Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach

This paper introduces a novel deep-learning assisted video list decoding method for error-prone video transmission systems. Unlike traditional list decoding techniques, our proposed system uses a Transformer-based no-reference image quality assessment method to select the highest-scoring reconstruct...

Full description

Saved in:
Bibliographic Details
Main Authors: Yujing Zhang, Stephane Coulombe, Francois-Xavier Coudoux, Alexis Guichemerre, Patrick Corlay
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10755955/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060961613873152
author Yujing Zhang
Stephane Coulombe
Francois-Xavier Coudoux
Alexis Guichemerre
Patrick Corlay
author_facet Yujing Zhang
Stephane Coulombe
Francois-Xavier Coudoux
Alexis Guichemerre
Patrick Corlay
author_sort Yujing Zhang
collection DOAJ
description This paper introduces a novel deep-learning assisted video list decoding method for error-prone video transmission systems. Unlike traditional list decoding techniques, our proposed system uses a Transformer-based no-reference image quality assessment method to select the highest-scoring reconstructed video candidate after reception. Three new components are defined and used in the Transformer-assisted image quality evaluation metric: neighborhood-based patch fidelity aggregation, discriminant color texture transformation and ranking-constrained penalty loss function. We have also created our own database of non-uniformly distorted images, similar to those that might result from transmission errors, in a High Efficiency Video Coding (HEVC) context. In our specific testing context, our improved Transformer-assisted method has a decision accuracy of 100% for intra-coded image, while, for errors occurring in an inter image, it is 96%. Notably, in the few cases where a wrong choice is made, the selected candidate&#x2019;s quality remains similar to the intact frame. Code: <uri>https://github.com/Yujing0926/Robust-Video-List-Decoding-Using-a-Deep-Learning-Approach</uri>.
format Article
id doaj-art-5b4e4bf62d9e4984bbbeb8c90b9a28bd
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5b4e4bf62d9e4984bbbeb8c90b9a28bd2025-08-20T02:50:25ZengIEEEIEEE Access2169-35362024-01-011217063217064710.1109/ACCESS.2024.350115210755955Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning ApproachYujing Zhang0https://orcid.org/0009-0003-9371-0502Stephane Coulombe1https://orcid.org/0000-0003-4495-3906Francois-Xavier Coudoux2https://orcid.org/0000-0002-5817-7429Alexis Guichemerre3https://orcid.org/0009-0008-0894-1901Patrick Corlay4https://orcid.org/0000-0002-3407-8805Department of Software and IT Engineering, &#x00C9;cole de technologie sup&#x00E9;rieure, Universit&#x00E9; du Qu&#x00E9;bec, Montr&#x00E9;al, QC, CanadaDepartment of Software and IT Engineering, &#x00C9;cole de technologie sup&#x00E9;rieure, Universit&#x00E9; du Qu&#x00E9;bec, Montr&#x00E9;al, QC, CanadaCNRS, UMR 8520, D&#x00E9;partement d&#x2019;Opto-Acousto-&#x00C9;lectronique (DOAE), Institut d&#x2019;&#x00C9;lectronique de Micro&#x00E9;lectronique et de Nanotechnologie (IEMN), Universit&#x00E9; Polytechnique Hauts-de-France, Valenciennes, FranceDepartment of Software and IT Engineering, &#x00C9;cole de technologie sup&#x00E9;rieure, Universit&#x00E9; du Qu&#x00E9;bec, Montr&#x00E9;al, QC, CanadaCNRS, UMR 8520, D&#x00E9;partement d&#x2019;Opto-Acousto-&#x00C9;lectronique (DOAE), Institut d&#x2019;&#x00C9;lectronique de Micro&#x00E9;lectronique et de Nanotechnologie (IEMN), Universit&#x00E9; Polytechnique Hauts-de-France, Valenciennes, FranceThis paper introduces a novel deep-learning assisted video list decoding method for error-prone video transmission systems. Unlike traditional list decoding techniques, our proposed system uses a Transformer-based no-reference image quality assessment method to select the highest-scoring reconstructed video candidate after reception. Three new components are defined and used in the Transformer-assisted image quality evaluation metric: neighborhood-based patch fidelity aggregation, discriminant color texture transformation and ranking-constrained penalty loss function. We have also created our own database of non-uniformly distorted images, similar to those that might result from transmission errors, in a High Efficiency Video Coding (HEVC) context. In our specific testing context, our improved Transformer-assisted method has a decision accuracy of 100% for intra-coded image, while, for errors occurring in an inter image, it is 96%. Notably, in the few cases where a wrong choice is made, the selected candidate&#x2019;s quality remains similar to the intact frame. Code: <uri>https://github.com/Yujing0926/Robust-Video-List-Decoding-Using-a-Deep-Learning-Approach</uri>.https://ieeexplore.ieee.org/document/10755955/Video transmissionlist decodingnon-uniform distortionsno-reference image quality assessmentvision transformerconvolutional neural network
spellingShingle Yujing Zhang
Stephane Coulombe
Francois-Xavier Coudoux
Alexis Guichemerre
Patrick Corlay
Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
IEEE Access
Video transmission
list decoding
non-uniform distortions
no-reference image quality assessment
vision transformer
convolutional neural network
title Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
title_full Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
title_fullStr Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
title_full_unstemmed Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
title_short Robust Video List Decoding in Error-Prone Transmission Systems Using a Deep Learning Approach
title_sort robust video list decoding in error prone transmission systems using a deep learning approach
topic Video transmission
list decoding
non-uniform distortions
no-reference image quality assessment
vision transformer
convolutional neural network
url https://ieeexplore.ieee.org/document/10755955/
work_keys_str_mv AT yujingzhang robustvideolistdecodinginerrorpronetransmissionsystemsusingadeeplearningapproach
AT stephanecoulombe robustvideolistdecodinginerrorpronetransmissionsystemsusingadeeplearningapproach
AT francoisxaviercoudoux robustvideolistdecodinginerrorpronetransmissionsystemsusingadeeplearningapproach
AT alexisguichemerre robustvideolistdecodinginerrorpronetransmissionsystemsusingadeeplearningapproach
AT patrickcorlay robustvideolistdecodinginerrorpronetransmissionsystemsusingadeeplearningapproach