{"id":"https://openalex.org/W4385488559","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191705","title":"A Generative Approach to Audio-Visual Generalized Zero-Shot Learning: Combining Contrastive and Discriminative Techniques","display_name":"A Generative Approach to Audio-Visual Generalized Zero-Shot Learning: Combining Contrastive and Discriminative Techniques","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488559","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191705"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5009318392","display_name":"Qichen Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qichen Zheng","raw_affiliation_strings":["College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia","Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057904986","display_name":"Jie Hong","orcid":"https://orcid.org/0000-0002-2831-7523"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Hong","raw_affiliation_strings":["College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia","College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I1292875679","https://openalex.org/I42894916"]},{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067223903","display_name":"Moshiur Farazi","orcid":"https://orcid.org/0000-0003-1494-5921"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Moshiur Farazi","raw_affiliation_strings":["College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia","College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Imaging and Computer Vision Group, Data61-CSIRO, Canberra, Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I1292875679","https://openalex.org/I42894916"]},{"raw_affiliation_string":"College of Engineering, Computing and Cybernetics, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009318392"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I1292875679","https://openalex.org/I2802348851","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79601928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9537000060081482,"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/discriminative-model","display_name":"Discriminative model","score":0.8095331192016602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253409624099731},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6655470132827759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6091123223304749},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5652764439582825},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5590436458587646},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49158939719200134},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48237863183021545},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.462923526763916},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4572990834712982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44251134991645813},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4127545952796936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4092108905315399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35201337933540344},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07848507165908813}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8095331192016602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253409624099731},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6655470132827759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6091123223304749},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5652764439582825},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5590436458587646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49158939719200134},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48237863183021545},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.462923526763916},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4572990834712982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44251134991645813},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4127545952796936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092108905315399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35201337933540344},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07848507165908813},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1503933356","https://openalex.org/W1522734439","https://openalex.org/W1614298861","https://openalex.org/W1682403713","https://openalex.org/W1927052826","https://openalex.org/W2017458735","https://openalex.org/W2409534643","https://openalex.org/W2526050071","https://openalex.org/W2703895418","https://openalex.org/W2788241093","https://openalex.org/W2890952074","https://openalex.org/W2962903908","https://openalex.org/W2963290645","https://openalex.org/W2963499153","https://openalex.org/W2963960318","https://openalex.org/W2964171275","https://openalex.org/W2990113535","https://openalex.org/W3015371781","https://openalex.org/W3025520547","https://openalex.org/W3035655772","https://openalex.org/W3037195468","https://openalex.org/W3119136678","https://openalex.org/W3121070744","https://openalex.org/W3123709248","https://openalex.org/W3136499730","https://openalex.org/W3137028092","https://openalex.org/W3162322471","https://openalex.org/W3171926364","https://openalex.org/W3190580390","https://openalex.org/W3203711169","https://openalex.org/W3211196264","https://openalex.org/W4285787895","https://openalex.org/W4312763854","https://openalex.org/W6600983433","https://openalex.org/W6636510571","https://openalex.org/W6749074686","https://openalex.org/W6754392867","https://openalex.org/W6779844698","https://openalex.org/W6789528441","https://openalex.org/W6802360106","https://openalex.org/W6809837078"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4241564561"],"abstract_inverted_index":{"Audio-visual":[0],"generalized":[1],"zero-shot":[2,55],"learning":[3],"(AV-GZSL)":[4],"for":[5,97],"video":[6,18,38],"classification":[7,39],"is":[8,25,65],"a":[9,26,54,104,115,132,147],"task":[10],"where":[11,33,140],"the":[12,47,66,87,108,123,136,161],"model":[13,169],"learns":[14],"to":[15,36,50,68,81,135],"identify":[16],"unseen":[17,143,183],"classes":[19,184],"from":[20,40],"multimodal":[21],"audio-visual":[22,144],"inputs.":[23],"This":[24],"combination":[27],"of":[28,44,110,122,163],"two":[29,41,88],"equally":[30],"challenging":[31],"tasks":[32],"one":[34],"tries":[35],"perform":[37],"different":[42,111],"modalities":[43,64,112],"inputs,":[45],"and":[46,62,91,100,118,150,156,173,175,179],"other":[48],"pushes":[49],"achieve":[51],"this":[52,70],"in":[53,77],"setting.":[56],"The":[57,74],"natural":[58],"alignment":[59],"between":[60,86,107],"audio":[61],"visual":[63],"key":[67],"addressing":[69],"relatively":[71],"unexplored":[72],"task.":[73],"predominant":[75],"approach":[76,134],"AV-GZSL":[78],"has":[79],"been":[80],"learn":[82],"better":[83,98,186],"cross-modal":[84],"attention":[85,99],"input":[89],"domains":[90],"leverage":[92],"large":[93],"language":[94],"pretraining.":[95],"However,":[96],"pretraining,":[101],"there":[102],"exists":[103],"semantic":[105],"gap":[106],"embedding":[109,125],"that":[113,182],"requires":[114],"more":[116],"diverse":[117],"less":[119],"sparse":[120],"representation":[121],"joint":[124],"space.":[126],"To":[127,159],"overcome":[128],"this,":[129],"we":[130,141,166],"propose":[131],"complementary":[133],"existing":[137],"research":[138],"direction,":[139],"simulate":[142],"features":[145],"using":[146],"generative":[148,191],"model,":[149],"regulate":[151],"it":[152],"by":[153],"combining":[154],"contrastive":[155],"discriminative":[157],"loss.":[158],"demonstrate":[160],"effectiveness":[162],"our":[164,168,190],"approach,":[165],"benchmark":[167],"on":[170],"VGGSound-GZSL,":[171],"ActivityNet-GZSL,":[172],"UCF-GZSL":[174],"report":[176],"state-of-the-art":[177],"performance,":[178],"qualitatively":[180],"show":[181],"are":[185],"clustered":[187],"together":[188],"with":[189],"approach.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}