{"id":"https://openalex.org/W4416125095","doi":"https://doi.org/10.1109/iccv51701.2025.01115","title":"Ditailistener: Controllable High Fidelity Listener Video Generation with Diffusion","display_name":"Ditailistener: Controllable High Fidelity Listener Video Generation with Diffusion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416125095","doi":"https://doi.org/10.1109/iccv51701.2025.01115"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01115","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.04010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027304898","display_name":"Maksim Siniukov","orcid":"https://orcid.org/0000-0001-8529-2281"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maksim Siniukov","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626683","display_name":"Di Chang","orcid":"https://orcid.org/0000-0003-4790-3402"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Chang","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612317","display_name":"Minh Tr\u1ea7n","orcid":"https://orcid.org/0000-0003-4637-6081"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minh Tran","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongkun Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongkun Gong","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120394259","display_name":"Ashutosh Chaubey","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Chaubey","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073987472","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0003-2770-7236"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027304898"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31397522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11991","last_page":"12001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6610000133514404,"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":0.6610000133514404,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2702000141143799,"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/T10860","display_name":"Speech and Audio Processing","score":0.021900000050663948,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.38199999928474426},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.3806000053882599},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.34869998693466187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3353999853134155},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3199000060558319},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.31839999556541443},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523000240325928},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5698999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555999875068665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01115","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:2504.04010","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.04010","pdf_url":"https://arxiv.org/pdf/2504.04010","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.2504.04010","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.04010","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:2504.04010","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.04010","pdf_url":"https://arxiv.org/pdf/2504.04010","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/G7127029262","display_name":null,"funder_award_id":"IIS-2211550","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"naturalistic":[1],"and":[2,33,66,110,152,161,189,219],"nuanced":[3],"listener":[4,59,94,130],"motions":[5,68],"for":[6,21,79,90],"extended":[7],"interactions":[8],"remains":[9],"an":[10],"open":[11],"problem.":[12],"Existing":[13],"methods":[14],"often":[15],"rely":[16],"on":[17,62,178,187,196],"low-dimensional":[18],"motion":[19,190],"codes":[20],"facial":[22,67,159],"behavior":[23],"generation":[24,97,124],"followed":[25],"by":[26,44,98,170,223],"photorealistic":[27],"rendering,":[28],"limiting":[29],"both":[30,182],"visual":[31,111],"fidelity":[32],"expressive":[34],"richness.":[35],"To":[36],"address":[37],"these":[38],"challenges,":[39],"we":[40,136],"introduce":[41,137],"DiTaiListener,":[42,206],"powered":[43],"a":[45,80,86,100,118,139,224],"video":[46,123,134,148,167],"diffusion":[47,143],"model":[48,146,209],"with":[49,69,207],"multimodal":[50],"conditions.":[51],"Our":[52],"approach":[53],"first":[54],"generates":[55],"short":[56,166],"segments":[57,149,168],"of":[58,93,205,216],"responses":[60],"conditioned":[61],"the":[63,74,91,122,175,202,208,211],"speaker's":[64],"speech":[65],"DiTaiListener-Gen.":[70,171],"It":[71],"then":[72],"refines":[73],"transitional":[75],"frames":[76],"via":[77],"DiTaiListener-Edit":[78],"seamless":[81],"transition.":[82],"Specifically,":[83],"DiTaiListener-Gen":[84],"adapts":[85],"Diffusion":[87],"Transformer":[88],"(DiT)":[89],"task":[92],"head":[95],"portrait":[96],"introducing":[99],"Causal":[101],"Temporal":[102],"Multimodal":[103],"Adapter":[104],"(CTM-Adapter)":[105],"to":[106,126],"process":[107,125],"speakers'":[108,115],"auditory":[109],"cues.":[112],"CTM-Adapter":[113],"integrates":[114],"input":[116],"in":[117,158,181,185,193,214],"causal":[119],"manner":[120],"into":[121,150],"ensure":[127],"temporally":[128],"coherent":[129],"responses.":[131],"For":[132],"long-form":[133],"generation,":[135],"DiTaiListener-Edit,":[138],"transition":[140],"refinement":[141],"video-to-video":[142],"model.":[144],"The":[145],"fuses":[147],"smooth":[151],"continuous":[153],"videos,":[154],"ensuring":[155],"temporal":[156],"consistency":[157],"expressions":[160],"image":[162],"quality":[163],"when":[164],"merging":[165],"produced":[169],"Quantitatively,":[172],"DiTaiListener":[173],"achieves":[174],"state-of-the-art":[176],"performance":[177,204],"benchmark":[179],"datasets":[180],"photorealism":[183],"(+73.8%":[184],"FID":[186],"RealTalk)":[188],"representation":[191],"(+6.1%":[192],"FD":[194],"metric":[195],"VICO)":[197],"spaces.":[198],"User":[199],"studies":[200],"confirm":[201],"superior":[203],"being":[210],"clear":[212],"preference":[213],"terms":[215],"feedback,":[217],"diversity,":[218],"smoothness,":[220],"outperforming":[221],"competitors":[222],"significant":[225],"margin.":[226]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
