From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

Published:2023 Issue: Volume: Page:1-15
ISSN:0162-8828
Container-title:IEEE Transactions on Pattern Analysis and Machine Intelligence
language:
Short-container-title:IEEE Trans. Pattern Anal. Mach. Intell.

Author:

Mallis Dimitrios¹^ORCID,Sanchez Enrique²^ORCID,Bell Matt³^ORCID,Tzimiropoulos Georgios⁴

Affiliation:

1. Computer Vision Lab, University of Nottingham, U.K.

2. Samsung AI Center Cambridge, U.K.

3. Department of Animal and Agriculture, Hartpury University, U.K.

4. School of Electronic Engineering and Computer Science, Queen Mary University of London, U.K.

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

http://xplorestaging.ieee.org/ielx7/34/4359286/10005822.pdf?arnumber=10005822

Reference89 articles.

1. Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts

2. Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model Using Deep Non-Rigid Structure From Motion

3. Unsupervised learning of visual features by contrasting cluster assignments;caron;Proc Int Conf Neural Inf Process,2020

4. 300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge

5. Unsupervised discovery of object landmarks via contrastive learning;cheng,2020

Cited by 1 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. Unsupervised detection of contrast enhanced highlight landmarks;IET Computer Vision;2023-05-04

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