{"id":"https://openalex.org/W4213452141","doi":"https://doi.org/10.1109/tmm.2022.3152941","title":"Audio Matters in Video Super-Resolution by Implicit Semantic Guidance","display_name":"Audio Matters in Video Super-Resolution by Implicit Semantic Guidance","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213452141","doi":"https://doi.org/10.1109/tmm.2022.3152941"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3152941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3152941","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101845614","display_name":"Yanxiang Chen","orcid":"https://orcid.org/0000-0001-7974-6494"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanxiang Chen","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030474289","display_name":"Pengcheng Zhao","orcid":"https://orcid.org/0000-0003-3774-5113"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhao","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073550769","display_name":"Meibin Qi","orcid":"https://orcid.org/0000-0001-9074-211X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meibin Qi","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021991838","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0002-4032-8049"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395308","display_name":"Wei Jia","orcid":"https://orcid.org/0000-0001-5628-6237"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jia","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050071143","display_name":"Ronggang Wang","orcid":"https://orcid.org/0000-0003-0873-0465"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronggang Wang","raw_affiliation_strings":["Peng Cheng National Laboratory, Shenzhen, China","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China, 518055"],"affiliations":[{"raw_affiliation_string":"Peng Cheng National Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China, 518055","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101845614"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52245646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"24","issue":null,"first_page":"4128","last_page":"4142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9957000017166138,"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":0.9767000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8713392019271851},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6710460782051086},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6588373184204102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.585326611995697},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.517885684967041},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4877477288246155},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48454228043556213},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4600098133087158},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3234604597091675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3209528923034668},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2103072702884674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8713392019271851},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6710460782051086},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6588373184204102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.585326611995697},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.517885684967041},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4877477288246155},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48454228043556213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4600098133087158},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3234604597091675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3209528923034668},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2103072702884674},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3152941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3152941","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5721666953","display_name":null,"funder_award_id":"61972129","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5943813557","display_name":null,"funder_award_id":"62076086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6064834736","display_name":null,"funder_award_id":"61771180","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7947159105","display_name":null,"funder_award_id":"61972127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W54257720","https://openalex.org/W208009482","https://openalex.org/W2015701667","https://openalex.org/W2032849384","https://openalex.org/W2166563626","https://openalex.org/W2242218935","https://openalex.org/W2476548250","https://openalex.org/W2526050071","https://openalex.org/W2610638008","https://openalex.org/W2619947201","https://openalex.org/W2769654144","https://openalex.org/W2798664922","https://openalex.org/W2808