{"id":"https://openalex.org/W7125788834","doi":"https://doi.org/10.1145/3793552","title":"CP-Diffusion: Conditional Prompt-Based Diffusion Models for Video Generation","display_name":"CP-Diffusion: Conditional Prompt-Based Diffusion Models for Video Generation","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125788834","doi":"https://doi.org/10.1145/3793552"},"language":"en","primary_location":{"id":"doi:10.1145/3793552","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793552","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3793552","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124016527","display_name":"Muhammad Saeed","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Muhammad Saeed","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0003-4462-9863","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124047339","display_name":"Mustaqeem Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I201726411","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862","country_code":"AE","type":"education","lineage":["https://openalex.org/I201726411"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mustaqeem Khan","raw_affiliation_strings":["College of Information Technology, United Arab Emirates University, Al Ain, UAE"],"raw_orcid":"https://orcid.org/0000-0002-8020-3590","affiliations":[{"raw_affiliation_string":"College of Information Technology, United Arab Emirates University, Al Ain, UAE","institution_ids":["https://openalex.org/I201726411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123897842","display_name":"Muhammad Saad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Saad","raw_affiliation_strings":["Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0009-0005-9846-8991","affiliations":[{"raw_affiliation_string":"Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123930952","display_name":"Nasir Rahim","orcid":null},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nasir Rahim","raw_affiliation_strings":["School of Computing, Gachon University, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6274-2593","affiliations":[{"raw_affiliation_string":"School of Computing, Gachon University, Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I12832649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036560577","display_name":"Wail Gueaieb","orcid":"https://orcid.org/0000-0001-6490-4648"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wail Gueaieb","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6490-4648","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123884285","display_name":"Abdulmotaleb El Saddik","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdulmotaleb El Saddik","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7690-8547","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6237,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9793996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"16"},"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":0.4546000063419342,"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":0.4546000063419342,"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/T12290","display_name":"Human Motion and Animation","score":0.36579999327659607,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.04690000042319298,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/personalization","display_name":"Personalization","score":0.6546000242233276},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.5442000031471252},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.5252000093460083},{"id":"https://openalex.org/keywords/quarter-pixel-motion","display_name":"Quarter-pixel motion","score":0.40380001068115234},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543999791145325},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5494999885559082},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249999761581421},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.34439998865127563},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C72560505","wikidata":"https://www.wikidata.org/wiki/Q204510","display_name":"Motion interpolation","level":5,"score":0.27790001034736633},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3793552","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793552","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3793552","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793552","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42508068680763245,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3204588463","https://openalex.org/W4226211505","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386075890","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4402090583","https://openalex.org/W4402727368","https://openalex.org/W4402753775","https://openalex.org/W4403792277","https://openalex.org/W4403792309"],"related_works":[],"abstract_inverted_index":{"Motion":[0,45],"customization":[1,65,149],"plays":[2],"a":[3,51,84,106,123],"pivotal":[4],"role":[5],"in":[6,35,66,144,167],"video":[7,24,145],"generation":[8,25,146],"by":[9],"preserving":[10],"the":[11,43,99,132,142,168],"original":[12],"appearance":[13],"and":[14,30,37,77,95,118,134],"context":[15],"while":[16,75,90,113,150],"adhering":[17],"to":[18,33,130,162],"specific":[19],"motion":[20,39,64,79,88,125,148],"patterns.":[21,40],"In":[22],"contrast,":[23],"techniques":[26],"often":[27],"lack":[28],"coherence":[29],"realism":[31],"due":[32],"difficulties":[34],"capturing":[36],"transferring":[38],"Building":[41],"upon":[42],"Video":[44],"Customization":[46],"(VMC)":[47],"framework,":[48],"we":[49],"proposed":[50,138],"few-shot":[52],"learning":[53],"approach":[54,157],"using":[55,147],"our":[56,156],"unified":[57],"Multi-Head":[58],"Temporal":[59],"Attention":[60],"(MHTA)":[61],"module":[62],"for":[63,87],"text-to-video":[67],"diffusion":[68],"models.":[69],"This":[70],"significantly":[71,152],"reduces":[72],"computational":[73],"requirements":[74],"maintaining":[76,91,114],"improving":[78],"quality.":[80],"Our":[81,137],"model":[82,121,140],"provides":[83],"streamlined":[85],"mechanism":[86,108],"distillation":[89],"separate":[92],"self-,":[93],"cross-,":[94],"temporal":[96,100],"attention.":[97],"Moreover,":[98,155],"attention":[101],"layer":[102],"is":[103],"adapted":[104],"through":[105],"simplified":[107],"with":[109],"efficient":[110],"Q/K/V":[111],"projections,":[112],"fixed":[115],"spatial":[116],"self-":[117],"cross-attention.":[119],"The":[120],"distills":[122],"ground-truth":[124,135],"vector":[126],"from":[127],"consecutive":[128],"frames":[129],"align":[131],"predicted":[133],"motion.":[136],"MHTA":[139],"outperforms":[141],"baseline":[143],"being":[151],"more":[153],"resource-efficient.":[154],"can":[158],"easily":[159],"be":[160],"applied":[161],"generate":[163],"conditional":[164],"prompt-based":[165],"videos":[166],"gaming":[169],"industry.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-28T00:00:00"}
