Skeleton-Based Gesture Recognition With Learnable Paths and Signature Features

计算机科学 判别式 模式识别(心理学) 卷积神经网络 人工智能 特征提取 路径(计算) 图形 签名(拓扑) 运动学 理论计算机科学 数学 几何学 经典力学 物理 程序设计语言
作者
Jiale Cheng,Dongzi Shi,Chenyang Li,Yu Li,Hao Ni,Lianwen Jin,Xin Zhang
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:26: 3951-3961 被引量:1
标识
DOI:10.1109/tmm.2023.3318242
摘要

For the skeleton-based gesture recognition, graph convolutional networks (GCNs) have achieved remarkable performance since the human skeleton is a natural graph. However, the biological structure might not be the crucial one for motion analysis. Also, spatial differential information like joint distance and angle between bones may be overlooked during the graph convolution. In this paper, we focus on obtaining meaningful joint groups and extracting their discriminative features by the path signature (PS) theory. Firstly, to characterize the constraints and dependencies of various joints, we propose three types of paths, i.e., spatial, temporal, and learnable path. Especially, a learnable path generation mechanism can group joints together that are not directly connected or far away, according to their kinematic characteristic. Secondly, to obtain informative and compact features, a deep integration of PS with few parameters are introduced. All the computational process is packed into two modules, i.e., spatial-temporal path signature module (ST-PSM) and learnable path signature module (L-PSM) for the convenience of utilization. They are plug-and-play modules available for any neural network like CNNs and GCNs to enhance the feature extraction ability. Extensive experiments have conducted on three mainstream datasets (ChaLearn 2013, ChaLearn 2016, and AUTSL). We achieved the state-of-the-art results with simpler framework and much smaller model size. By inserting our two modules into the several GCN-based networks, we can observe clear improvements demonstrating the great effectiveness of our proposed method.
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
1秒前
2秒前
南风知我意完成签到,获得积分20
3秒前
段一帆发布了新的文献求助30
5秒前
wangqinlei完成签到 ,获得积分10
5秒前
fenghp发布了新的文献求助10
6秒前
王馨雨发布了新的文献求助10
6秒前
8秒前
CipherSage应助ccalvintan采纳,获得10
9秒前
9秒前
雪天的阳完成签到 ,获得积分10
11秒前
12秒前
13秒前
13秒前
烟花应助ren采纳,获得10
14秒前
讨厌科研发布了新的文献求助10
14秒前
量子星尘发布了新的文献求助10
15秒前
苏卿应助科研通管家采纳,获得30
16秒前
fd163c应助科研通管家采纳,获得10
17秒前
香蕉觅云应助科研通管家采纳,获得10
17秒前
思源应助科研通管家采纳,获得10
17秒前
SYLH应助科研通管家采纳,获得10
17秒前
17秒前
CAOHOU应助科研通管家采纳,获得10
17秒前
爆米花应助科研通管家采纳,获得10
17秒前
SYLH应助科研通管家采纳,获得30
17秒前
小蘑菇应助科研通管家采纳,获得10
17秒前
17秒前
殷勤的紫槐完成签到,获得积分10
17秒前
风轻青柠发布了新的文献求助10
18秒前
18秒前
机智冬灵完成签到,获得积分10
19秒前
20秒前
为小嗳打伞完成签到 ,获得积分10
22秒前
小木安华发布了新的文献求助10
22秒前
体贴的之卉完成签到,获得积分20
24秒前
大侠完成签到 ,获得积分10
24秒前
spy777应助机智冬灵采纳,获得20
25秒前
晨曦发布了新的文献求助10
25秒前
27秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
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 3989390
求助须知:如何正确求助?哪些是违规求助? 3531487
关于积分的说明 11254109
捐赠科研通 3270153
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809174