{"id":"https://openalex.org/W4409050809","doi":"https://doi.org/10.1109/iccv51701.2025.00986","title":"EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-To-Video Diffusion Models","display_name":"EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-To-Video Diffusion Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4409050809","doi":"https://doi.org/10.1109/iccv51701.2025.00986"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.19369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035714966","display_name":"Yufei Cai","orcid":"https://orcid.org/0000-0002-0785-7045"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Cai","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101976576","display_name":"Han Hu","orcid":"https://orcid.org/0000-0001-5104-6146"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Han","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058312928","display_name":"Yuxiang Wei","orcid":"https://orcid.org/0000-0002-4391-3753"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Wei","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.0599707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10592","last_page":"10601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.953000009059906,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.953000009059906,"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":0.9409999847412109,"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":0.9261000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7470942735671997},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6463767290115356},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6100653409957886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.571868896484375},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5409852266311646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3311634659767151},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13231658935546875},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08975711464881897},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.05205163359642029}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7470942735671997},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6463767290115356},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6100653409957886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.571868896484375},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5409852266311646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3311634659767151},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13231658935546875},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08975711464881897},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.05205163359642029},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.19369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19369","pdf_url":"https://arxiv.org/pdf/2503.19369","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2503.19369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.19369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19369","pdf_url":"https://arxiv.org/pdf/2503.19369","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G738465104","display_name":null,"funder_award_id":"U2336213,62176249","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W2912421143"],"abstract_inverted_index":{"The":[0],"progress":[1],"on":[2,10,42,146],"generative":[3],"models":[4],"has":[5],"led":[6],"to":[7,34,109,122],"significant":[8],"advances":[9],"text-to-video":[11],"(T2V)":[12],"generation,":[13],"yet":[14],"the":[15,28,103,106,140],"motion":[16,24,29,65,75,88,98,137,156,176],"controllability":[17],"of":[18,31,72,105],"generated":[19],"videos":[20,33],"remains":[21],"limited.":[22],"Existing":[23],"transfer":[25,76,89,157],"methods":[26,39,170],"explored":[27],"representations":[30],"reference":[32,114,136],"guide":[35],"generation.":[36],"Nevertheless,":[37],"these":[38],"typically":[40],"rely":[41],"sample-specific":[43],"optimization":[44],"strategy,":[45],"resulting":[46],"in":[47,171],"high":[48],"computational":[49],"burdens.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,101,127],"propose":[55,118],"EfficientMT,":[56],"a":[57,69,81,86,119,129],"novel":[58],"and":[59,95,116],"efficient":[60],"end-to-end":[61],"framework":[62,90],"for":[63],"video":[64,141,155],"transfer.":[66],"By":[67],"leveraging":[68],"small":[70],"set":[71],"synthetic":[73,149],"paired":[74,150],"samples,":[77,151],"EfficientMT":[78,152,167],"effectively":[79],"adapts":[80],"pretrained":[82],"T2V":[83,107],"model":[84,108],"into":[85,139],"general":[87,154],"that":[91,133,165],"can":[92],"accurately":[93],"capture":[94],"reproduce":[96],"diverse":[97],"patterns.":[99],"Specifically,":[100],"repurpose":[102],"backbone":[104],"extract":[110],"temporal":[111,130],"information":[112],"from":[113],"videos,":[115],"further":[117],"scaler":[120],"module":[121],"distill":[123],"motion-related":[124],"information.":[125],"Subsequently,":[126],"introduce":[128],"integration":[131],"mechanism":[132],"seamlessly":[134],"incorporates":[135],"features":[138],"generation":[142],"process.":[143],"After":[144],"training":[145],"our":[147,166],"self-collected":[148],"enables":[153],"without":[158],"requiring":[159],"test-time":[160],"optimization.":[161],"Extensive":[162],"experiments":[163],"demonstrate":[164],"outperforms":[168],"existing":[169],"efficiency":[172],"while":[173],"maintaining":[174],"flexible":[175],"controllability.":[177],"Our":[178],"code":[179],"will":[180],"be":[181],"available":[182],"https://github.com/PrototypeNx/EfficientMT.":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}