{"id":"https://openalex.org/W2997320828","doi":"https://doi.org/10.1109/icpr48806.2021.9412309","title":"GAN-based Gaussian Mixture Model Responsibility Learning","display_name":"GAN-based Gaussian Mixture Model Responsibility Learning","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W2997320828","doi":"https://doi.org/10.1109/icpr48806.2021.9412309","mag":"2997320828"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5046013836","display_name":"Wanming Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Wanming Huang","raw_affiliation_strings":["Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073709711","display_name":"Richard Yi Da Xu","orcid":"https://orcid.org/0000-0003-2080-4762"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Yi Da Xu","raw_affiliation_strings":["Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103160576","display_name":"Shuai Jiang","orcid":"https://orcid.org/0000-0002-9305-0538"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuai Jiang","raw_affiliation_strings":["Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078771477","display_name":"Liang Xuan","orcid":"https://orcid.org/0000-0002-8420-3109"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuan Liang","raw_affiliation_strings":["Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012626641","display_name":"Ian Oppermann","orcid":"https://orcid.org/0000-0003-2263-9430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian Oppermann","raw_affiliation_strings":["NSW Data Analytics Centre, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"NSW Data Analytics Centre, Sydney, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046013836"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00315359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1706 8500","issue":null,"first_page":"3467","last_page":"3474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9984999895095825,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9984999895095825,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/mixture-model","display_name":"Mixture model","score":0.7555921077728271},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5813824534416199},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5767610669136047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5756045579910278},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5607410669326782},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.544781506061554},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5129849314689636},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.5038718581199646},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.459555983543396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.456545352935791},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.4550950229167938},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4400429427623749},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4250308871269226},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.419039785861969},{"id":"https://openalex.org/keywords/mixture-distribution","display_name":"Mixture distribution","score":0.4185100793838501},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3786906599998474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3732128143310547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3356587290763855},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.30221813917160034},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.27949267625808716},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15470269322395325},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1321641206741333},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10139644145965576}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7555921077728271},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5813824534416199},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5767610669136047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5756045579910278},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5607410669326782},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.544781506061554},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5129849314689636},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.5038718581199646},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.459555983543396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.456545352935791},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.4550950229167938},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4400429427623749},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4250308871269226},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.419039785861969},{"id":"https://openalex.org/C56672385","wikidata":"https://www.wikidata.org/wiki/Q17157111","display_name":"Mixture