Attention-Based Bi-Prediction Network for Versatile Video Coding (VVC) over 5G Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Young-Ju | - |
dc.contributor.author | Lee, Young-Woon | - |
dc.contributor.author | Kim, Jongho | - |
dc.contributor.author | Jeong, Se Yoon | - |
dc.contributor.author | Choi, Jin Soo | - |
dc.contributor.author | Kim, Byung-Gyu | - |
dc.date.accessioned | 2023-11-08T06:47:40Z | - |
dc.date.available | 2023-11-08T06:47:40Z | - |
dc.date.issued | 2023-03-01 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.issn | 1424-3210 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151952 | - |
dc.description.abstract | As the demands of various network-dependent services such as Internet of things (IoT)applications, autonomous driving, and augmented and virtual reality (AR/VR) increase, the fifthgeneration(5G) network is expected to become a key communication technology. The latest videocoding standard, versatile video coding (VVC), can contribute to providing high-quality services byachieving superior compression performance. In video coding, inter bi-prediction serves to improvethe coding efficiency significantly by producing a precise fused prediction block. Although block-wisemethods, such as bi-prediction with CU-level weight (BCW), are applied in VVC, it is still difficult forthe linear fusion-based strategy to represent diverse pixel variations inside a block. In addition, apixel-wise method called bi-directional optical flow (BDOF) has been proposed to refine bi-predictionblock. However, the non-linear optical flow equation in BDOF mode is applied under assumptions,so this method is still unable to accurately compensate various kinds of bi-prediction blocks. Inthis paper, we propose an attention-based bi-prediction network (ABPN) to substitute for the wholeexisting bi-prediction methods. The proposed ABPN is designed to learn efficient representations ofthe fused features by utilizing an attention mechanism. Furthermore, the knowledge distillation (KD)-based approach is employed to compress the size of the proposed network while keeping comparableoutput as the large model. The proposed ABPN is integrated into the VTM-11.0 NNVC-1.0 standardreference software. When compared with VTM anchor, it is verified that the BD-rate reduction of thelightweighted ABPN can be up to 5.89% and 4.91% on Y component under random access (RA) andlow delay B (LDB), respectively. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | MDPI | - |
dc.title | Attention-Based Bi-Prediction Network for Versatile Video Coding (VVC) over 5G Network | - |
dc.type | Article | - |
dc.publisher.location | 스위스 | - |
dc.identifier.doi | 10.3390/s23052631 | - |
dc.identifier.scopusid | 2-s2.0-85149805466 | - |
dc.identifier.wosid | 000948124300001 | - |
dc.identifier.bibliographicCitation | SENSORS, v.23, no.5 | - |
dc.citation.title | SENSORS | - |
dc.citation.volume | 23 | - |
dc.citation.number | 5 | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Instruments & Instrumentation | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Analytical | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Instruments & Instrumentation | - |
dc.subject.keywordPlus | ALGORITHM | - |
dc.subject.keywordPlus | HEVC | - |
dc.subject.keywordAuthor | 5G | - |
dc.subject.keywordAuthor | versatile video coding | - |
dc.subject.keywordAuthor | attention mechanism | - |
dc.subject.keywordAuthor | bi-prediction | - |
dc.subject.keywordAuthor | convolutional neural network | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.