{"id":"https://openalex.org/W3131910188","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533745","title":"Image Modeling with Deep Convolutional Gaussian Mixture Models","display_name":"Image Modeling with Deep Convolutional Gaussian Mixture Models","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3131910188","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533745","mag":"3131910188"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.12686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030810660","display_name":"Alexander Gepperth","orcid":"https://orcid.org/0000-0003-2216-7808"},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Gepperth","raw_affiliation_strings":["Fulda University of Applied Sciences,Fulda,Germany","Fulda University of Applied Sciences, Fulda, Germany"],"affiliations":[{"raw_affiliation_string":"Fulda University of Applied Sciences,Fulda,Germany","institution_ids":["https://openalex.org/I201850948"]},{"raw_affiliation_string":"Fulda University of Applied Sciences, Fulda, Germany","institution_ids":["https://openalex.org/I201850948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073874147","display_name":"Benedikt Pf\u00fclb","orcid":"https://orcid.org/0000-0002-0108-1936"},"institutions":[{"id":"https://openalex.org/I201850948","display_name":"Fulda University of Applied Sciences","ror":"https://ror.org/041bz9r75","country_code":"DE","type":"education","lineage":["https://openalex.org/I201850948"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benedikt Pfulb","raw_affiliation_strings":["Fulda University of Applied Sciences,Fulda,Germany","Fulda University of Applied Sciences, Fulda, Germany"],"affiliations":[{"raw_affiliation_string":"Fulda University of Applied Sciences,Fulda,Germany","institution_ids":["https://openalex.org/I201850948"]},{"raw_affiliation_string":"Fulda University of Applied Sciences, Fulda, Germany","institution_ids":["https://openalex.org/I201850948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030810660"],"corresponding_institution_ids":["https://openalex.org/I201850948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02728266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9976999759674072,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9972000122070312,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9930999875068665,"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/mixture-model","display_name":"Mixture model","score":0.8320132493972778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060033679008484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6436333656311035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6131410598754883},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.4813878834247589},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.46583572030067444},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.45706313848495483},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.43122580647468567},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42460232973098755},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.41756579279899597},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4166424870491028},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3625779151916504},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2841702103614807},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16480648517608643}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8320132493972778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060033679008484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6436333656311035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6131410598754883},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4813878834247589},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.46583572030067444},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.45706313848495483},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.43122580647468567},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42460232973098755},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.41756579279899597},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4166424870491028},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3625779151916504},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2841702103614807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16480648517608643},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.12686","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.12686","pdf_url":"https://arxiv.org/pdf/2104.12686","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3131910188","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.12686","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.12686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.12686","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:2104.12686","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.12686","pdf_url":"https://arxiv.org/pdf/2104.12686","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3131910188.pdf","grobid_xml":"https://content.openalex.org/works/W3131910188.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1975321310","https://openalex.org/W1990368529","https://openalex.org/W2023831651","https://openalex.org/W2040370888","https://openalex.org/W2049633694","https://openalex.org/W2051224630","https://openalex.org/W2112796928","https://openalex.org/W2125389028","https://openalex.org/W2137983211","https://openalex.org/W2148464528","https://openalex.org/W2158581396","https://openalex.org/W2399803916","https://openalex.org/W2423557781","https://openalex.org/W2534135591","https://openalex.org/W2627006445","https://openalex.org/W2750384547","https://openalex.org/W2768611535","https://openalex.org/W2805225995","https://openalex.org/W2891859490","https://openalex.org/W2894309325","https://openalex.org/W2904464104","https://openalex.org/W2953106669","https://openalex.org/W2964121744","https://openalex.org/W2996001619","https://openalex.org/W3017049286","https://openalex.org/W3146803896","https://openalex.org/W6630304437","https://openalex.org/W6631190155","https://openalex.org/W6637034065","https://openalex.org/W6728959867","https://openalex.org/W6751990271","https://openalex.org/W6754397796","https://openalex.org/W6755196428","https://openalex.org/W6755431558","https://openalex.org/W6776348259"],"related_works":["https://openalex.org/W3200427223","https://openalex.org/W2180686776","https://openalex.org/W1582113396","https://openalex.org/W3015832418","https://openalex.org/W2810480597","https://openalex.org/W2889262940","https://openalex.org/W2173697287","https://openalex.org/W2082831393","https://openalex.org/W1982648793","https://openalex.org/W2913934873","https://openalex.org/W2946188111","https://openalex.org/W1972168313","https://openalex.org/W2473963253","https://openalex.org/W2514783721","https://openalex.org/W2680287507","https://openalex.org/W3158763274","https://openalex.org/W1991848923","https://openalex.org/W1608175048","https://openalex.org/W1992610201","https://openalex.org/W2793631173"],"abstract_inverted_index":{"In":[0],"this":[1,56],"conceptual":[2],"work,":[3],"we":[4,126,148],"present":[5],"Deep":[6],"Convolutional":[7],"Gaussian":[8,18],"Mixture":[9,19],"Models":[10,20],"(DCGMMs):":[11],"a":[12,36,58,80,109,117,128],"new":[13,129],"formulation":[14],"of":[15,40,61,77],"deep":[16,84],"hierarchical":[17],"(GMMs)":[21],"that":[22],"is":[23,114],"particularly":[24],"suitable":[25],"for":[26,132,160],"describing":[27],"and":[28,51,68,139,145,163],"generating":[29,121],"images.":[30],"Vanilla":[31],"(i.e.,":[32],"flat)":[33],"GMMs":[34,102,159],"require":[35],"very":[37],"large":[38],"number":[39],"components":[41],"to":[42,47,73],"describe":[43],"images":[44,78,123],"well,":[45],"leading":[46],"long":[48],"training":[49],"times":[50],"memory":[52],"issues.":[53],"DCGMMs":[54,87,151],"avoid":[55],"by":[57,66,92,106,153],"stacked":[59],"architecture":[60],"multiple":[62],"GMM":[63],"layers,":[64],"linked":[65],"convolution":[67,138],"pooling":[69],"operations.":[70],"This":[71,96],"allows":[72],"exploit":[74],"the":[75,143,150],"compositionality":[76],"in":[79,116],"similar":[81],"way":[82],"as":[83],"CNNs":[85],"do.":[86],"can":[88],"be":[89],"trained":[90,105],"end-to-end":[91],"Stochastic":[93],"Gradient":[94],"Descent.":[95],"sets":[97],"them":[98],"apart":[99],"from":[100],"vanilla":[101],"which":[103,113],"are":[104],"Expectation-Maximization,":[107],"requiring":[108],"prior":[110],"k-means":[111],"initialization":[112],"infeasible":[115],"layered":[118],"structure.":[119],"For":[120],"sharp":[122],"with":[124],"DCGMMs,":[125],"introduce":[127],"gradient-based":[130],"technique":[131],"sampling":[133,162],"through":[134],"non-invertible":[135],"operations":[136],"like":[137],"pooling.":[140],"Based":[141],"on":[142],"MNIST":[144],"FashionMNIST":[146],"datasets,":[147],"validate":[149],"model":[152],"demonstrating":[154],"its":[155],"superiority":[156],"over":[157],"flat":[158],"clustering,":[161],"outlier":[164],"detection.":[165]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}