S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adiban, Mohammad, Stefanov, Kalin, Siniscalchi, Sabato Marco, Salvi, Giampiero
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929597256302592
author Adiban, Mohammad
Stefanov, Kalin
Siniscalchi, Sabato Marco
Salvi, Giampiero
author_facet Adiban, Mohammad
Stefanov, Kalin
Siniscalchi, Sabato Marco
Salvi, Giampiero
contents We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with major challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on four challenging tasks, namely KTH Human Action, TrafficBJ, Human3.6M, and Kitti, demonstrate that our model compares favorably against state-of-the-art video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and AST-PM parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2307_06701
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
Adiban, Mohammad
Stefanov, Kalin
Siniscalchi, Sabato Marco
Salvi, Giampiero
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.2.10; I.4.10; I.4.5; I.4.2; I.2.6
We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with major challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on four challenging tasks, namely KTH Human Action, TrafficBJ, Human3.6M, and Kitti, demonstrate that our model compares favorably against state-of-the-art video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and AST-PM parameters.
title S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
I.2.10; I.4.10; I.4.5; I.4.2; I.2.6
url https://arxiv.org/abs/2307.06701