{"id":"https://openalex.org/W7137858719","doi":"https://doi.org/10.1609/aaai.v40i10.37750","title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","display_name":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137858719","doi":"https://doi.org/10.1609/aaai.v40i10.37750"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37750","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37750","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37750/41712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37750/41712","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076343947","display_name":"Tuna Han Salih Meral","orcid":"https://orcid.org/0000-0002-0379-848X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tuna Han Salih Meral","raw_affiliation_strings":["Virginia Polytechnic Institute and State University"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093452545","display_name":"Hidir Yesiltepe","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hidir Yesiltepe","raw_affiliation_strings":["Virginia Polytechnic Institute and State University"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115057046","display_name":"Connor Dunlop","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Connor Dunlop","raw_affiliation_strings":["Virginia Polytechnic Institute and State University"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016498717","display_name":"Pinar Yanardag","orcid":"https://orcid.org/0000-0003-0193-7818"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pinar Yanardag","raw_affiliation_strings":["Virginia Polytechnic Institute and State University"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076343947"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09253731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8043","last_page":"8051"},"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":0.9577999711036682,"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":0.9577999711036682,"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":0.013299999758601189,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.00430000014603138,"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/motion","display_name":"Motion (physics)","score":0.7225000262260437},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4426000118255615},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.38749998807907104},{"id":"https://openalex.org/keywords/motion-analysis","display_name":"Motion analysis","score":0.36010000109672546},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.351500004529953},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7434999942779541},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7225000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7132999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6561999917030334},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.351500004529953},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.3278999924659729},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C27402916","wikidata":"https://www.wikidata.org/wiki/Q31009","display_name":"Image stabilization","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37750","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37750","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37750/41712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37750","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37750","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37750/41712","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137858719.pdf","grobid_xml":"https://content.openalex.org/works/W7137858719.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-video":[0],"models":[1],"have":[2],"demonstrated":[3],"impressive":[4],"capabilities":[5],"in":[6,52,146],"producing":[7],"diverse":[8],"video":[9,28,37,81],"content,":[10],"yet":[11],"often":[12],"lack":[13],"fine-grained":[14],"control":[15],"over":[16],"motion.":[17],"We":[18,57],"address":[19],"the":[20,40,45,92,99,113],"problem":[21],"of":[22],"motion":[23,42,71,89,147],"transfer:":[24],"given":[25],"a":[26,30,35,60,79,137],"source":[27,41,93],"and":[29,48,54,84,123,129,133,151],"target":[31,46,100,114],"text":[32,115],"prompt,":[33],"generate":[34],"new":[36],"that":[38,63,103,141],"preserves":[39],"while":[43,112],"matching":[44],"semantics":[47],"allowing":[49],"large":[50],"changes":[51],"appearance":[53],"scene":[55,156],"layout.":[56],"introduce":[58],"MotionFlow,":[59],"training-free":[61],"framework":[62],"performs":[64],"test-time":[65],"latent":[66],"optimization":[67],"guided":[68],"by":[69],"attention-derived":[70],"cues.":[72],"MotionFlow":[73,142],"first":[74],"extracts":[75],"cross-attention":[76],"maps":[77],"from":[78],"pre-trained":[80],"diffusion":[82],"model":[83],"converts":[85],"them":[86],"into":[87],"spatio-temporal":[88],"masks":[90],"for":[91],"subject.":[94],"During":[95],"generation,":[96],"it":[97],"optimizes":[98],"latents":[101],"so":[102],"their":[104],"evolving":[105],"attention":[106],"patterns":[107],"align":[108],"with":[109],"these":[110],"masks,":[111],"controls":[116],"appearance.":[117],"This":[118],"avoids":[119],"direct":[120],"attention-map":[121],"replacement":[122],"any":[124],"model-specific":[125],"fine-tuning,":[126],"reducing":[127],"artifacts":[128],"improving":[130],"flexibility.":[131],"Qualitative":[132],"quantitative":[134],"experiments,":[135],"including":[136],"user":[138],"study,":[139],"show":[140],"outperforms":[143],"existing":[144],"methods":[145],"fidelity,":[148],"temporal":[149],"consistency,":[150],"versatility,":[152],"even":[153],"under":[154],"drastic":[155],"changes.":[157]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}