{"id":"https://openalex.org/W4415708362","doi":"https://doi.org/10.1109/icme59968.2025.11210223","title":"UniVG: Towards UNIfied-modal Video Generation","display_name":"UniVG: Towards UNIfied-modal Video Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708362","doi":"https://doi.org/10.1109/icme59968.2025.11210223"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5020928190","display_name":"Ludan Ruan","orcid":"https://orcid.org/0009-0009-1039-4940"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ludan Ruan","raw_affiliation_strings":["Baidu Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777330","display_name":"Lei Tian","orcid":"https://orcid.org/0000-0001-5449-3232"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Tian","raw_affiliation_strings":["Baidu Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008896305","display_name":"Chuanwei Huang","orcid":"https://orcid.org/0000-0003-3475-9325"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanwei Huang","raw_affiliation_strings":["Baidu Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878977","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0003-2679-8412"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Baidu Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112673776","display_name":"Xinyan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Xiao","raw_affiliation_strings":["Baidu Inc.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc.,Beijing,China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9505000114440918,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9505000114440918,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.00860000029206276,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007000000216066837,"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/inference","display_name":"Inference","score":0.4993000030517578},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4903999865055084},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4277999997138977},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4268999993801117},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.35749998688697815},{"id":"https://openalex.org/keywords/video-content-analysis","display_name":"Video content analysis","score":0.33640000224113464},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3147999942302704},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.31130000948905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653999924659729},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4903999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650999903678894},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.33640000224113464},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2721000015735626},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W3170837227","https://openalex.org/W4312933868","https://openalex.org/W4319300158","https://openalex.org/W4386071957","https://openalex.org/W4390872681","https://openalex.org/W4390873030","https://openalex.org/W4402727798","https://openalex.org/W4403716358","https://openalex.org/W4403906510","https://openalex.org/W4407881938"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"based":[1,96],"video":[2,24,65,88,115,136],"generation":[3,25,66,89],"has":[4],"received":[5],"significant":[6],"attention":[7],"in":[8,36,79,192],"both":[9],"the":[10,74,80,98,140,147,150,154,176,185],"academic":[11],"and":[12,93,132,156,180,190],"industrial":[13],"communities.":[14],"Despite":[15],"recent":[16],"exploration":[17],"of":[18,45,62,76,125,130,149],"diverse":[19],"conditional":[20,162],"inputs":[21],"for":[22,110],"better":[23],"control,":[26],"existing":[27],"methods,":[28],"primarily":[29],"targeting":[30],"individual":[31],"tasks,":[32],"often":[33],"fall":[34],"short":[35],"real-world":[37],"scenarios":[38],"where":[39],"users":[40],"may":[41],"use":[42],"any":[43],"form":[44],"conditioning,":[46],"either":[47],"individually":[48],"or":[49],"combined.":[50],"To":[51],"address":[52],"this,":[53],"we":[54,117,138],"propose":[55,139],"a":[56,119],"Unified-modal":[57],"Video":[58],"Generation":[59],"system":[60],"capable":[61,124],"handling":[63,126],"multiple":[64],"tasks":[67,90],"across":[68],"different":[69,107],"modalities.":[70],"Our":[71,165],"approach":[72],"introduces":[73],"concept":[75],"generative":[77],"freedom":[78],"diffusion":[81,108,151],"process,":[82],"which":[83],"allows":[84],"us":[85],"to":[86,145],"reclassify":[87],"into":[91],"high-freedom":[92,114],"low-freedom":[94,135],"categories":[95],"on":[97,172,182],"solution":[99],"space":[100],"given":[101],"certain":[102],"conditions.":[103],"We":[104],"then":[105],"design":[106],"paradigms":[109],"each":[111],"category.":[112],"For":[113,134,195],"generation,":[116,137],"present":[118],"base":[120],"model":[121],"that":[122],"is":[123,181],"varied":[127],"semantic":[128],"combinations":[129],"text":[131],"image.":[133],"Biased":[141],"Gaussian":[142],"Noise":[143],"(BGN)":[144],"tackle":[146],"discrepancy":[148],"process":[152],"between":[153],"training":[155],"inference":[157],"stage":[158],"when":[159],"using":[160],"strong":[161],"guidance":[163],"strategy.":[164],"proposed":[166],"UniVG":[167],"achieves":[168],"superior":[169],"objective":[170],"results":[171],"public":[173],"datasets,":[174],"surpassing":[175],"current":[177,186],"open-source":[178],"methods":[179],"par":[183],"with":[184],"close-source":[187],"method":[188],"Gen2":[189],"Pika":[191],"human":[193],"evaluations.":[194],"more":[196],"samples,":[197],"visit":[198],"our":[199],"homepage.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}