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的填写文献信息,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!

A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities

计算机科学 RGB颜色模型 人工智能 计算机视觉 卷积神经网络 杠杆(统计) 深度学习 模式识别(心理学)
作者
Cheng Qin,Jun Cheng,Zhen Liu,Ziliang Ren,Jianming Liu
出处
期刊:Expert Systems With Applications [Elsevier]
卷期号:244: 123061-123061
标识
DOI:10.1016/j.eswa.2023.123061
摘要

The vulnerability of RGB-based human action recognition in complex environment and variational scenes can be compensated by skeleton modality. Therefore, action recognition methods fusing RGB and skeleton modalities have received increasing attention. However, the recognition performance of the existing methods is still not satisfactory due to the insufficiently optimized sampling, modeling and fusion strategy, even the computational cost is heavy. In this paper, we propose a Dense-Sparse Complementary Network (DSCNet), which aims to leverage the complementary information of the RGB and skeleton modalities at light computational cost to obtain the competitive action recognition performance. Specifically, we first adopt dense and sparse sampling strategies according to the advantages of RGB and skeleton modalities, respectively. And then, we use the skeleton as guiding information to crop the key active region of the persons in the RGB frame, which largely eliminates the interference of the background. Moreover, a Short-Term Motion Extraction Module (STMEM) is proposed to compress the densely sampled RGB frames to fewer frames before feeding them into the backbone network, which avoids a surge in computational cost. And a Sparse Multi-Scale Spatial–Temporal convolutional neural Network (Sparse-MSSTNet) is designed to modeling sparse skeleton. Extensive experiments show that our method effectively combines complementary information of RGB and skeleton modalities to improve recognition accuracy. The DSCNet achieves competitive performance on NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, UAV-human, IKEA ASM and Northwest-UCLA datasets with much less computational cost than exiting methods. The code is available at https://github.com/Maxchengqin/DSCNet.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
刚刚
三方完成签到,获得积分10
2秒前
杨无敌完成签到 ,获得积分10
4秒前
星辰大海应助超人不会飞采纳,获得10
9秒前
susu发布了新的文献求助10
10秒前
研友_VZG7GZ应助科研通管家采纳,获得10
10秒前
充电宝应助科研通管家采纳,获得10
11秒前
科研通AI2S应助科研通管家采纳,获得10
11秒前
Jasper应助科研通管家采纳,获得10
11秒前
hui发布了新的文献求助10
12秒前
20秒前
乐观的小笼包完成签到,获得积分10
27秒前
summer发布了新的文献求助10
28秒前
大个应助醉酒笑红尘采纳,获得10
29秒前
包容沛儿完成签到 ,获得积分10
30秒前
在水一方应助summer采纳,获得10
32秒前
二汀完成签到 ,获得积分10
36秒前
hui完成签到,获得积分20
36秒前
hhhhh完成签到 ,获得积分10
38秒前
47秒前
wang5945发布了新的文献求助10
48秒前
布丁儿完成签到 ,获得积分10
50秒前
Sandy完成签到 ,获得积分10
53秒前
53秒前
54秒前
无花果应助阔达凝阳采纳,获得10
55秒前
cherish完成签到,获得积分20
57秒前
Szhou发布了新的文献求助10
57秒前
薰硝壤应助hui采纳,获得30
58秒前
59秒前
魁梧的太清完成签到 ,获得积分10
1分钟前
deswin完成签到 ,获得积分10
1分钟前
正在摸鱼仙人完成签到,获得积分10
1分钟前
Raunio完成签到,获得积分10
1分钟前
粉红色的滑动变阻器完成签到 ,获得积分10
1分钟前
orixero应助Szhou采纳,获得10
1分钟前
喜宝完成签到 ,获得积分10
1分钟前
Jasper应助甜美的雅旋采纳,获得10
1分钟前
cherish关注了科研通微信公众号
1分钟前
专一的芒果完成签到 ,获得积分10
1分钟前
高分求助中
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
Retention of title in secured transactions law from a creditor's perspective: A comparative analysis of selected (non-)functional approaches 500
"Sixth plenary session of the Eighth Central Committee of the Communist Party of China" 400
New China Forges Ahead: Important Documents of the Third Session of the First National Committee of the Chinese People's Political Consultative Conference 400
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 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3056425
求助须知:如何正确求助?哪些是违规求助? 2713032
关于积分的说明 7434284
捐赠科研通 2357989
什么是DOI,文献DOI怎么找? 1249182
科研通“疑难数据库(出版商)”最低求助积分说明 606972
版权声明 596195