Human action recognition using attention based LSTM network with dilated CNN features

计算机科学 Softmax函数 判别式 人工智能 卷积神经网络 模式识别(心理学) 帧(网络) 人工神经网络 机器学习 电信
作者
Khan Muhammad,Mustaqeem Khan,Amin Ullah,Ali Shariq Imran,Muhammad Sajjad,Mustafa Servet Kıran,Giovanna Sannino,Victor Hugo C. de Albuquerque
出处
期刊:Future Generation Computer Systems [Elsevier BV]
卷期号:125: 820-830 被引量:158
标识
DOI:10.1016/j.future.2021.06.045
摘要

Human action recognition in videos is an active area of research in computer vision and pattern recognition. Nowadays, artificial intelligence (AI) based systems are needed for human-behavior assessment and security purposes. The existing action recognition techniques are mainly using pre-trained weights of different AI architectures for the visual representation of video frames in the training stage, which affect the features’ discrepancy determination, such as the distinction between the visual and temporal signs. To address this issue, we propose a bi-directional long short-term memory (BiLSTM) based attention mechanism with a dilated convolutional neural network (DCNN) that selectively focuses on effective features in the input frame to recognize the different human actions in the videos. In this diverse network, we use the DCNN layers to extract the salient discriminative features by using the residual blocks to upgrade the features that keep more information than a shallow layer. Furthermore, we feed these features into a BiLSTM to learn the long-term dependencies, which is followed by the attention mechanism to boost the performance and extract the additional high-level selective action related patterns and cues. We further use the center loss with Softmax to improve the loss function that achieves a higher performance in the video-based action classification. The proposed system is evaluated on three benchmarks, i.e., UCF11, UCF sports, and J-HMDB datasets for which it achieved a recognition rate of 98.3%, 99.1%, and 80.2%, respectively, showing 1%–3% improvement compared to the state-of-the-art (SOTA) methods.
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
淡烟流水发布了新的文献求助10
1秒前
1秒前
小李发布了新的文献求助30
2秒前
汉堡包应助明芬采纳,获得30
2秒前
爆米花应助彭栋采纳,获得10
2秒前
3秒前
3秒前
MeiyanZou完成签到 ,获得积分10
3秒前
6秒前
6秒前
潇湘雪月发布了新的文献求助10
7秒前
7秒前
7秒前
8秒前
感动黄豆发布了新的文献求助10
8秒前
hhhblabla应助东方红采纳,获得10
10秒前
Poker应助sb采纳,获得10
11秒前
Ginger发布了新的文献求助10
11秒前
吃骨头的猫完成签到,获得积分10
11秒前
小李完成签到,获得积分10
11秒前
11秒前
12秒前
明芬发布了新的文献求助30
14秒前
14秒前
Smile完成签到,获得积分10
14秒前
Chaoe完成签到,获得积分10
17秒前
建国发布了新的文献求助10
18秒前
闪闪w发布了新的文献求助10
21秒前
淡烟流水完成签到,获得积分10
21秒前
俏皮芷蕊完成签到,获得积分10
22秒前
完美世界应助忐忑的阑香采纳,获得10
22秒前
华仔应助兴奋千兰采纳,获得10
27秒前
Ginger完成签到,获得积分10
28秒前
潇湘雪月发布了新的文献求助10
31秒前
科研通AI5应助科研通管家采纳,获得10
33秒前
33秒前
佳琳有乐完成签到,获得积分10
33秒前
33秒前
小蘑菇应助科研通管家采纳,获得10
33秒前
大模型应助科研通管家采纳,获得10
33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 3989115
求助须知:如何正确求助?哪些是违规求助? 3531367
关于积分的说明 11253688
捐赠科研通 3269986
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882078
科研通“疑难数据库(出版商)”最低求助积分说明 809105