Improvement of predictive recurrent neural network based on feature fusion

Xiaomei Zhang; Zhilin Teng; Jiwei Hu

doi:10.1117/12.2641408

10 November 2022 Improvement of predictive recurrent neural network based on feature fusion

Xiaomei Zhang, Zhilin Teng, Jiwei Hu

Proceedings Volume 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022); 123480Z (2022) https://doi.org/10.1117/12.2641408
Event: 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 2022, Zhuhai, China

Abstract

Video can be regarded as a sequence composed of several related images. To predict video, we should not only grasp the characteristics of a single image, but also combine the temporal logic information between images. The Predictive Recurrent Neural Network (PredRNN) is a video frame prediction network using spatiotemporal memory stream structure in spatiotemporal LSTM network. This paper introduces the improved method of PredRNN based on feature fusion. The spatiotemporal memory flow structure of PredRNN will bring the problem of gradient disappearance with the increase of depth. This paper proposes to perform feature fusion on the spatiotemporal memory information and increase the gradient of deep network to improve the long-term video prediction effect of the network. Finally, the moving MNIST dataset and the KTH dataset are used to prove our network. The experimental results show that our method has a certain improvement over the PredRNN.

Citation Download Citation

Xiaomei Zhang, Zhilin Teng, and Jiwei Hu "Improvement of predictive recurrent neural network based on feature fusion", Proc. SPIE 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 123480Z (10 November 2022); https://doi.org/10.1117/12.2641408

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available