{"id":"https://openalex.org/W4317555198","doi":"https://doi.org/10.1109/pcs56426.2022.10017998","title":"Multi-Stage Spatial and Frequency Feature Fusion using Transformer in CNN-Based In-Loop Filter for VVC","display_name":"Multi-Stage Spatial and Frequency Feature Fusion using Transformer in CNN-Based In-Loop Filter for VVC","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4317555198","doi":"https://doi.org/10.1109/pcs56426.2022.10017998"},"language":"en","primary_location":{"id":"doi:10.1109/pcs56426.2022.10017998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs56426.2022.10017998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Picture Coding Symposium (PCS)","raw_type":"proceedings-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/A5036691509","display_name":"Birendra Kathariya","orcid":"https://orcid.org/0000-0001-9297-8978"},"institutions":[{"id":"https://openalex.org/I75421653","display_name":"University of Missouri\u2013Kansas City","ror":"https://ror.org/01w0d5g70","country_code":"US","type":"education","lineage":["https://openalex.org/I75421653"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Birendra Kathariya","raw_affiliation_strings":["University of Missouri-Kansas City,Kansas City,USA","University of Missouri-Kansas City, Kansas City, USA"],"affiliations":[{"raw_affiliation_string":"University of Missouri-Kansas City,Kansas City,USA","institution_ids":["https://openalex.org/I75421653"]},{"raw_affiliation_string":"University of Missouri-Kansas City, Kansas City, USA","institution_ids":["https://openalex.org/I75421653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380625","display_name":"Zhu Li","orcid":"https://orcid.org/0000-0002-8246-177X"},"institutions":[{"id":"https://openalex.org/I75421653","display_name":"University of Missouri\u2013Kansas City","ror":"https://ror.org/01w0d5g70","country_code":"US","type":"education","lineage":["https://openalex.org/I75421653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu Li","raw_affiliation_strings":["University of Missouri-Kansas City,Kansas City,USA","University of Missouri-Kansas City, Kansas City, USA"],"affiliations":[{"raw_affiliation_string":"University of Missouri-Kansas City,Kansas City,USA","institution_ids":["https://openalex.org/I75421653"]},{"raw_affiliation_string":"University of Missouri-Kansas City, Kansas City, USA","institution_ids":["https://openalex.org/I75421653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602780","display_name":"Hongtao Wang","orcid":"https://orcid.org/0000-0002-1013-5713"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongtao Wang","raw_affiliation_strings":["Qualcomm Technologies, Inc.,San Diego,USA","Qualcomm Technologies, Inc., San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Technologies, Inc., San Diego, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059461658","display_name":"Mohammad Coban","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Coban","raw_affiliation_strings":["Qualcomm Technologies, Inc.,San Diego,USA","Qualcomm Technologies, Inc., San Diego, USA"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc.,San Diego,USA","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Technologies, Inc., San Diego, USA","institution_ids":["https://openalex.org/I4210087596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036691509"],"corresponding_institution_ids":["https://openalex.org/I75421653"],"apc_list":null,"apc_paid":null,"fwci":0.7046,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71138113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","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":0.9994000196456909,"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":0.7530530691146851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367012858390808},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5315803289413452},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.5053970813751221},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5019738674163818},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4428480267524719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4314529299736023},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.4314473271369934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12259611487388611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530530691146851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367012858390808},