distribution","level":3,"score":0.4185100793838501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3786906599998474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732128143310547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3356587290763855},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30221813917160034},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.27949267625808716},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15470269322395325},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1321641206741333},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10139644145965576},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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":27,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2183341477","https://openalex.org/W2551604710","https://openalex.org/W2556467266","https://openalex.org/W2687693326","https://openalex.org/W2742760508","https://openalex.org/W2750384547","https://openalex.org/W2782980316","https://openalex.org/W2889205371","https://openalex.org/W2963373786","https://openalex.org/W2963761396","https://openalex.org/W2963873275","https://openalex.org/W2963981733","https://openalex.org/W3118608800","https://openalex.org/W4293568373","https://openalex.org/W4320013936","https://openalex.org/W6686164453","https://openalex.org/W6718379498","https://openalex.org/W6729832310","https://openalex.org/W6730333270","https://openalex.org/W6740327194","https://openalex.org/W6743688258","https://openalex.org/W6746090280","https://openalex.org/W6747733185","https://openalex.org/W6754432133","https://openalex.org/W6780248173","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3099192420","https://openalex.org/W3007519100","https://openalex.org/W2778147733","https://openalex.org/W4297730821","https://openalex.org/W2488457351","https://openalex.org/W4244110343","https://openalex.org/W2588734120","https://openalex.org/W153701065","https://openalex.org/W4288408954","https://openalex.org/W2061603704"],"abstract_inverted_index":{"Mixture":[0],"model":[1,294],"(MM)":[2],"is":[3,21,62,71,200,221,281],"a":[4,24,37,41,48,66,189,237,245,254,272,334],"probabilistic":[5],"framework":[6,186],"allows":[7,101,291],"us":[8,102,292],"to":[9,29,73,103,159,166,174,187,193,240,274,293,305],"define":[10],"dataset":[11,132,296],"containing":[12,125,139],"K":[13],"different":[14],"modes.":[15],"When":[16],"each":[17,96,116],"of":[18,47,108,115,117,212,217,229,297,309,330],"the":[19,45,59,77,85,92,99,109,113,118,147,151,181,206,227,266,295,331],"modes":[20,332],"associated":[22,63],"with":[23],"Gaussian":[25,32,58],"distribution,":[26],"we":[27,179,202],"refer":[28],"it":[30,70,242,270,290],"as":[31,82,84,130,316,318],"MM":[33],"or":[34],"GMM.":[35],"Given":[36],"data":[38,61,152,322],"point":[39],"x,":[40,89],"GMM":[42,68,172,302],"may":[43,133],"assume":[44],"existence":[46],"random":[49],"index":[50],"k":[51],"\u03f5":[52],"{1,":[53],"...,":[54],"K}":[55],"identifying":[56],"which":[57,225],"particular":[60],"with.":[64],"In":[65,143,176],"traditional":[67],"paradigm,":[69],"straightforward":[72],"compute":[74,167,194,203],"in":[75,283,333],"closed-form,":[76],"conditional":[78],"likelihood":[79],"p(x|k,":[80],"\u03b8)":[81,90,232],"well":[83,317],"responsibility":[86,100,168,230],"probability":[87],"p(k|":[88],"describing":[91],"distribution":[93,169,273],"weights":[94,114],"for":[95],"data.":[97],"Computing":[98],"retrieve":[104],"many":[105],"important":[106],"statistics":[107],"overall":[110],"dataset,":[111,312],"including":[112,313],"modes/clusters.":[119],"Modern":[120],"large":[121],"datasets":[122],"are":[123],"often":[124],"multiple":[126],"unlabelled":[127,141],"modes,":[128],"such":[129],"paintings":[131],"contain":[134],"several":[135,140],"styles;":[136],"fashion":[137],"images":[138],"categories.":[142],"its":[144,257,314],"raw":[145],"representation,":[146],"Euclidean":[148],"distances":[149],"between":[150],"(e.g.,":[153],"images)":[154],"do":[155],"not":[156,264],"allow":[157],"them":[158,204],"form":[160],"mixtures":[161],"naturally,":[162],"nor":[163],"it's":[164],"feasible":[165],"analytically,":[170],"making":[171],"unable":[173],"apply.":[175],"this":[177,215],"paper,":[178],"utilize":[180],"generative":[182],"adversarial":[183],"network":[184,280],"(GAN)":[185],"achieve":[188],"plausible":[190],"alternative":[191],"method":[192,239],"these":[195,288],"probabilities.":[196],"The":[197,278],"key":[198],"insight":[199],"that":[201],"at":[205],"data's":[207],"latent":[208],"space":[209],"z":[210,218],"instead":[211,269],"x.":[213],"However,":[214],"process":[216],"\u2192":[219],"x":[220],"irreversible":[222],"under":[223],"GAN":[224],"renders":[226],"computation":[228],"p(k|x,":[231,276],"infeasible.":[233],"Our":[234],"paper":[235],"proposed":[236],"novel":[238],"solve":[241],"by":[243,323],"using":[244,301],"socalled":[246],"posterior":[247],"consistency":[248],"module":[249],"(PCM).":[250],"PCM":[251],"acts":[252],"like":[253],"GAN,":[255],"except":[256],"generator":[258],"C":[259],"<sub":[260],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[261],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">PCM</sub>":[262],"does":[263],"output":[265],"data,":[267],"but":[268],"outputs":[271],"approximate":[275],"\u03b8).":[277],"entire":[279],"trained":[282],"an":[284,310],"\u201cend-to-end\u201d":[285],"fashion.":[286],"Trough":[287],"techniques,":[289],"very":[298],"complex":[299],"structure":[300],"and":[303],"subsequently":[304],"discover":[306],"interesting":[307],"properties":[308],"unsupervised":[311,336],"segments,":[315],"generating":[319],"new":[320],"\u201cout-distribution\u201d":[321],"smooth":[324],"linear":[325],"interpolation":[326],"across":[327],"any":[328],"combinations":[329],"completely":[335],"manner.":[337]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}