Semi-Supervised Crowd Counting With Spatial Temporal Consistency and Pseudo-Label Filter

Author:

Wang Xin1ORCID,Zhan Yue1,Zhao Yang2,Yang Tangwen1ORCID,Ruan Qiuqi1

Affiliation:

1. Beijing Key Laboratory of Advanced Information Science and Network Technology and the Institute of Information Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China

2. College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China

Funder

Fundamental Research Funds for the Central Universities

State’s Key Project of Research and Development Plan

National Natural Science Foundation of China

China Post-Doctoral Science Foundation

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Reference59 articles.

1. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks;lee;Proc Int Conf Mach Learn (ICML),2013

2. Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

3. Almost Unsupervised Learning for Dense Crowd Counting

4. Scale Aggregation Network for Accurate and Efficient Crowd Counting

5. Unsupervised data augmentation for consistency training;xie;Proc NIPS,2020

Cited by 4 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. Learning Models in Crowd Analysis: A Review;Archives of Computational Methods in Engineering;2024-06-24

2. MJPNet-S*: Multistyle Joint-Perception Network With Knowledge Distillation for Drone RGB-Thermal Crowd Density Estimation in Smart Cities;IEEE Internet of Things Journal;2024-06-01

3. Cross-scale Vision Transformer for crowd localization;Journal of King Saud University - Computer and Information Sciences;2024-02

4. BLUES: Before-reLU-EStimates Bayesian Inference for Crowd Counting;Image Analysis and Processing – ICIAP 2023;2023

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