{"id":"https://openalex.org/W3202161946","doi":"https://doi.org/10.1109/lsp.2021.3116518","title":"Improving Super-Resolution Performance Using Meta-Attention Layers","display_name":"Improving Super-Resolution Performance Using Meta-Attention Layers","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3202161946","doi":"https://doi.org/10.1109/lsp.2021.3116518","mag":"3202161946"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3116518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3116518","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.14638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matthew Aquilina","orcid":"https://orcid.org/0000-0002-4039-1398"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Aquilina","raw_affiliation_strings":["The University of Edinburgh College of Medicine and Veterinary Medicine, 12206 Edinburgh, United Kingdom of Great Britain and Northern Ireland, EH93DW (e-mail: matthew.aquilina@um.edu.mt)"],"raw_orcid":"https://orcid.org/0000-0002-4039-1398","affiliations":[{"raw_affiliation_string":"The University of Edinburgh College of Medicine and Veterinary Medicine, 12206 Edinburgh, United Kingdom of Great Britain and Northern Ireland, EH93DW (e-mail: matthew.aquilina@um.edu.mt)","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christian Galea","orcid":"https://orcid.org/0000-0002-0353-7028"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Christian Galea","raw_affiliation_strings":["Department of Communications and Computer Engineering, University of Malta, 37563 Msida, Malta, (e-mail: christian.p.galea@um.edu.mt)"],"raw_orcid":"https://orcid.org/0000-0002-0353-7028","affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, University of Malta, 37563 Msida, Malta, (e-mail: christian.p.galea@um.edu.mt)","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":null,"display_name":"John Abela","orcid":"https://orcid.org/0000-0002-8162-5816"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"John Abela","raw_affiliation_strings":["Msida, Malta, (e-mail: john.abela@um.edu.mt)"],"raw_orcid":"https://orcid.org/0000-0002-8162-5816","affiliations":[{"raw_affiliation_string":"Msida, Malta, (e-mail: john.abela@um.edu.mt)","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kenneth P. Camilleri","orcid":"https://orcid.org/0000-0003-0436-6408"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Kenneth P. Camilleri","raw_affiliation_strings":["Systems and Control Engineering, University of Malta, Msida, Malta, Malta, MSD2080 (e-mail: kenneth.camilleri@um.edu.mt)"],"raw_orcid":"https://orcid.org/0000-0003-0436-6408","affiliations":[{"raw_affiliation_string":"Systems and Control Engineering, University of Malta, Msida, Malta, Malta, MSD2080 (e-mail: kenneth.camilleri@um.edu.mt)","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"last","author":{"id":null,"display_name":"Reuben A. Farrugia","orcid":"https://orcid.org/0000-0001-8106-9891"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Reuben A. Farrugia","raw_affiliation_strings":["Communications and Computer Engineering, University of Malta, 37563 Msida, NA, Malta, MSD2080 (e-mail: reuben.farrugia@um.edu.mt)"],"raw_orcid":"https://orcid.org/0000-0001-8106-9891","affiliations":[{"raw_affiliation_string":"Communications and Computer Engineering, University of Malta, 37563 Msida, NA, Malta, MSD2080 (e-mail: reuben.farrugia@um.edu.mt)","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9079,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73401293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2082","last_page":"2086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.015599999576807022,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6388999819755554},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6281999945640564},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6208000183105469},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.49779999256134033},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4887000024318695},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4684999883174896},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4178999960422516},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309000134468079},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.49779999256134033},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.32179999351501465},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2883000075817108},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2517000138759613},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2021.3116518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3116518","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2110.14638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14638","pdf_url":"https://arxiv.org/pdf/2110.14638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.14638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14638","pdf_url":"https://arxiv.org/pdf/2110.14638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2693838155","display_name":null,"funder_award_id":"R&I-2017-002-T","funder_id":"https://openalex.org/F4320321039","funder_display_name":"Malta