{"id":"https://openalex.org/W4410342953","doi":"https://doi.org/10.1109/icnc64010.2025.10993780","title":"Rethinking Video Generation: Overcoming the Limits of Pretrained Models","display_name":"Rethinking Video Generation: Overcoming the Limits of Pretrained Models","publication_year":2025,"publication_date":"2025-02-17","ids":{"openalex":"https://openalex.org/W4410342953","doi":"https://doi.org/10.1109/icnc64010.2025.10993780"},"language":"en","primary_location":{"id":"doi:10.1109/icnc64010.2025.10993780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc64010.2025.10993780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Computing, Networking and Communications (ICNC)","raw_type":"proceedings-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/A5103095740","display_name":"U\u011fur Demir","orcid":"https://orcid.org/0000-0002-1774-0369"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ugur Demir","raw_affiliation_strings":["Northwestern University,Evanston,USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114685784","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0009-0002-4938-3279"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlotte Lynn Chen","raw_affiliation_strings":["University of Washington,Seattle,USA"],"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle,USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029517941","display_name":"Anthony Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anthony Zhao","raw_affiliation_strings":["University of Toronto,Toronto,Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030839201","display_name":"Nicholas X. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129168","display_name":"BASIS International (United States)","ror":"https://ror.org/03q4sef08","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129168"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas X. Wang","raw_affiliation_strings":["BASIS Independent Silicon Valley,San Jose,USA"],"affiliations":[{"raw_affiliation_string":"BASIS Independent Silicon Valley,San Jose,USA","institution_ids":["https://openalex.org/I4210129168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640076","display_name":"Michelle Wang","orcid":"https://orcid.org/0000-0002-0761-6954"},"institutions":[{"id":"https://openalex.org/I4210151590","display_name":"Robert Louis Stevenson School","ror":"https://ror.org/03wbjgx32","country_code":"US","type":"education","lineage":["https://openalex.org/I4210151590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Wang","raw_affiliation_strings":["Robert Louis Stevenson,USA"],"affiliations":[{"raw_affiliation_string":"Robert Louis Stevenson,USA","institution_ids":["https://openalex.org/I4210151590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112966423","display_name":"Derek Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129168","display_name":"BASIS International (United States)","ror":"https://ror.org/03q4sef08","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129168"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Li","raw_affiliation_strings":["BASIS Independent Silicon Valley,San Jose,USA"],"affiliations":[{"raw_affiliation_string":"BASIS Independent Silicon Valley,San Jose,USA","institution_ids":["https://openalex.org/I4210129168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048650003","display_name":"Aggelos K. Katsaggelos","orcid":"https://orcid.org/0000-0003-4554-0070"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aggelos K. Katsaggelos","raw_affiliation_strings":["Northwestern University,Evanston,USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103095740"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10835838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.6855999827384949,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.6855999827384949,"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/T10758","display_name":"Cinema and Media Studies","score":0.6186000108718872,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6118000149726868,"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":0.660086989402771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3675801753997803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34755849838256836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660086989402771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675801753997803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34755849838256836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnc64010.2025.10993780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc64010.2025.10993780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Computing, Networking and Communications (ICNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W4312445951","https://openalex.org/W4312933868","https://openalex.org/W4409346646","https://openalex.org/W6640963894","https://openalex.org/W6854463369","https://openalex.org/W6858758126","https://openalex.org/W6858865347","https://openalex.org/W6863149945"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"generation":[1,32,88,134,231],"has":[2],"emerged":[3],"as":[4],"a":[5,126,146,184],"promising":[6],"research":[7],"direction":[8],"following":[9],"the":[10,86,96,121,152,157,170],"success":[11],"of":[12,98,203],"Stable":[13,41],"Diffusion-based":[14],"models":[15,21,43,62,113,192],"in":[16,72],"photo-realistic":[17],"image":[18],"synthesis.":[19],"These":[20,61],"excel":[22],"at":[23,78,135],"generating":[24,76],"fixed-size":[25],"content":[26,133],"but":[27],"struggle":[28],"with":[29,190],"arbitrary-size":[30,102,221],"video":[31,87,103,127,204,230],"due":[33],"to":[34,47,55,94],"architectural":[35],"constraints":[36],"and":[37,58,90,163,200],"training":[38,59,179],"biases.":[39],"Pre-trained":[40],"Diffusion":[42],"have":[44],"democratized":[45],"access":[46],"powerful":[48],"generative":[49],"capabilities.":[50],"However,":[51],"they":[52],"limit":[53],"researchers":[54,188],"specific":[56],"architectures":[57,66],"configurations.":[60],"primarily":[63],"use":[64],"U-Net":[65],"trained":[67],"on":[68],"square-format":[69],"content,":[70],"resulting":[71],"quality":[73,218],"degradation":[74],"when":[75],"videos":[77],"non-standard":[79],"dimensions.":[80],"In":[81],"this":[82],"work,":[83],"we":[84],"revisit":[85],"topics":[89],"propose":[91],"new":[92],"solutions":[93],"overcome":[95],"limits":[97],"pre-trained":[99,191],"models,":[100],"for":[101,160,172,178,187,225],"generation.":[104,205],"A":[105],"novel":[106],"approach":[107,168,215],"was":[108],"proposed":[109],"that":[110,150,212],"uses":[111],"existing":[112],"without":[114,155],"expensive":[115],"retraining.":[116],"Our":[117],"method":[118],"builds":[119],"upon":[120],"publicly":[122],"available":[123],"AnimateDiff":[124],"model,":[125],"outpainting":[128],"technique.":[129],"This":[130,206],"combination":[131],"enables":[132],"any":[136],"desired":[137],"dimension":[138],"while":[139],"maintaining":[140],"visual":[141],"quality.":[142],"We":[143],"also":[144],"employ":[145],"frame":[147],"interpolation":[148],"technique":[149],"increases":[151],"temporal":[153,165,201],"resolution":[154],"altering":[156],"context,":[158],"allowing":[159],"smooth":[161],"motion":[162],"enhanced":[164],"coherence.":[166],"The":[167],"eliminates":[169],"need":[171,194],"large-scale":[173],"computing":[174],"clusters":[175],"typically":[176],"required":[177],"foundation":[180],"models.":[181,232],"It":[182],"provides":[183],"practical":[185],"solution":[186],"working":[189],"who":[193],"flexible":[195],"control":[196],"over":[197],"both":[198],"spatial":[199],"dimensions":[202],"work":[207],"presents":[208],"preliminary":[209],"results":[210],"showing":[211],"our":[213],"modular":[214],"achieves":[216],"better":[217],"than":[219],"direct":[220],"generation,":[222],"demonstrating":[223],"promise":[224],"future":[226],"integration":[227],"into":[228],"end-to-end":[229]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}