{"id":"https://openalex.org/W4408223193","doi":"https://doi.org/10.1109/robio64047.2024.10907605","title":"Multi-Head AdaIN Audio-to-Video Motion Style Transfer","display_name":"Multi-Head AdaIN Audio-to-Video Motion Style Transfer","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4408223193","doi":"https://doi.org/10.1109/robio64047.2024.10907605"},"language":"en","primary_location":{"id":"doi:10.1109/robio64047.2024.10907605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5036432480","display_name":"Nuha Aldausari","orcid":"https://orcid.org/0000-0001-6068-2945"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Nuha Aldausari","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055952724","display_name":"Arcot Sowmya","orcid":"https://orcid.org/0000-0001-9236-5063"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arcot Sowmya","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032060005","display_name":"Gelareh Mohammadi","orcid":"https://orcid.org/0000-0002-8087-2241"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gelareh Mohammadi","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036432480"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32273263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"589","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9959999918937683,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9758999943733215,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9735999703407288,"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":0.7292079925537109},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5594238042831421},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4495750665664673},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4313521385192871},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4103526473045349},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37036216259002686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3692147135734558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33310651779174805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292079925537109},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5594238042831421},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4495750665664673},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4313521385192871},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4103526473045349},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37036216259002686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3692147135734558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33310651779174805},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio64047.2024.10907605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1482998036","https://openalex.org/W2301937176","https://openalex.org/W2487442924","https://openalex.org/W2603777577","https://openalex.org/W2806833697","https://openalex.org/W2883183894","https://openalex.org/W2948242301","https://openalex.org/W2963092440","https://openalex.org/W2963290645","https://openalex.org/W2964037671","https://openalex.org/W2971634123","https://openalex.org/W2977816919","https://openalex.org/W2981767644","https://openalex.org/W2990452356","https://openalex.org/W3010049297","https://openalex.org/W3010931949","https://openalex.org/W3019952993","https://openalex.org/W3024902055","https://openalex.org/W3025521275","https://openalex.org/W3034241236","https://openalex.org/W3035169015","https://openalex.org/W3035471785","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3092950464","https://openalex.org/W3107666850","https://openalex.org/W3172500391","https://openalex.org/W3174763799","https://openalex.org/W3175779516","https://openalex.org/W3177211254","https://openalex.org/W3204221554","https://openalex.org/W3205904637","https://openalex.org/W3207250917","https://openalex.org/W4210657261","https://openalex.org/W4214626920","https://openalex.org/W4292829115","https://openalex.org/W4293518720","https://openalex.org/W6718379498","https://openalex.org/W6726983635","https://openalex.org/W6745560452","https://openalex.org/W6765779288","https://openalex.org/W6773664900","https://openalex.org/W6783443514"],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2113206756","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W2613352840","https://openalex.org/W2379547295","https://openalex.org/W2180861836","https://openalex.org/W2079398652","https://openalex.org/W4388166999","https://openalex.org/W2724652190"],"abstract_inverted_index":{"By":[0],"leveraging":[1],"the":[2,12,128,145,158],"advancements":[3],"in":[4],"deep":[5],"learning,":[6],"video":[7,70,81,106,149],"generation":[8,71,129,146],"not":[9],"only":[10],"simplifies":[11],"creation":[13],"of":[14,30,56,69,123,147,157],"visual":[15,24],"content":[16],"but":[17],"also":[18],"enhances":[19],"storytelling,":[20],"thereby":[21],"making":[22],"dynamic":[23],"experiences":[25],"more":[26],"accessible.":[27],"The":[28,155],"process":[29,130],"generating":[31],"videos":[32],"from":[33],"audio":[34,153],"input":[35],"entails":[36],"several":[37],"key":[38],"considerations,":[39],"including":[40],"frame":[41],"quality,":[42],"smooth":[43,60],"motion":[44,63,82,102,124],"and":[45,61,88,167],"synchronisation":[46],"with":[47,171],"audio.":[48],"While":[49],"image":[50,57],"quality":[51],"is":[52,65,116],"a":[53,66,89,120],"fundamental":[54],"aspect":[55,68],"generation,":[58],"creating":[59],"synchronised":[62,148],"trajectories":[64],"challenging":[67],"that":[72,118],"needs":[73],"significant":[74],"attention.":[75],"Various":[76],"approaches":[77,97],"exist":[78],"to":[79,105,141],"learn":[80],"dynamics,":[83],"such":[84,100],"as":[85,93,101],"representation":[86],"decomposition":[87],"self-supervised":[90],"technique":[91],"known":[92],"shuffling.":[94],"However,":[95],"these":[96],"have":[98],"drawbacks":[99],"artifacts":[103],"due":[104],"segmentation.":[107],"To":[108],"address":[109],"this":[110],"challenge,":[111],"an":[112],"alternative":[113],"novel":[114],"methodology":[115],"proposed":[117,159],"offers":[119],"comprehensive":[121],"understanding":[122],"dynamics":[125],"without":[126],"dividing":[127],"into":[131],"multiple":[132,172],"streams.":[133],"This":[134],"work":[135],"leverages":[136],"Adaptive":[137],"Instance":[138],"Normalisation":[139],"(AdaIN)":[140],"adjust":[142],"motion,":[143],"enabling":[144],"sequences":[150],"based":[151],"on":[152],"signals.":[154],"effectiveness":[156],"method":[160],"has":[161],"been":[162],"validated":[163],"through":[164],"both":[165],"qualitative":[166],"quantitative":[168],"metrics,":[169],"comparing":[170],"models.":[173]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}