{"id":"https://openalex.org/W2946004347","doi":null,"title":"Faster Attend-Infer-Repeat with Tractable Probabilistic Models.","display_name":"Faster Attend-Infer-Repeat with Tractable Probabilistic Models.","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2946004347","mag":"2946004347"},"language":"en","primary_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/49c00514-1491-4264-a9f3-e67a51ff1926","doi":null,"is_oa":false,"landing_page_url":"https://www.scopus.com/pages/publications/85077992880","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Stelzner, K, Peharz, R & Kersting, K 2019, Faster attend-infer-repeat with tractable probabilistic models. in 36th International Conference on Machine Learning, ICML 2019. Proceedings of Machine Learning Research, pp. 10455-10466, 36th International Conference on Machine Learning (ICML 2019), Long Beach, United States, 9/06/19.","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5087861569","display_name":"Karl Stelzner","orcid":"https://orcid.org/0009-0009-6750-0644","observed_orcids":["https://orcid.org/0009-0009-6750-0644"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karl Stelzner","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057485787","display_name":"Robert Peharz","orcid":"https://orcid.org/0000-0002-8644-9655","observed_orcids":["https://orcid.org/0000-0002-8644-9655"]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Peharz","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8644-9655","affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037636074","display_name":"Kristian Kersting","orcid":"https://orcid.org/0000-0002-2873-9152","observed_orcids":["https://orcid.org/0000-0002-2873-9152"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kristian Kersting","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2873-9152","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.713,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.88917966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5966","last_page":"5975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8349999785423279,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.8349999785423279,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1111999973654747,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.00839999970048666,"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/sum-product-networks","display_name":"sum-product networks","score":0.7929999828338623},{"id":"https://openalex.org/keywords/object-occlusion","display_name":"object occlusion","score":0.5709999799728394},{"id":"https://openalex.org/keywords/background-noise-modeling","display_name":"background noise modeling","score":0.8299999833106995},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.7480000257492065},{"id":"https://openalex.org/keywords/learning-speed","display_name":"learning speed","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7797505855560303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671114206314087},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7177765369415283},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7048097848892212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258050799369812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5844302773475647},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5831071138381958},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5087509751319885},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4965875744819641},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.43085676431655884},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3570062518119812},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":3,"locations":[{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/49c00514-1491-4264-a9f3-e67a51ff1926","doi":null,"is_oa":false,"landing_page_url":"https://www.scopus.com/pages/publications/85077992880","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Stelzner, K, Peharz, R & Kersting, K 2019, Faster attend-infer-repeat with tractable probabilistic models. in 36th International Conference on Machine Learning, ICML 2019. Proceedings of Machine Learning Research, pp. 10455-10466, 36th International Conference on Machine Learning (ICML 2019), Long Beach, United States, 9/06/19.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/49c00514-1491-4264-a9f3-e67a51ff1926","doi":null,"is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/49c00514-1491-4264-a9f3-e67a51ff1926","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"36th International Conference on Machine Learning, ICML 2019, 10455 - 10466","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"mag:2946004347","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v97/stelzner19a/stelzner19a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1646152356","https://openalex.org/W1835282959","https://openalex.org/W1959608418","https://openalex.org/W2070450685","https://openalex.org/W2099471712","https://openalex.org/W2139546855","https://openalex.org/W2145983039","https://openalex.org/W2150807068","https://openalex.org/W2166851633","https://openalex.org/W2168906135","https://openalex.org/W2170111110","https://openalex.org/W2194321275","https://openalex.org/W2196348858","https://openalex.org/W2327562811","https://openalex.org/W2399803916","https://openalex.org/W2403726878","https://openalex.org/W2420777250","https://openalex.org/W2574963492","https://openalex.org/W2606712314","https://openalex.org/W2765332150","https://openalex.org/W2775593698","https://openalex.org/W2784067649","https://openalex.org/W2788951710","https://openalex.org/W2788983691","https://openalex.org/W2807242871","https://openalex.org/W2807461489","https://openalex.org/W2897613819","https://openalex.org/W2903585023","https://openalex.org/W2911448865","https://openalex.org/W2952264928","https://openalex.org/W2956476286","https://openalex.org/W2962851448","https://openalex.org/W2962947707","https://openalex.org/W2963368172","https://openalex.org/W2963636093"],"related_works":["https://openalex.org/W2327562811","https://openalex.org/W2921490118","https://openalex.org/W7095628201","https://openalex.org/W2752144649","https://openalex.org/W6964972575","https://openalex.org/W149894577","https://openalex.org/W6888846000","https://openalex.org/W2094059388","https://openalex.org/W2910371331","https://openalex.org/W2807242871"],"abstract_inverted_index":{"The":[0,115],"recent":[1],"Attend-Infer-Repeat":[2],"(AIR)":[3],"framework":[4],"marks":[5],"a":[6,108,132,141],"milestone":[7],"in":[8,48,79,131],"structured":[9],"probabilistic":[10,93,105],"modeling,":[11],"as":[12],"it":[13,62],"tackles":[14],"the":[15,27,41,49,73,87,138,146],"challenging":[16],"problem":[17],"of":[18,29,43,77,111,123,140,148],"unsupcrviscd":[19],"scene":[20,150],"understanding":[21],"via":[22],"Baycsian":[23],"inference.":[24],"AIR":[25,80],"expresses":[26],"composition":[28],"visual":[30],"scenes":[31],"from":[32],"individual":[33],"objects,":[34],"and":[35,60,75,135],"uses":[36],"vari-ational":[37],"autoencoders":[38],"to":[39,64],"model":[40,51],"appearance":[42],"those":[44],"objects.":[45],"However,":[46],"inference":[47,113],"overall":[50],"is":[52],"highly":[53],"intractable,":[54],"which":[55],"hampers":[56],"its":[57],"learning":[58,78],"speed":[59,74],"makes":[61],"prone":[63],"suboptimal":[65],"solutions.":[66],"In":[67,95],"this":[68],"paper,":[69],"we":[70,97],"show":[71],"that":[72],"robustness":[76,147],"can":[81],"be":[82],"considerably":[83],"improved":[84],"by":[85],"replacing":[86],"intractable":[88],"object":[89,129],"representations":[90],"with":[91,107],"tractable":[92,112],"models.":[94],"particular,":[96],"opt":[98],"for":[99,137],"sum-product":[100],"networks":[101],"(SPNs),":[102],"expressive":[103],"deep":[104],"models":[106],"rich":[109],"set":[110],"routines.":[114],"resulting":[116],"model,":[117,144],"called":[118],"SuPAIR,":[119],"learns":[120],"an":[121],"order":[122],"magnitude":[124],"faster":[125],"than":[126],"AIR,":[127],"treats":[128],"occlusions":[130],"consistent":[133],"manner,":[134],"allows":[136],"inclusion":[139],"background":[142],"noise":[143],"improving":[145],"Bayesian":[149],"understanding.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-05-29T00:00:00"}