PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
Author:
Affiliation:
1. MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
2. School of Software, BNRist, Tsinghua University, Beijing, China
3. Microsoft Corporation, Wangjing, China
Funder
National Natural Science Foundation of China
Beijing Nova Program
BNRist Innovation Fund
Shanghai Municipal Science and Technology Major Project
Shanghai Sailing Program
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/ielx7/34/10008914/09749915.pdf?arnumber=9749915
Reference88 articles.
1. Self-supervised visual planning with temporal skip connections;ebert;Proc Conf Robot Learn,2016
2. Decomposing motion and content for natural video sequence prediction;villegas;Proc Int Conf Learn Representations,2017
3. Deep visual foresight for planning robot motion
4. Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
5. Backpropagation through time: what it does and how to do it
Cited by 84 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. FastNet: A feature aggregation spatiotemporal network for predictive learning;Engineering Applications of Artificial Intelligence;2024-04
2. Effective LSTMs with seasonal-trend decomposition and adaptive learning and niching-based backtracking search algorithm for time series forecasting;Expert Systems with Applications;2024-02
3. An Long Short-Term Memory Model with Multi-Scale Context Fusion and Attention for Radar Echo Extrapolation;Remote Sensing;2024-01-17
4. Accurate nowcasting of cloud cover at solar photovoltaic plants using geostationary satellite images;Nature Communications;2024-01-13
5. Multi-Scale Spatio-Temporal Fusion With Adaptive Brain Topology Learning for fMRI Based Neural Decoding;IEEE Journal of Biomedical and Health Informatics;2024-01
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