Council for Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321039","display_name":"Malta Council for Science and Technology","ror":"https://ror.org/05qk3dq04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1791560514","https://openalex.org/W1834627138","https://openalex.org/W1930824406","https://openalex.org/W2047920195","https://openalex.org/W2110158442","https://openalex.org/W2133665775","https://openalex.org/W2192954843","https://openalex.org/W2503458650","https://openalex.org/W2739757502","https://openalex.org/W2741137940","https://openalex.org/W2798691622","https://openalex.org/W2899195858","https://openalex.org/W2903906970","https://openalex.org/W2954930822","https://openalex.org/W2962814024","https://openalex.org/W2963372104","https://openalex.org/W2964277374","https://openalex.org/W2970971581","https://openalex.org/W2983467712","https://openalex.org/W3013529009","https://openalex.org/W3014771563","https://openalex.org/W3016355810","https://openalex.org/W3034521057","https://openalex.org/W3034595214","https://openalex.org/W3035302306","https://openalex.org/W3040726448","https://openalex.org/W3109016549","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6745560452","https://openalex.org/W6753074096","https://openalex.org/W6772154291","https://openalex.org/W6782282802","https://openalex.org/W6792162099"],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4,90],"achieved":[5],"impressive":[6],"results":[7],"across":[8],"many":[9,17,109],"super-resolution":[10],"(SR)":[11],"and":[12,243,253,269,275],"image":[13,44],"restoration":[14],"tasks.":[15],"While":[16],"such":[18],"networks":[19,69,86,142,195,224],"can":[20,36,67,215],"upscale":[21],"low-resolution":[22],"(LR)":[23],"images":[24,73,262],"using":[25],"just":[26],"the":[27,31,55,60,78,105,126,163,175,187,218,241,248,257],"raw":[28],"pixel-level":[29,219],"information,":[30],"ill-posed":[32],"nature":[33,107],"of":[34,100,108,113,128,204,221,235,264],"SR":[35,85,110,141,159,194,277],"make":[37],"it":[38,199],"difficult":[39,136],"to":[40,70,77,94,104,137,161,206],"accurately":[41],"super-resolve":[42,71],"an":[43],"which":[45,156,182],"has":[46,211],"undergone":[47],"multiple":[48],"different":[49],"degradations.":[50],"Additional":[51],"information":[52,164],"(metadata)":[53],"describing":[54],"degradation":[56,88,168,229],"process":[57],"(such":[58],"as":[59,198],"blur":[61],"kernel":[62],"applied,":[63],"compression":[64],"level,":[65],"etc.)":[66],"guide":[68],"LR":[72],"with":[74,87,227],"higher":[75],"fidelity":[76],"original":[79],"source.":[80],"Previous":[81],"attempts":[82],"at":[83],"informing":[84],"parameters":[89],"indeed":[91],"been":[92],"able":[93],"improve":[95,217],"performance":[96,249],"in":[97,166,183],"a":[98,120,153,178],"number":[99],"scenarios.":[101],"However,":[102],"due":[103],"fully-convolutional":[106],"networks,":[111],"most":[112],"these":[114,133],"metadata":[115,176],"fusion":[116],"methods":[117],"either":[118],"require":[119],"complete":[121],"architectural":[122],"change,":[123],"or":[124],"necessitate":[125],"addition":[127],"significant":[129],"extra":[130],"complexity.":[131],"Thus,":[132],"approaches":[134],"are":[135],"introduce":[138,151],"into":[139,177,193],"arbitrary":[140],"without":[143],"considerable":[144],"design":[145],"alterations.":[146],"In":[147],"this":[148,285],"paper,":[149],"we":[150],"meta-attention,":[152],"simple":[154],"mechanism":[155,171],"allows":[157],"any":[158],"CNN":[160],"exploit":[162],"available":[165,288],"relevant":[167,228],"parameters.":[169],"The":[170,280],"functions":[172],"by":[173],"translating":[174],"channel":[179],"attention":[180],"vector,":[181],"turn":[184],"selectively":[185],"modulates":[186],"network's":[188],"feature":[189],"maps.":[190],"Incorporating":[191],"meta-attention":[192,214,246],"is":[196,263,287],"straightforward,":[197],"requires":[200],"no":[201],"specific":[202],"type":[203],"architecture":[205],"function":[207],"correctly.":[208],"Extensive":[209],"testing":[210],"shown":[212],"that":[213],"consistently":[216],"accuracy":[220],"state-of-the-art":[222],"(SOTA)":[223],"when":[225],"provided":[226],"metadata.":[230],"Despite":[231],"average":[232],"memory/runtime":[233],"overheads":[234],"less":[236],"than":[237],"~2.6%/0.025":[238],"seconds":[239],"for":[240,250,255,272,284],"datasets":[242],"models":[244],"considered,":[245],"improves":[247],"both":[251],"PSNR":[252],"SSIM;":[254],"PSNR,":[256],"gain":[258],"on":[259],"blurred/downsampled":[260],"(X4)":[261],"0.2969":[265],"dB":[266,271],"(on":[267],"average)":[268],"0.3320":[270],"SOTA":[273],"general":[274],"face":[276],"models,":[278],"respectively.":[279],"coding":[281],"framework":[282],"used":[283],"paper":[286],"at:":[289],"https://github.com/um-dsrg/Super-Resolution-Meta-Attention-Networks.":[290]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2021-10-11T00:00:00"}