{"id":"https://openalex.org/W4415524370","doi":"https://doi.org/10.1109/mlsp62443.2025.11204234","title":"Foundation Model-Aided Video Semantic Communication: Framework Design and Prototype Validation","display_name":"Foundation Model-Aided Video Semantic Communication: Framework Design and Prototype Validation","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524370","doi":"https://doi.org/10.1109/mlsp62443.2025.11204234"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019261779","display_name":"Jiarun Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarun Ding","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086728390","display_name":"Peiwen Jiang","orcid":"https://orcid.org/0000-0003-1902-2827"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiwen Jiang","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024436944","display_name":"Chao-Kai Wen","orcid":"https://orcid.org/0000-0001-5952-232X"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Kai Wen","raw_affiliation_strings":["Institute of Communications Engineering, National Sun Yat-sen University,Kaohsiung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communications Engineering, National Sun Yat-sen University,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375264","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0001-9660-9053"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013079905","display_name":"Shi Jin","orcid":"https://orcid.org/0000-0003-0271-6021"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Jin","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9560999870300293,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9319999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/wireless","display_name":"Wireless","score":0.45840001106262207},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4494999945163727},{"id":"https://openalex.org/keywords/multiple-description-coding","display_name":"Multiple description coding","score":0.4375},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.37059998512268066},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800599992275238},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C135554599","wikidata":"https://www.wikidata.org/wiki/Q3682206","display_name":"Multiple description coding","level":3,"score":0.4375},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2986797740","wikidata":"https://www.wikidata.org/wiki/Q16873051","display_name":"Wireless transmission","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1003364742","display_name":null,"funder_award_id":"62261160576","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354369925","display_name":null,"funder_award_id":"BE2023022-1,BE2023022","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":9,"referenced_works":["https://openalex.org/W2094655360","https://openalex.org/W2128765501","https://openalex.org/W2548527721","https://openalex.org/W2962785568","https://openalex.org/W3216777582","https://openalex.org/W4297697565","https://openalex.org/W4312051474","https://openalex.org/W4388191556","https://openalex.org/W4390873795"],"related_works":[],"abstract_inverted_index":{"The":[0,67],"growing":[1],"demand":[2],"for":[3,61,87,115],"video":[4,57,62,72,139],"services":[5],"places":[6],"substantial":[7],"pressure":[8],"on":[9,17,126],"wireless":[10],"communication":[11,59],"systems.":[12],"Semantic":[13],"communication,":[14],"which":[15],"focuses":[16],"the":[18,109,124],"transmission":[19,63,73,97,104],"of":[20,98,100,105],"meaning":[21],"rather":[22],"than":[23],"raw":[24],"data,":[25],"presents":[26],"a":[27,54,112,127],"promising":[28],"solution.":[29],"However,":[30],"existing":[31],"approaches":[32],"are":[33],"typically":[34],"confined":[35],"to":[36,119,145],"single":[37],"scenarios":[38,93],"and":[39,79,102,132,141],"have":[40],"not":[41],"been":[42],"validated":[43],"over":[44,89],"practical":[45],"air":[46],"interfaces.":[47],"To":[48],"overcome":[49],"these":[50],"limitations,":[51],"we":[52,122],"propose":[53],"foundation":[55,113],"modelaided":[56],"semantic":[58,116],"framework":[60,69,110,125],"across":[64],"diverse":[65],"scenarios.":[66],"proposed":[68],"facilitates":[70],"end-to-end":[71],"using":[74],"joint":[75],"source-channel":[76],"coding":[77],"(JSCC)":[78],"employs":[80],"multiple-input":[81],"multiple-output":[82],"orthogonal":[83],"frequency-division":[84],"multiplexing":[85],"(MIMO-OFDM)":[86],"delivery":[88],"3GPP-standard":[90],"channels.":[91],"In":[92],"that":[94],"require":[95],"full":[96],"regions":[99],"interest":[101],"selective":[103],"less":[106],"critical":[107],"areas,":[108],"utilizes":[111],"model":[114],"segmentation":[117],"prior":[118],"JSCC.":[120],"Furthermore,":[121],"implement":[123],"physical":[128],"testbed.":[129],"Simulation":[130],"results":[131],"over-the-air":[133],"experiments":[134],"demonstrate":[135],"significant":[136],"improvements":[137],"in":[138],"quality":[140],"bandwidth":[142],"efficiency":[143],"compared":[144],"conventional":[146],"methods.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}
