{"id":"https://openalex.org/W4411631864","doi":"https://doi.org/10.1145/3731715.3733411","title":"OT-Talk: Animating 3D Talking Head with Optimal Transportation","display_name":"OT-Talk: Animating 3D Talking Head with Optimal Transportation","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631864","doi":"https://doi.org/10.1145/3731715.3733411"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030630745","display_name":"Xinmu Wang","orcid":"https://orcid.org/0000-0001-5655-4342"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinmu Wang","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5655-4342","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Gao","orcid":"https://orcid.org/0009-0005-4385-3630"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Gao","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":"https://orcid.org/0009-0005-4385-3630","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233664","display_name":"Xiyun Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiyun Song","raw_affiliation_strings":["Futurewei Technologies, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-3114-7322","affiliations":[{"raw_affiliation_string":"Futurewei Technologies, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109800849","display_name":"Heather Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heather Yu","raw_affiliation_strings":["Futurewei Technologies, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-4793-7585","affiliations":[{"raw_affiliation_string":"Futurewei Technologies, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101333457","display_name":"Zongfang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongfang Lin","raw_affiliation_strings":["Futurewei Technologies, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0002-6111-0708","affiliations":[{"raw_affiliation_string":"Futurewei Technologies, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101333458","display_name":"Liang Peng","orcid":"https://orcid.org/0009-0000-5161-9688"},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["Futurewei Technologies, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0000-5161-9688","affiliations":[{"raw_affiliation_string":"Futurewei Technologies, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210146936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100607707","display_name":"Xianfeng Gu","orcid":"https://orcid.org/0000-0001-8226-5851"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianfeng Gu","raw_affiliation_strings":["Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-8226-5851","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1340","last_page":"1349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9990000128746033,"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/T11448","display_name":"Face recognition and analysis","score":0.9990000128746033,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.6972370147705078},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6539552211761475},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4467964172363281},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4092247188091278},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14088675379753113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972370147705078},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6539552211761475},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4467964172363281},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4092247188091278},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14088675379753113},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W1585160083","https://openalex.org/W2019106840","https://openalex.org/W2124116628","https://openalex.org/W2154961933","https://openalex.org/W2235901111","https://openalex.org/W2468212864","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2741275949","https://openalex.org/W2745771616","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2883221003","https://openalex.org/W2914165399","https://openalex.org/W2943355826","https://openalex.org/W2963197375","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W3008956107","https://openalex.org/W3034192160","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3154411171","https://openalex.org/W3174763799","https://openalex.org/W3186090335","https://openalex.org/W3194006130","https://openalex.org/W3198131199","https://openalex.org/W4200630629","https://openalex.org/W4206471589","https://openalex.org/W4233762729","https://openalex.org/W4241602464","https://openalex.org/W4254161494","https://openalex.org/W4297793551","https://openalex.org/W4386076250","https://openalex.org/W4387967971","https://openalex.org/W4387969119","https://openalex.org/W4388157164","https://openalex.org/W4390872742","https://openalex.org/W4392251762","https://openalex.org/W4393026872","https://openalex.org/W4400818936"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Animating":[0],"3D":[1,16],"head":[2,62],"meshes":[3,130],"using":[4],"audio":[5,77],"inputs":[6],"has":[7],"significant":[8],"applications":[9],"in":[10,34,60,163,187],"AR/VR,":[11],"gaming,":[12],"and":[13,26,38,79,121,134,158,165,185,193],"entertainment":[14],"through":[15],"avatars.":[17],"However,":[18],"bridging":[19],"the":[20,48,57,143,154,210],"modality":[21],"gap":[22],"between":[23,124],"speech":[24],"signals":[25],"facial":[27,40,160,167],"dynamics":[28],"remains":[29],"a":[30,71,80,200],"challenge,":[31],"often":[32],"resulting":[33,162],"incorrect":[35],"lip":[36],"syncing":[37],"unnatural":[39],"movements.":[41],"To":[42,110],"address":[43],"this,":[44],"we":[45,69,98,114,128,198],"propose":[46],"OT-Talk,":[47],"first":[49],"approach":[50,152],"to":[51,55,75,83,103,141,207],"leverage":[52,142],"optimal":[53],"transportation":[54],"optimize":[56],"learning":[58,67,155],"model":[59,74,82],"talking":[61],"animation.":[63],"Building":[64],"on":[65,93,171],"existing":[66],"frameworks,":[68],"utilize":[70],"pre-trained":[72],"Hubert":[73],"extract":[76,104],"features":[78,106],"transformer":[81],"process":[84],"temporal":[85,194],"sequences.":[86],"Unlike":[87],"previous":[88],"methods":[89],"that":[90,177],"focus":[91],"solely":[92],"vertex":[94],"coordinates":[95],"or":[96],"displacements,":[97],"introduce":[99],"Chebyshev":[100],"Graph":[101],"Convolution":[102],"geometric":[105],"from":[107],"triangulated":[108],"meshes.":[109],"measure":[111],"mesh":[112,118,149,190],"dissimilarities,":[113],"go":[115],"beyond":[116],"traditional":[117],"reconstruction":[119,191],"errors":[120],"velocity":[122],"differences":[123],"adjacent":[125],"frames.":[126],"Instead,":[127],"represent":[129],"as":[131],"probability":[132],"measures":[133],"approximate":[135],"their":[136],"surfaces.":[137],"This":[138,151],"allows":[139],"us":[140],"sliced":[144],"Wasserstein":[145],"distance":[146],"for":[147],"modeling":[148],"variations.":[150],"facilitates":[153],"of":[156,189,212],"smooth":[157],"accurate":[159],"motions,":[161],"coherent":[164],"natural":[166],"animations.":[168],"Our":[169],"experiments":[170],"two":[172],"public":[173],"audio-mesh":[174],"datasets":[175],"demonstrate":[176],"our":[178,213],"method":[179],"outperforms":[180],"state-of-the-art":[181],"techniques":[182],"both":[183],"quantitatively":[184],"qualitatively":[186],"terms":[188],"accuracy":[192],"alignment.":[195],"In":[196],"addition,":[197],"conducted":[199],"user":[201],"perception":[202],"study":[203],"with":[204],"20":[205],"volunteers":[206],"further":[208],"assess":[209],"effectiveness":[211],"approach.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}