{"id":"https://openalex.org/W4408345917","doi":"https://doi.org/10.1109/icassp49660.2025.10888491","title":"M3-CVC: Controllable Video Compression with Multimodal Generative Models","display_name":"M3-CVC: Controllable Video Compression with Multimodal Generative Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345917","doi":"https://doi.org/10.1109/icassp49660.2025.10888491"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5077950332","display_name":"Rui Wan","orcid":"https://orcid.org/0000-0002-8097-5590"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wan","raw_affiliation_strings":["Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020731826","display_name":"Qi Zheng","orcid":"https://orcid.org/0000-0002-8617-5025"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zheng","raw_affiliation_strings":["Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085004179","display_name":"Yibo Fan","orcid":"https://orcid.org/0000-0003-2523-8261"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Fan","raw_affiliation_strings":["Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.996999979019165,"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":0.996999979019165,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9351000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7038534879684448},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6202885508537292},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6142559051513672},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5895467400550842},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4122962951660156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3693286180496216},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.21906474232673645},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0722942054271698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038534879684448},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6202885508537292},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6142559051513672},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5895467400550842},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4122962951660156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693286180496216},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.21906474232673645},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0722942054271698},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6600000262260437}],"awards":[],"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":27,"referenced_works":["https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2425121537","https://openalex.org/W2511458122","https://openalex.org/W2752796333","https://openalex.org/W2962684798","https://openalex.org/W3031546776","https://openalex.org/W3109908659","https://openalex.org/W3160069937","https://openalex.org/W3202918664","https://openalex.org/W3216456501","https://openalex.org/W4293795298","https://openalex.org/W4312806968","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4386065808","https://openalex.org/W4398163936","https://openalex.org/W4402727507","https://openalex.org/W4402727736","https://openalex.org/W4402772372","https://openalex.org/W4402916321","https://openalex.org/W4404356490","https://openalex.org/W4404784276","https://openalex.org/W6843772381","https://openalex.org/W6874427462","https://openalex.org/W6874943832","https://openalex.org/W6876712728"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Traditional":[0],"and":[1,10,49,68,132],"neural":[2],"video":[3,25,52,73],"codecs":[4],"commonly":[5],"encounter":[6],"limitations":[7],"in":[8,92,124,129],"controllability":[9],"generality":[11],"under":[12],"ultra-low-bitrate":[13],"coding":[14],"scenarios.":[15],"To":[16],"overcome":[17],"these":[18],"challenges,":[19],"we":[20],"propose":[21],"M3-CVC,":[22],"a":[23,35,54,82],"controllable":[24],"compression":[26,87],"framework":[27,33],"incorporating":[28],"multimodal":[29,57],"generative":[30],"models.":[31],"The":[32],"utilizes":[34],"semantic-motion":[36],"composite":[37],"strategy":[38],"for":[39,71],"keyframe":[40,48,86],"selection":[41],"to":[42,106],"retain":[43],"critical":[44],"information.":[45],"For":[46],"each":[47],"its":[50],"corresponding":[51],"clip,":[53],"dialogue-based":[55],"large":[56],"model":[58],"(LMM)":[59],"approach":[60],"extracts":[61],"hierarchical":[62],"spatiotemporal":[63],"details,":[64],"enabling":[65],"both":[66],"inter-frame":[67],"intra-frame":[69],"representations":[70],"improved":[72],"fidelity":[74,91],"while":[75],"enhancing":[76],"encoding":[77],"interpretability.":[78],"M3-CVC":[79,117],"further":[80],"employs":[81],"conditional":[83],"diffusion-based,":[84],"text-guided":[85],"method,":[88],"achieving":[89],"high":[90],"frame":[93],"reconstruction.":[94],"During":[95],"decoding,":[96],"textual":[97],"descriptions":[98],"derived":[99],"from":[100],"LMMs":[101],"guide":[102],"the":[103,108,120],"diffusion":[104],"process":[105],"restore":[107],"original":[109],"video\u2019s":[110],"content":[111],"accurately.":[112],"Experimental":[113],"results":[114],"demonstrate":[115],"that":[116],"significantly":[118],"outperforms":[119],"state-of-the-art":[121],"VVC":[122],"standard":[123],"ultra-low":[125],"bitrate":[126],"scenarios,":[127],"particularly":[128],"preserving":[130],"semantic":[131],"perceptual":[133],"fidelity.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}