文献求助20
6秒前
忧郁的雨发布了新的文献求助10
6秒前
7秒前
7秒前
SciGPT应助s615采纳,获得10
7秒前
7秒前
8秒前
8秒前
Alger完成签到,获得积分10
8秒前
1111完成签到,获得积分10
8秒前
9秒前
酷波er应助亦玉采纳,获得10
10秒前
10秒前
碧玉墨绿发布了新的文献求助10
11秒前
靓丽琳发布了新的文献求助10
11秒前
小呆发布了新的文献求助10
13秒前
勤奋映梦完成签到,获得积分10
13秒前
13秒前
13秒前
忧郁的雨完成签到,获得积分20
13秒前
13秒前
liyanfeng完成签到,获得积分10
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
NMR in Plants and Soils: New Developments in Time-domain NMR and Imaging 600
Electrochemistry: Volume 17 600
Physical Chemistry: How Chemistry Works 500
SOLUTIONS Adhesive restoration techniques restorative and integrated surgical procedures 500
Energy-Size Reduction Relationships In Comminution 500
Principles Of Comminution, I-Size Distribution And Surface Calculations 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 内科学 生物化学 物理 计算机科学 纳米技术 遗传学 基因 复合材料 化学工程 物理化学 病理 催化作用 免疫学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 4951300
求助须知:如何正确求助?哪些是违规求助? 4213988
关于积分的说明 13107085
捐赠科研通 3995738
什么是DOI,文献DOI怎么找? 2187102
邀请新用户注册赠送积分活动 1202366
关于科研通互助平台的介绍 1115447