Facial Action Unit Detection via Adaptive Attention and Relation

Author:

Shao Zhiwen1ORCID,Zhou Yong1ORCID,Cai Jianfei2ORCID,Zhu Hancheng1ORCID,Yao Rui1ORCID

Affiliation:

1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China

2. Faculty of Information Technology, Monash University, Clayton, Victoria, Australia

Funder

National Natural Science Foundation of China

High-Level Talent Program for Innovation and Entrepreneurship (ShuangChuang Doctor) of Jiangsu Province

Talent Program for Deputy General Manager of Science and Technology of Jiangsu Province

Natural Science Foundation of Jiangsu Province

Shanghai Sailing Program

Fundamental Research Funds for the Central Universities

K. C. Wong Education Foundation, Hong Kong

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer Graphics and Computer-Aided Design,Software

Reference66 articles.

1. Capturing Global Semantic Relationships for Facial Action Unit Recognition

2. ImageNet classification with deep convolutional neural networks;krizhevsky;Proc Adv Neural Inf Process Syst,2012

3. Capturing Complex Spatio-temporal Relations among Facial Muscles for Facial Expression Recognition

4. LIBLINEAR: A library for large linear classification;fan;J Mach Learn Res,2008

5. Deep Structure Inference Network for Facial Action Unit Recognition

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A method for recognizing facial expression intensity based on facial muscle variations;Multimedia Tools and Applications;2024-07-13

2. Facial Action Unit Recognition Based on Self-Attention Spatiotemporal Fusion;Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of Things;2024-05-24

3. KHFA: Knowledge-Driven Hierarchical Feature Alignment Framework for Subject-Invariant Facial Action Unit Detection;IEEE Transactions on Instrumentation and Measurement;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3