S2A: Scale-Attention-Aware Networks for Video Super-Resolution

Convolutional Neural Networks (CNNs) have been widely used in video super-resolution (VSR). Most existing VSR methods focus on how to utilize the information of multiple frames, while neglecting the feature correlations of the intermediate features, thus limiting the feature expression of the models...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taian Guo, Tao Dai, Ling Liu, Zexuan Zhu, Shu-Tao Xia
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	scale-and-attention-aware criss-cross channel attention video super-resolution Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/b7d53997d2bb46e89a8f6f647cae8cef
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b7d53997d2bb46e89a8f6f647cae8cef
record_format	dspace
spelling	oai:doaj.org-article:b7d53997d2bb46e89a8f6f647cae8cef2021-11-25T17:29:18ZS2A: Scale-Attention-Aware Networks for Video Super-Resolution10.3390/e231113981099-4300https://doaj.org/article/b7d53997d2bb46e89a8f6f647cae8cef2021-10-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1398https://doaj.org/toc/1099-4300Convolutional Neural Networks (CNNs) have been widely used in video super-resolution (VSR). Most existing VSR methods focus on how to utilize the information of multiple frames, while neglecting the feature correlations of the intermediate features, thus limiting the feature expression of the models. To address this problem, we propose a novel SAA network, that is, Scale-and-Attention-Aware Networks, to apply different attention to different temporal-length streams, while further exploring both spatial and channel attention on separate streams with a newly proposed Criss-Cross Channel Attention Module (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>C</mi><mn>3</mn></msup><mi>A</mi><mi>M</mi></mrow></semantics></math></inline-formula>). Experiments on public VSR datasets demonstrate the superiority of our method over other state-of-the-art methods in terms of both quantitative and qualitative metrics.Taian GuoTao DaiLing LiuZexuan ZhuShu-Tao XiaMDPI AGarticlescale-and-attention-awarecriss-cross channel attentionvideo super-resolutionScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1398, p 1398 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	scale-and-attention-aware criss-cross channel attention video super-resolution Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	scale-and-attention-aware criss-cross channel attention video super-resolution Science Q Astrophysics QB460-466 Physics QC1-999 Taian Guo Tao Dai Ling Liu Zexuan Zhu Shu-Tao Xia S2A: Scale-Attention-Aware Networks for Video Super-Resolution
description	Convolutional Neural Networks (CNNs) have been widely used in video super-resolution (VSR). Most existing VSR methods focus on how to utilize the information of multiple frames, while neglecting the feature correlations of the intermediate features, thus limiting the feature expression of the models. To address this problem, we propose a novel SAA network, that is, Scale-and-Attention-Aware Networks, to apply different attention to different temporal-length streams, while further exploring both spatial and channel attention on separate streams with a newly proposed Criss-Cross Channel Attention Module (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>C</mi><mn>3</mn></msup><mi>A</mi><mi>M</mi></mrow></semantics></math></inline-formula>). Experiments on public VSR datasets demonstrate the superiority of our method over other state-of-the-art methods in terms of both quantitative and qualitative metrics.
format	article
author	Taian Guo Tao Dai Ling Liu Zexuan Zhu Shu-Tao Xia
author_facet	Taian Guo Tao Dai Ling Liu Zexuan Zhu Shu-Tao Xia
author_sort	Taian Guo
title	S2A: Scale-Attention-Aware Networks for Video Super-Resolution
title_short	S2A: Scale-Attention-Aware Networks for Video Super-Resolution
title_full	S2A: Scale-Attention-Aware Networks for Video Super-Resolution
title_fullStr	S2A: Scale-Attention-Aware Networks for Video Super-Resolution
title_full_unstemmed	S2A: Scale-Attention-Aware Networks for Video Super-Resolution
title_sort	s2a: scale-attention-aware networks for video super-resolution
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b7d53997d2bb46e89a8f6f647cae8cef
work_keys_str_mv	AT taianguo s2ascaleattentionawarenetworksforvideosuperresolution AT taodai s2ascaleattentionawarenetworksforvideosuperresolution AT lingliu s2ascaleattentionawarenetworksforvideosuperresolution AT zexuanzhu s2ascaleattentionawarenetworksforvideosuperresolution AT shutaoxia s2ascaleattentionawarenetworksforvideosuperresolution
_version_	1718412307131793408

S2A: Scale-Attention-Aware Networks for Video Super-Resolution

Ejemplares similares