631503","https://openalex.org/W2810432089","https://openalex.org/W2866634454","https://openalex.org/W2901702433","https://openalex.org/W2904835235","https://openalex.org/W2914107945","https://openalex.org/W2923834406","https://openalex.org/W2938555542","https://openalex.org/W2944294033","https://openalex.org/W2962699416","https://openalex.org/W2962927175","https://openalex.org/W2963150162","https://openalex.org/W2963372104","https://openalex.org/W2963470893","https://openalex.org/W2963814095","https://openalex.org/W2964101377","https://openalex.org/W2965669158","https://openalex.org/W2970835139","https://openalex.org/W2970903655","https://openalex.org/W2971680695","https://openalex.org/W2979157532","https://openalex.org/W2982619606","https://openalex.org/W2988539781","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3010433305","https://openalex.org/W3010434693","https://openalex.org/W3013529009","https://openalex.org/W3015785290","https://openalex.org/W3015791137","https://openalex.org/W3034257218","https://openalex.org/W3034475761","https://openalex.org/W3034658206","https://openalex.org/W3035753399","https://openalex.org/W3038124041","https://openalex.org/W3044723170","https://openalex.org/W3087305966","https://openalex.org/W3095671795","https://openalex.org/W3102015846","https://openalex.org/W3108367559","https://openalex.org/W3118120400","https://openalex.org/W3136101383","https://openalex.org/W3154807520","https://openalex.org/W3174816433","https://openalex.org/W3175335326","https://openalex.org/W3176148916","https://openalex.org/W4254174875","https://openalex.org/W4287705107","https://openalex.org/W6600983433","https://openalex.org/W6767936260","https://openalex.org/W6774285787","https://openalex.org/W6774748123","https://openalex.org/W6783915111","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2005437358","https://openalex.org/W1669643531","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673","https://openalex.org/W2110230079","https://openalex.org/W1982826852","https://openalex.org/W2613186388","https://openalex.org/W1967061043"],"abstract_inverted_index":{"Video":[0],"super-resolution":[1,70],"(VSR)":[2],"aims":[3],"to":[4,10,66,80,115,170],"use":[5],"multiple":[6],"consecutive":[7],"low-resolution":[8],"frames":[9],"recover":[11],"the":[12,58,89,93,121,135,148,156,171,196,202,206,219,224],"corresponding":[13],"high-resolution":[14],"frames.":[15],"However,":[16],"existing":[17],"VSR":[18,117,197],"methods":[19],"only":[20],"consider":[21],"videos":[22],"as":[23,88,129],"image":[24],"sequences,":[25],"ignoring":[26],"another":[27],"essential":[28],"timing":[29],"informationaudio,":[30],"while":[31],"in":[32,54,69,92,101],"fact,":[33],"there":[34],"is":[35,78],"a":[36,74,106,162],"semantic":[37,61,82,131,149,184,215],"link":[38],"between":[39],"audio":[40,49,87,123,182,192],"and":[41,43,108,159,221,229],"vision,":[42],"extensive":[44],"studies":[45],"have":[46],"shown":[47],"that":[48,191],"can":[50,96,126,193,210],"provide":[51],"supervisory":[52],"information":[53,90],"visual":[55,174],"networks.":[56],"Meanwhile,":[57],"addition":[59],"of":[60,137,152,155,223,226],"priors":[62],"has":[63],"been":[64],"proven":[65],"be":[67,97,127],"effective":[68,181],"(SR)":[71],"tasks,":[72],"but":[73],"pretrained":[75],"segmentation":[76,83,139],"network":[77],"required":[79],"obtain":[81],"maps.":[84],"By":[85],"contrast,":[86],"contained":[91],"video":[94],"itself":[95],"directly":[98],"used.":[99],"Therefore,":[100],"this":[102],"study,":[103],"we":[104,142],"propose":[105],"novel":[107],"pluggable":[109],"multiscale":[110,164],"audiovisual":[111,145,214],"fusion":[112,165],"(MS-AVF)":[113],"module":[114],"enhance":[116],"performance":[118],"by":[119,177,200],"exploiting":[120],"relevant":[122],"information,":[124],"which":[125],"regarded":[128],"implicit":[130,183],"guidance":[132,185],"compared":[133],"with":[134],"kind":[136],"explicit":[138],"priors.":[140],"Specifically,":[141],"first":[143],"fuse":[144],"features":[146,175],"on":[147],"feature":[150],"maps":[151],"different":[153],"granularities":[154],"target":[157],"frames,":[158],"then":[160],"through":[161],"top-down":[163],"approach,":[166],"feedback":[167],"high-level":[168],"semantics":[169],"underlying":[172],"global":[173],"layer":[176],"layer,":[178],"thereby":[179],"providing":[180],"for":[186],"VSR.":[187],"Experimental":[188],"results":[189],"show":[190],"further":[194],"improve":[195],"effect.":[198],"Moreover,":[199],"visualizing":[201],"learned":[203],"attention":[204],"mask,":[205],"proposed":[207],"end-to-end":[208],"model":[209],"automatically":[211],"learn":[212],"potential":[213],"links,":[216],"especially":[217],"improving":[218],"accuracy":[220],"effectiveness":[222],"SR":[225],"sound":[227],"sources":[228],"their":[230],"surrounding":[231],"regions.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}