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5315803289413452},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5053970813751221},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5019738674163818},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4428480267524719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4314529299736023},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.4314473271369934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12259611487388611},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pcs56426.2022.10017998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs56426.2022.10017998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Picture Coding Symposium (PCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W2142683286","https://openalex.org/W2146395539","https://openalex.org/W2477177239","https://openalex.org/W2508457857","https://openalex.org/W2510648513","https://openalex.org/W2793408333","https://openalex.org/W2884585870","https://openalex.org/W2915130236","https://openalex.org/W2963372104","https://openalex.org/W2966431607","https://openalex.org/W2970872821","https://openalex.org/W3012998522","https://openalex.org/W3043029414","https://openalex.org/W3090654092","https://openalex.org/W3094502228","https://openalex.org/W3104772632","https://openalex.org/W3138516171","https://openalex.org/W3166014221","https://openalex.org/W3169596802","https://openalex.org/W3202918664","https://openalex.org/W3207918547","https://openalex.org/W4224294196","https://openalex.org/W4225672218"],"related_works":["https://openalex.org/W2094583657","https://openalex.org/W1594300462","https://openalex.org/W2158009109","https://openalex.org/W1606460848","https://openalex.org/W1706111048","https://openalex.org/W2115252864","https://openalex.org/W2129927873","https://openalex.org/W2112852877","https://openalex.org/W2772846670","https://openalex.org/W2034796835"],"abstract_inverted_index":{"Versatile":[0],"Video":[1,12,17],"Coding":[2,13,18],"(VVC)/H.266":[3],"is":[4],"a":[5,72,92,153],"video":[6,33],"coding":[7,24,34,173],"successor":[8],"to":[9,37,56,78,107,176],"High":[10],"Efficiency":[11],"(HEVC)/H.255":[14],"and":[15,23,110,116,136],"Advanced":[16],"(AVC)/H.264":[19],"with":[20],"significant":[21],"technical":[22],"improvement.":[25],"Nonetheless,":[26],"it":[27],"follows":[28],"the":[29,44,58,80,125,130,143,148,168,189],"conventional":[30],"block-based":[31],"hybrid":[32],"scheme":[35],"similar":[36],"its":[38,117],"predecessors.":[39],"The":[40,86],"consequence":[41],"is,":[42],"that":[43,158,167],"reconstructed":[45],"picture":[46],"contains":[47],"compression":[48],"artifacts.":[49],"VVC,":[50],"by":[51],"default,":[52],"has":[53],"in-loop":[54,82,89,156],"filters":[55,63],"correct":[57],"deformities":[59],"but":[60],"these":[61],"handcrafted":[62],"offer":[64],"suboptimal":[65],"performance.":[66],"In":[67],"this":[68],"work,":[69],"we":[70],"designed":[71],"novel":[73],"convolutional":[74],"neural":[75],"network":[76,127],"(CNN)":[77],"replace":[79],"inbuilt":[81],"filter":[83,90,157],"of":[84,99,142],"VVC.":[85],"proposed":[87,126,149,169],"CNN-based":[88],"utilizes":[91],"modified":[93],"Spectral-wise":[94,101],"Multi-Head":[95],"Self-Attention":[96],"(S-MSA)":[97],"layer":[98],"Multistage":[100],"Transformer":[102],"(MST++)":[103],"at":[104],"multiple":[105],"stages":[106],"fuse":[108],"spatial":[109],"frequency-decomposed":[111],"features":[112],"extracted":[113],"from":[114],"pixel":[115],"discrete-cosine-transform":[118],"(DCT)":[119],"applied":[120],"input":[121],"respectively.":[122],"We":[123],"named":[124],"MSTFNet":[128],"where":[129],"first":[131],"three":[132],"letters":[133],"represent":[134],"MST++":[135],"F":[137],"stands":[138],"for":[139,188],"fusion.":[140],"Because":[141],"multi-stage":[144],"feature":[145],"fusion":[146],"operation,":[147],"CNN":[150],"acts":[151],"as":[152],"powerful":[154],"learned":[155],"significantly":[159],"outperforms":[160],"previous":[161],"methods.":[162],"Our":[163],"experimental":[164],"results":[165],"show":[166],"method":[170],"can":[171],"achieve":[172],"improvements":[174],"up":[175],"10.31%":[177],"on":[178],"average":[179],"Bj\u00f8ntegaard":[180],"Delta":[181],"(BD)-Bitrate":[182],"savings":[183],"under":[184],"all-intra":[185],"(AI)":[186],"configurations":[187],"luma":[190],"(Y)":[191],"component.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}