Detailed Information

Cited 4 time in webofscience Cited 4 time in scopus
Metadata Downloads

Group-based bi-directional recurrent wavelet neural network for efficient video super-resolution (VSR)

Full metadata record
DC Field Value Language
dc.contributor.authorChoi, Young-Ju-
dc.contributor.authorLee, Young-Woon-
dc.contributor.authorKim, Byung-Gyu-
dc.date.accessioned2023-11-08T07:47:42Z-
dc.date.available2023-11-08T07:47:42Z-
dc.date.issued2022-12-
dc.identifier.issn0167-8655-
dc.identifier.issn1872-7344-
dc.identifier.urihttps://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/152270-
dc.description.abstractVideo super-resolution (VSR) is an important technology for enhancing the quality of video frames. The recurrent neural network (RNN)-based approach is suitable for sequential data because it can use accumulated temporal information. However, since existing methods only tend to capture slow and symmetrical motion with low frame rate, there are still limitations to restore the missing details for more dynamic motion. Most of the previous methods using spatial information treat different types of the spatial features identically. It leads to lack of obtaining meaningful information and enhancing the fine details. We propose a group-based bi-directional recurrent wavelet neural network (GBR-WNN) to exploit spatio-temporal information effectively. The proposed group-based bi-directional RNN (GBR) framework is built on the well-structured process with the group of pictures (GOP). In a GOP, we resolves the low-resolution (LR) frames from border frames to center target frame. Because super-resolved features in a GOP are cumulative, neighboring features are improved progressively and asymmetrical motion can be dealt with. Also, we propose a temporal wavelet attention (TWA) adopting attention module for both spatial and temporal features simultaneously based on discrete wavelet transform. Experiments show that the proposed scheme achieves superior performance compared with state-of-the-art methods. © 2022-
dc.format.extent8-
dc.language영어-
dc.language.isoENG-
dc.publisherElsevier B.V.-
dc.titleGroup-based bi-directional recurrent wavelet neural network for efficient video super-resolution (VSR)-
dc.typeArticle-
dc.publisher.location네델란드-
dc.identifier.doi10.1016/j.patrec.2022.11.014-
dc.identifier.scopusid2-s2.0-85142323060-
dc.identifier.wosid000919537100018-
dc.identifier.bibliographicCitationPattern Recognition Letters, v.164, pp 246 - 253-
dc.citation.titlePattern Recognition Letters-
dc.citation.volume164-
dc.citation.startPage246-
dc.citation.endPage253-
dc.type.docTypeArticle-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.subject.keywordAuthorAttention mechanism-
dc.subject.keywordAuthorDiscrete wavelet transform-
dc.subject.keywordAuthorRecurrent neural network-
dc.subject.keywordAuthorVideo super-resolution-
dc.identifier.urlhttps://www.sciencedirect.com/science/article/pii/S0167865522003440-
Files in This Item
Go to Link
Appears in
Collections
ICT융합공학부 > IT공학전공 > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Kim, Byung Gyu photo

Kim, Byung Gyu
공과대학 (인공지능공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE