{"id":"https://openalex.org/W4412939921","doi":"https://doi.org/10.1109/tvt.2025.3595688","title":"Generative Video Semantic Communication via Multimodal Semantic Fusion With Large Model","display_name":"Generative Video Semantic Communication via Multimodal Semantic Fusion With Large Model","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4412939921","doi":"https://doi.org/10.1109/tvt.2025.3595688"},"language":"en","primary_location":{"id":"doi:10.1109/tvt.2025.3595688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3595688","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","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":null,"display_name":"Hang Yin","orcid":"https://orcid.org/0009-0006-2065-7239"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yin","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2065-7239","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Qiao","orcid":"https://orcid.org/0000-0003-0586-189X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Qiao","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0586-189X","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101106354","display_name":"Yu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ma","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8303-6486","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuo Sun","orcid":"https://orcid.org/0009-0006-8221-6324"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Sun","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8221-6324","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kan Li","orcid":"https://orcid.org/0000-0003-3528-4739"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kan Li","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3528-4739","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Gao","orcid":"https://orcid.org/0000-0002-2709-0216"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Gao","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2709-0216","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091266202","display_name":"Dusit Niyato","orcid":"https://orcid.org/0000-0002-7442-7416"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dusit Niyato","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7442-7416","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3693,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93195246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"75","issue":"1","first_page":"1701","last_page":"1706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9539999961853027,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9539999961853027,"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":0.6845847368240356},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48354196548461914},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47745493054389954},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.45699188113212585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4312141239643097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.428214967250824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3755371570587158},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3356287479400635},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32824191451072693},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.20670226216316223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845847368240356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48354196548461914},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47745493054389954},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.45699188113212585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4312141239643097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.428214967250824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3755371570587158},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3356287479400635},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32824191451072693},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.20670226216316223}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2025.3595688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3595688","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5261778551","display_name":null,"funder_award_id":"YQ24167","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6139073070","display_name":null,"funder_award_id":"62471036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6812773373","display_name":null,"funder_award_id":"U223320067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7894506616","display_name":null,"funder_award_id":"ZR2022YQ62","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G8699371724","display_name":null,"funder_award_id":"L242011","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2168171912","https://openalex.org/W2946889564","https://openalex.org/W2952311350","https://openalex.org/W2964268978","https://openalex.org/W3204588463","https://openalex.org/W3216777582","https://openalex.org/W4214774769","https://openalex.org/W4226042246","https://openalex.org/W4308619895","https://openalex.org/W4312557000","https://openalex.org/W4313350178","https://openalex.org/W4381785967","https://openalex.org/W4386065512","https://openalex.org/W4396688723","https://openalex.org/W4400679943","https://openalex.org/W4402509550","https://openalex.org/W4404037241","https://openalex.org/W4404784276","https://openalex.org/W4404965692","https://openalex.org/W4405844682","https://openalex.org/W4406355801"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advancements":[2],"in":[3,40],"traditional":[4],"syntactic":[5],"communications":[6],"based":[7],"on":[8],"Shannon's":[9],"theory,":[10],"these":[11],"methods":[12],"struggle":[13],"to":[14,65,107,136],"meet":[15],"the":[16,29,72,87,98,100,109,112,117,148],"requirements":[17],"of":[18,31,111],"6":[19],"G":[20],"immersive":[21],"communications,":[22],"especially":[23],"under":[24,143,179],"challenging":[25],"transmission":[26],"conditions.":[27,182],"With":[28],"development":[30],"generative":[32,54],"artificial":[33],"intelligence":[34],"(GenAI),":[35],"progress":[36],"has":[37],"been":[38],"made":[39],"reconstructing":[41,116],"videos":[42,138],"using":[43],"high-level":[44],"semantic":[45,56,63,134],"information.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"a":[52],"scalable":[53],"video":[55,68],"communication":[57],"framework":[58],"that":[59],"extracts":[60],"and":[61,75,93],"transmits":[62],"information":[64,135],"achieve":[66],"high-quality":[67],"reconstruction.":[69],"Specifically,":[70],"at":[71,123,161],"transmitter,":[73],"description":[74],"other":[76],"condition":[77],"signals":[78],"(e.g.,":[79],"first":[80],"frame,":[81],"sketches,":[82],"etc.)":[83],"are":[84,105],"extracted":[85],"from":[86],"source":[88],"video,":[89],"functioning":[90],"as":[91],"text":[92],"structural":[94],"semantics,":[95],"respectively.":[96],"At":[97],"receiver,":[99],"diffusion-based":[101],"GenAI":[102],"large":[103],"models":[104],"utilized":[106],"fuse":[108],"semantics":[110],"multiple":[113],"modalities":[114],"for":[115,165],"video.":[118],"Simulation":[119],"results":[120],"demonstrate":[121],"that,":[122],"an":[124],"ultra-low":[125],"channel":[126],"bandwidth":[127],"ratio":[128],"(CBR),":[129],"our":[130],"scheme":[131,154],"effectively":[132],"captures":[133],"reconstruct":[137],"aligned":[139],"with":[140],"human":[141],"perception":[142],"different":[144],"signal-to-noise":[145],"ratios.":[146],"Notably,":[147],"proposed":[149],"<bold":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151,168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">First":[152],"Frame+Desc.</b>":[153],"consistently":[155],"achieves":[156],"CLIP":[157],"score":[158],"exceeding":[159],"0.92":[160],"CBR":[162],"=":[163],"0.0031":[164],"SNR":[166,181],"<inline-formula":[167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[169],"notation=\"LaTeX\">$&gt;$</tex-math></inline-formula>":[170],"0":[171],"dB.":[172],"This":[173],"demonstrates":[174],"its":[175],"robust":[176],"performance":[177],"even":[178],"low":[180]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}