{"id":"https://openalex.org/W2148985659","doi":null,"title":"Multiple Choice Learning: Learning to Produce Multiple Structured Outputs","display_name":"Multiple Choice Learning: Learning to Produce Multiple Structured Outputs","publication_year":2012,"publication_date":"2012-12-03","ids":{"openalex":"https://openalex.org/W2148985659","mag":"2148985659"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.5445","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.5445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/pkohli/papers/gbk_nips2012.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5079297608","display_name":"Abner Guzman-Rivera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abner Guzman-Rivera","raw_affiliation_strings":["University of Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011","observed_orcids":["https://orcid.org/0000-0002-1358-0011"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013834379","display_name":"Pushmeet Kohli","orcid":"https://orcid.org/0000-0002-7466-7997","observed_orcids":["https://orcid.org/0000-0002-7466-7997"]},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pushmeet Kohli","raw_affiliation_strings":["Microsoft Research Cambridge,#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-7466-7997","affiliations":[{"raw_affiliation_string":"Microsoft Research Cambridge,#TAB#","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0627,"has_fulltext":false,"cited_by_count":147,"citation_normalized_percentile":{"value":0.94128263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"1799","last_page":"1807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.5562000274658203,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.5562000274658203,"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":0.1949000060558319,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04749999940395355,"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/loss-function-design","display_name":"loss function design","score":0.6340000033378601},{"id":"https://openalex.org/keywords/cascaded-architecture","display_name":"cascaded architecture","score":0.7570000290870667},{"id":"https://openalex.org/keywords/user-interaction","display_name":"user interaction","score":0.6690000295639038},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"image segmentation","score":0.9900000095367432}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7453113198280334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089427709579468},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.6993771195411682},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.604539155960083},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5919619202613831},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.587810218334198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5535335540771484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492574572563171},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47588956356048584},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.4730597734451294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4657491147518158},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19458144903182983},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.09798875451087952},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09109547734260559},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.5445","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.5445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/pkohli/papers/gbk_nips2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.925.3401","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.925.3401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2012_0891.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.933.407","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.933.407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/4549-multiple-choice-learning-learning-to-produce-multiple-structured-outputs.pdf","raw_type":"text"},{"id":"mag:2148985659","doi":null,"is_oa":false,"landing_page_url":"http://abnerguzman.com/publications/gbk_nips12.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W179314280","https://openalex.org/W1525954826","https://openalex.org/W1722931978","https://openalex.org/W1846689784","https://openalex.org/W1964884769","https://openalex.org/W1984407615","https://openalex.org/W2015447696","https://openalex.org/W2031248101","https://openalex.org/W2037894654","https://openalex.org/W2097798120","https://openalex.org/W2099305880","https://openalex.org/W2100805904","https://openalex.org/W2101105183","https://openalex.org/W2101309634","https://openalex.org/W2105644991","https://openalex.org/W2105842272","https://openalex.org/W2118246710","https://openalex.org/W2121127625","https://openalex.org/W2121812207","https://openalex.org/W2124351162","https://openalex.org/W2143516773","https://openalex.org/W2147880316","https://openalex.org/W2160668810","https://openalex.org/W2161508606","https://openalex.org/W2164918853","https://openalex.org/W2167961180","https://openalex.org/W2169551590","https://openalex.org/W2186094539","https://openalex.org/W2601795100"],"related_works":["https://openalex.org/W2306187462","https://openalex.org/W7096218252","https://openalex.org/W2626446744","https://openalex.org/W2160668810","https://openalex.org/W7097087292","https://openalex.org/W2189749715","https://openalex.org/W3038553612","https://openalex.org/W2126564540","https://openalex.org/W2965864709","https://openalex.org/W7095784507"],"abstract_inverted_index":{"We":[0,104],"address":[1],"the":[2,34,38,42,99,102],"problem":[3,92],"of":[4,27,101,136],"generating":[5],"multiple":[6,28,81],"hypotheses":[7,71],"for":[8,51,133],"structured":[9],"prediction":[10,91,124,144],"tasks":[11],"that":[12,96,109,126],"involve":[13],"interaction":[14],"with":[15,93],"users":[16],"or":[17],"successive":[18],"components":[19],"in":[20,45,143],"a":[21,25,54,60,68,88,94,106],"cascaded":[22],"architecture.":[23],"Given":[24],"set":[26],"hypotheses,":[29],"such":[30,53],"components/users":[31],"typically":[32],"have":[33],"ability":[35],"to":[36,57,79,140],"retrieve":[37],"best":[39],"(or":[40],"approximately":[41],"best)":[43],"solution":[44],"this":[46,73,85,114,134],"set.":[47],"The":[48],"standard":[49],"approach":[50],"handling":[52],"scenario":[55,137],"is":[56],"first":[58],"learn":[59,78],"single-output":[61],"model":[62],"and":[63,121,138],"then":[64],"produce":[65,80],"M-Best":[66],"Maximum":[67],"Posteriori":[69],"(MAP)":[70],"from":[72],"model.":[74],"In":[75],"contrast,":[76],"we":[77],"outputs":[82],"by":[83],"formulating":[84],"task":[86],"as":[87],"multiple-output":[89],"structured-output":[90],"loss-function":[95],"effectively":[97],"captures":[98],"setup":[100],"problem.":[103],"present":[105],"max-margin":[107],"formulation":[108],"minimizes":[110],"an":[111],"upper-bound":[112],"on":[113,118],"lossfunction.":[115],"Experimental":[116],"results":[117],"image":[119],"segmentation":[120],"protein":[122],"side-chain":[123],"show":[125],"our":[127],"method":[128],"outperforms":[129],"conventional":[130],"approaches":[131],"used":[132],"type":[135],"leads":[139],"substantial":[141],"improvements":[142],"accuracy.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}