{"id":"https://openalex.org/W2963066677","doi":"https://doi.org/10.1145/3126686.3126723","title":"Deep Cross-Modal Audio-Visual Generation","display_name":"Deep Cross-Modal Audio-Visual Generation","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2963066677","doi":"https://doi.org/10.1145/3126686.3126723","mag":"2963066677"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","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/A5101452655","display_name":"Lele Chen","orcid":"https://orcid.org/0000-0002-7073-0450"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lele Chen","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101123189","display_name":"Sudhanshu Srivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudhanshu Srivastava","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064805926","display_name":"Chenliang Xu","orcid":"https://orcid.org/0000-0002-2183-822X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101452655"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":16.1089,"has_fulltext":false,"cited_by_count":199,"citation_normalized_percentile":{"value":0.99490077,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9811000227928162,"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":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.770362377166748},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6732149720191956},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6346375346183777},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.584922194480896},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5195039510726929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48670580983161926},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4669032692909241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46456801891326904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33966654539108276},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33557599782943726},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20830991864204407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770362377166748},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6732149720191956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6346375346183777},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.584922194480896},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5195039510726929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48670580983161926},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4669032692909241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46456801891326904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33966654539108276},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33557599782943726},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20830991864204407},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126686.3126723","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1523224409","https://openalex.org/W1542441392","https://openalex.org/W1964073652","https://openalex.org/W1975141679","https://openalex.org/W1998749086","https://openalex.org/W2040221341","https://openalex.org/W2045085612","https://openalex.org/W2047668141","https://openalex.org/W2099471712","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2125389028","https://openalex.org/W2138118304","https://openalex.org/W2164587673","https://openalex.org/W2173520492","https://openalex.org/W2183759028","https://openalex.org/W2184188583","https://openalex.org/W2398118205","https://openalex.org/W2400717490","https://openalex.org/W2432004435","https://openalex.org/W2476034201","https://openalex.org/W2554423077","https://openalex.org/W2564082645","https://openalex.org/W2651884604","https://openalex.org/W2778764040","https://openalex.org/W2949999304","https://openalex.org/W2951523806","https://openalex.org/W2951538594","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2964345931","https://openalex.org/W3038022805","https://openalex.org/W4246999471","https://openalex.org/W4247442285"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W2380075625","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W627697492"],"abstract_inverted_index":{"Cross-modal":[0],"audio-visual":[1,37,79],"perception":[2,21],"has":[3,39,141],"been":[4,41],"a":[5,157],"long-lasting":[6],"topic":[7],"in":[8,19,44,174],"psychology":[9],"and":[10,12,24,91,94,101,121,134],"neurology,":[11],"various":[13,163],"studies":[14],"have":[15],"discovered":[16],"strong":[17],"correlations":[18],"human":[20,135],"of":[22,35,64,81,119,123,126],"auditory":[23],"visual":[25,92],"stimuli.":[26],"Despite":[27],"work":[28,95],"on":[29,96,162],"computational":[30],"multimodal":[31],"modeling,":[32],"the":[33,45,52,62,105,142,151,168],"problem":[34,60,177],"cross-modal":[36,58,78],"generation":[38,59,80,100],"not":[40],"systematically":[42],"studied":[43],"literature.":[46],"In":[47],"this":[48,57,109,175],"paper,":[49],"we":[50,70,112],"make":[51],"first":[53,106],"attempt":[54],"to":[55,76,107,144,156],"solve":[56],"leveraging":[61],"power":[63],"deep":[65],"generative":[66,73],"adversarial":[67,74],"training.":[68],"Specifically,":[69],"use":[71],"conditional":[72],"networks":[75],"achieve":[77],"musical":[82,124],"performances.":[83],"We":[84],"explore":[85,108],"different":[86,127],"encoding":[87],"methods":[88],"for":[89],"audio":[90],"signals,":[93],"two":[97,114],"scenarios:":[98],"instrument-oriented":[99],"pose-oriented":[102],"generation.":[103],"Being":[104],"new":[110,115,176],"problem,":[111],"compose":[113],"datasets":[116,169],"with":[117,167],"pairs":[118],"images":[120],"sounds":[122],"performances":[125],"instruments.":[128],"Our":[129,160],"experiments":[130,161],"using":[131],"both":[132],"classification":[133],"evaluation":[136],"demonstrate":[137],"that":[138],"our":[139],"model":[140],"ability":[143],"generate":[145],"one":[146],"modality,":[147,153],"i.e.,":[148,154],"audio/visual,":[149],"from":[150],"other":[152],"visual/audio,":[155],"good":[158],"extent.":[159],"design":[164],"choices":[165],"along":[166],"will":[170],"facilitate":[171],"future":[172],"research":[173],"space.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":14}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}