A ViT‐Based Adaptive Recurrent Mobilenet With Attention Network for Video Compression and Bit‐Rate Reduction Using Improved Heuristic Approach Under Versatile Video Coding.
Saved in:
| Title: | A ViT‐Based Adaptive Recurrent Mobilenet With Attention Network for Video Compression and Bit‐Rate Reduction Using Improved Heuristic Approach Under Versatile Video Coding. |
|---|---|
| Authors: | Padmapriya, D.1,2 (AUTHOR) dpadmapriya.ece@gmail.com, Roseline A, Ameelia2 (AUTHOR) |
| Source: | Computational Intelligence. Dec2024, Vol. 40 Issue 6, p1-22. 22p. |
| Subjects: | Video compression standards, Transformer models, Bit rate, Video compression, Deep learning, Video processing, Video coding |
| Abstract: | Video compression received attention from the communities of video processing and deep learning. Modern learning‐aided mechanisms use a hybrid coding approach to reduce redundancy in pixel space across time and space, improving motion compensation accuracy. The experiments in video compression have important improvements in past years. The Versatile Video Coding (VVC) is the primary enhancing standard of video compression which is also referred to as H. 226. The VVC codec is a block‐assisted hybrid codec, making it highly capable and complex. Video coding effectively compresses data while reducing compression artifacts, enhancing the quality and functionality of AI video technologies. However, the traditional models suffer from the incorrect compression of the motion and ineffective compensation frameworks of the motion leading to compression faults with a minimal trade‐off of the rate distortion. This work implements an automated and effective video compression task under VVC using a deep learning approach. Motion estimation is conducted using the Motion Vector (MV) encoder‐decoder model to track movements in the video. Based on these MV, the reconstruction of the frame is carried out to compensate for the motions. The residual images are obtained by using Vision Transformer‐based Adaptive Recurrent MobileNet with Attention Network (ViT‐ARMAN). The parameters optimization of the ViT‐ARMAN is done using the Opposition‐based Golden Tortoise Beetle Optimizer (OGTBO). Entropy coding is used in the training phase of the developed work to find the bit rate of residual images. Extensive experiments were conducted to demonstrate the effectiveness of the developed deep learning‐based method for video compression and bit rate reduction under VVC. [ABSTRACT FROM AUTHOR] |
| Copyright of Computational Intelligence is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 181778421 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A ViT‐Based Adaptive Recurrent Mobilenet With Attention Network for Video Compression and Bit‐Rate Reduction Using Improved Heuristic Approach Under Versatile Video Coding. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Padmapriya%2C+D%2E%22">Padmapriya, D.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> dpadmapriya.ece@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Roseline+A%2C+Ameelia%22">Roseline A, Ameelia</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Computational+Intelligence%22">Computational Intelligence</searchLink>. Dec2024, Vol. 40 Issue 6, p1-22. 22p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Video+compression+standards%22">Video compression standards</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Bit+rate%22">Bit rate</searchLink><br /><searchLink fieldCode="DE" term="%22Video+compression%22">Video compression</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Video+processing%22">Video processing</searchLink><br /><searchLink fieldCode="DE" term="%22Video+coding%22">Video coding</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Video compression received attention from the communities of video processing and deep learning. Modern learning‐aided mechanisms use a hybrid coding approach to reduce redundancy in pixel space across time and space, improving motion compensation accuracy. The experiments in video compression have important improvements in past years. The Versatile Video Coding (VVC) is the primary enhancing standard of video compression which is also referred to as H. 226. The VVC codec is a block‐assisted hybrid codec, making it highly capable and complex. Video coding effectively compresses data while reducing compression artifacts, enhancing the quality and functionality of AI video technologies. However, the traditional models suffer from the incorrect compression of the motion and ineffective compensation frameworks of the motion leading to compression faults with a minimal trade‐off of the rate distortion. This work implements an automated and effective video compression task under VVC using a deep learning approach. Motion estimation is conducted using the Motion Vector (MV) encoder‐decoder model to track movements in the video. Based on these MV, the reconstruction of the frame is carried out to compensate for the motions. The residual images are obtained by using Vision Transformer‐based Adaptive Recurrent MobileNet with Attention Network (ViT‐ARMAN). The parameters optimization of the ViT‐ARMAN is done using the Opposition‐based Golden Tortoise Beetle Optimizer (OGTBO). Entropy coding is used in the training phase of the developed work to find the bit rate of residual images. Extensive experiments were conducted to demonstrate the effectiveness of the developed deep learning‐based method for video compression and bit rate reduction under VVC. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Computational Intelligence is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=181778421 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1111/coin.70014 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 22 StartPage: 1 Subjects: – SubjectFull: Video compression standards Type: general – SubjectFull: Transformer models Type: general – SubjectFull: Bit rate Type: general – SubjectFull: Video compression Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Video processing Type: general – SubjectFull: Video coding Type: general Titles: – TitleFull: A ViT‐Based Adaptive Recurrent Mobilenet With Attention Network for Video Compression and Bit‐Rate Reduction Using Improved Heuristic Approach Under Versatile Video Coding. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Padmapriya, D. – PersonEntity: Name: NameFull: Roseline A, Ameelia IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 08247935 Numbering: – Type: volume Value: 40 – Type: issue Value: 6 Titles: – TitleFull: Computational Intelligence Type: main |
| ResultId | 1 |
