A Novel Multiple-View Adversarial Learning Network for Unsupervised Domain Adaptation Action Recognition

人工智能 计算机科学 判别式 机器学习 模式识别(心理学) 特征学习 特征提取 稳健性(进化) 水准点(测量) RGB颜色模型 光流 图像(数学) 地理 大地测量学 化学 基因 生物化学
作者
Zan Gao,Yibo Zhao,Hua Zhang,Da Chen,An-An Liu,Shengyong Chen
出处
期刊:IEEE transactions on cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:52 (12): 13197-13211 被引量:6
标识
DOI:10.1109/tcyb.2021.3105637
摘要

Abstract-domain adaptation action recognition is a hot research topic in machine learning and some effective approaches have been proposed. However, samples in the target domain with label information are often required by these approaches. Moreover, domain-invariant discriminative feature learning, feature fusion, and classifier module learning have not been explored in an end-to-end framework. Thus, in this study, we propose a novel end-to-end multiple-view adversarial learning network (MAN) for unsupervised domain adaptation action recognition in which the fusion of RGB and optical-flow features, domain-invariant discrimination feature learning, and action recognition is conducted in a unified framework. Specifically, a robust spatiotemporal feature extraction network, including a spatial transform network and an adaptive intrachannel weight network, is proposed to improve the scale invariance and robustness of the method. Then, a self-attention mechanism fusion module is designed to adaptively fuse the RGB and optical-flow features. Moreover, a multiview adversarial learning loss is developed to obtain domain-invariant discriminative features. In addition, three benchmark datasets are constructed for unsupervised domain adaptation action recognition, for which all actions and samples are carefully collected from public action datasets, and their action categories are hierarchically augmented, which can guide how to extend existing action datasets. We conduct extensive experiments on four benchmark datasets, and the experimental results demonstrate that our proposed MAN can outperform several state-of-the-art unsupervised domain adaptation action recognition approaches. When the SDAI Action II-6 and SDAI Action II-11 datasets are used, MAN can achieve 3.7% ( H → U ) and 6.1% ( H → U ) improvements over the temporal attentive adversarial adaptation network (published in ICCV 2019) module, respectively. As an added contribution, the SDAI Action II-6, SDAI Action II-11, and SDAI Action II-16 datasets will be released to facilitate future research on domain adaptation action recognition.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
zwq发布了新的文献求助10
刚刚
刚刚
刚刚
所所的应助被科研通管家采纳,获得10
刚刚
自由的尔槐完成签到,获得积分10
刚刚
wu完成签到 ,获得积分10
刚刚
molihuakai的应助被科研通管家采纳,获得10
刚刚
包语梦发布了新的文献求助10
刚刚
桐桐的应助被科研通管家采纳,获得10
刚刚
搜集达人的应助被科研通管家采纳,获得10
1秒前
Hello的应助被科研通管家采纳,获得10
1秒前
鱼棒棒完成签到,获得积分10
1秒前
FashionBoy的应助被科研通管家采纳,获得10
1秒前
1秒前
CodeCraft的应助被科研通管家采纳,获得10
1秒前
1秒前
1秒前
CodeCraft的应助被29采纳,获得10
1秒前
华仔的应助被科研通管家采纳,获得10
1秒前
李爱国的应助被科研通管家采纳,获得10
2秒前
斯文败类的应助被4ll采纳,获得10
2秒前
orixero的应助被科研通管家采纳,获得10
2秒前
思源的应助被科研通管家采纳,获得10
2秒前
科目三的应助被科研通管家采纳,获得10
2秒前
赘婿的应助被科研通管家采纳,获得10
2秒前
彭于晏的应助被科研通管家采纳,获得10
2秒前
高大的映波完成签到 ,获得积分10
2秒前
脑洞疼的应助被科研通管家采纳,获得10
2秒前
桐桐的应助被科研通管家采纳,获得10
2秒前
丘比特的应助被科研通管家采纳,获得10
3秒前
张灬小胖发布了新的文献求助10
3秒前
大模型的应助被科研通管家采纳,获得10
3秒前
乐乐的应助被科研通管家采纳,获得10
3秒前
3秒前
orixero的应助被科研通管家采纳,获得10
3秒前
乐乐的应助被科研通管家采纳,获得10
3秒前
领导范儿的应助被GS采纳,获得10
3秒前
FashionBoy的应助被科研通管家采纳,获得10
3秒前
Julo发布了新的文献求助10
3秒前
3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
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8171477
求助须知:如何正确求助?哪些是违规求助? 9564248
关于积分的说明 21774106
捐赠科研通 7763073
什么是DOI,文献DOI怎么找? 3430972
关于科研通互助平台的介绍 2554805
邀请新用户注册赠送积分活动 2475887