Deep memory and prediction neural network for video prediction

被引：7

作者：

Liu, Zhipeng ^{[1
,3
]}

Chai, Xiujuan ^{[1
,2
]}

Chen, Xilin ^{[1
,3
]}

机构：

[1] Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China

[2] Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100081, Peoples R China

[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China

来源：

NEUROCOMPUTING | 2019年 / 331卷

关键词：

Video prediction; Predictive error; Memory mechanism; Neural network; WORKING-MEMORY; COGNITION;

D O I：

10.1016/j.neucom.2018.11.065

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Inspired by the concept of memory mechanism and predictive coding from the cognitive neuroscience, this paper presents a deep memory and prediction neural network (DMPNet) for video prediction. Correspondingly, memory and error propagation units are designed in DMPNet to capture the previous spatial-temporal information and compute current predictive error which is forwarded to the prediction unit for correcting the subsequent video prediction. Subsequently, prediction unit takes the information stored in memory unit and predictive error of previous frame as input to predict the next frame. We evaluate our method on two public real-world datasets and demonstrate that the proposed DMPNet outperforms some state-of-the-art methods quantitatively and qualitatively. (C) 2018 Elsevier B.V. All rights reserved.

引用

页码：235 / 241

页数：7