{"id":"https://openalex.org/W7135152171","doi":"https://doi.org/10.1109/lsp.2026.3673193","title":"When Video Compression Meets Multimodal Large Language Models: A Unified Paradigm for Cross-Modality Video Compression","display_name":"When Video Compression Meets Multimodal Large Language Models: A Unified Paradigm for Cross-Modality Video Compression","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7135152171","doi":"https://doi.org/10.1109/lsp.2026.3673193"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2026.3673193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3673193","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":["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/A5100451860","display_name":"Pingping Zhang","orcid":"https://orcid.org/0000-0003-4188-1572"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pingping Zhang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4188-1572","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454985","display_name":"Jinlong Li","orcid":"https://orcid.org/0000-0002-8746-4566"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jinlong Li","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020579227","display_name":"Kecheng Chen","orcid":"https://orcid.org/0000-0001-6657-3221"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kecheng Chen","raw_affiliation_strings":["Department of Electrical Engineering, Center for Intelligent Multidimensional Data Analysis, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6657-3221","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Center for Intelligent Multidimensional Data Analysis, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128861262","display_name":"Meng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Department of Computing and Decision Sciences, Lingnan University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Decision Sciences, Lingnan University, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025594135","display_name":"Lei Xu","orcid":"https://orcid.org/0000-0002-8499-0448"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Xu","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-9286-2876","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065859286","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-9198-3951"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoliang Li","raw_affiliation_strings":["Department of Electrical Engineering, Center for Intelligent Multidimensional Data Analysis, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8723-8112","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Center for Intelligent Multidimensional Data Analysis, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128816176","display_name":"Nicu Sebe","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128837982","display_name":"Sam Kwong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Department of Computing and Decision Sciences, Lingnan University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Department of Computing and Decision Sciences, Lingnan University, Hong Kong, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24748948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1716","last_page":"1720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.8095999956130981,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.8095999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.03680000081658363,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03530000150203705,"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/video-compression-picture-types","display_name":"Video compression picture types","score":0.6906999945640564},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6017000079154968},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5773000121116638},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.527899980545044},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.42719998955726624},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/video-post-processing","display_name":"Video post-processing","score":0.4083999991416931},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.40549999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385000228881836},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.6906999945640564},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5784000158309937},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5773000121116638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5097000002861023},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.42719998955726624},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.4083999991416931},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.3418000042438507},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.33889999985694885},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.29030001163482666},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2754000127315521},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2026.3673193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3673193","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:iris.unitn.it:11572/486910","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/486910","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"video":[1,37,59,65,91,151],"compression":[2,30,38],"methods":[3],"perform":[4],"well":[5],"at":[6,16],"high":[7],"bitrates":[8],"but":[9],"struggle":[10],"to":[11,74,88,119,149],"preserve":[12],"fine-grained":[13],"semantic":[14,98,132],"information":[15],"low":[17],"bitrates.":[18],"Recently,":[19],"with":[20],"the":[21,121,143],"blossoming":[22],"of":[23,145],"Multimodal":[24],"Large":[25],"Language":[26],"Models":[27],"(MLLMs),":[28],"Cross-modal":[29],"techniques":[31],"offer":[32],"prospective":[33],"solutions":[34],"for":[35,97,103],"improving":[36],"under":[39],"low-bitrate":[40],"conditions.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,107],"propose":[46],"a":[47],"unified":[48],"Cross-Modality":[49],"Video":[50],"Compression":[51],"(CMVC)":[52],"framework":[53],"that":[54,128],"integrates":[55],"multimodal":[56,147],"representations":[57,78],"and":[58,68,100],"generative":[60],"models.":[61],"The":[62],"encoder":[63],"disentangles":[64],"into":[66],"spatial":[67],"temporal":[69],"components,":[70],"which":[71],"are":[72,86],"mapped":[73],"compact":[75],"cross":[76],"modal":[77],"using":[79,115],"MLLMs.":[80],"During":[81],"decoding,":[82],"different":[83],"encoding-decoding":[84],"modes":[85],"employed":[87],"acquire":[89],"various":[90],"reconstruction":[92],"qualities,":[93],"including":[94],"Text-Text-to-Video":[95],"(TT2V)":[96],"preservation":[99],"Image-Text-to-Video":[101],"(IT2V)":[102],"perceptual":[104,122,138],"consistency.":[105,139],"Additionally,":[106],"elaborate":[108],"on":[109],"an":[110],"efficient":[111],"frame":[112],"interpolation":[113],"model":[114],"Low-Rank":[116],"Adaptation":[117],"(LoRA)":[118],"improve":[120,150],"quality.":[123],"Experimental":[124],"results":[125],"demon":[126],"strate":[127],"TT2V":[129],"achieves":[130],"effective":[131],"reconstruction,":[133],"while":[134],"IT2V":[135],"ensures":[136],"competitive":[137],"These":[140],"findings":[141],"suggest":[142],"potential":[144],"leveraging":[146],"priors":[148],"compression,":[152],"offering":[153],"promising":[154],"future":[155],"research":[156],"directions.":[157]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2026-03-13T00:00:00"}