{"id":"https://openalex.org/W2606845436","doi":"https://doi.org/10.1109/tpami.2017.2693987","title":"Learning Compositional Sparse Bimodal Models","display_name":"Learning Compositional Sparse Bimodal Models","publication_year":2017,"publication_date":"2017-04-12","ids":{"openalex":"https://openalex.org/W2606845436","doi":"https://doi.org/10.1109/tpami.2017.2693987","mag":"2606845436","pmid":"https://pubmed.ncbi.nlm.nih.gov/28422653"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2017.2693987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2693987","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5069769826","display_name":"Suren Kumar","orcid":"https://orcid.org/0000-0002-9706-2827"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suren Kumar","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI"],"raw_orcid":"https://orcid.org/0000-0002-9706-2827","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033777391","display_name":"Vikas Dhiman","orcid":"https://orcid.org/0000-0003-0078-3677"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikas Dhiman","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036212055","display_name":"Parker Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parker A Koch","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079301873","display_name":"Jason J. Corso","orcid":"https://orcid.org/0000-0001-6454-9594"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason J. Corso","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0924,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43953082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"40","issue":"5","first_page":"1032","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9950000047683716,"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/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.858824610710144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7981255054473877},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6568689346313477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.655445396900177},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5942698121070862},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5522397756576538},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.48039180040359497},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47180119156837463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44233137369155884},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4227233827114105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38469406962394714},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3747071623802185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12895655632019043}],"concepts":[{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.858824610710144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981255054473877},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6568689346313477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.655445396900177},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5942698121070862},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5522397756576538},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.48039180040359497},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47180119156837463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44233137369155884},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4227233827114105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38469406962394714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3747071623802185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12895655632019043},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2017.2693987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2693987","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:28422653","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28422653","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1290611643","display_name":null,"funder_award_id":"W911NF-15-1-0354","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332431","display_name":"College of Engineering, Michigan State University","ror":"https://ror.org/05hs6h993"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W81409850","https://openalex.org/W365491001","https://openalex.org/W1719717946","https://openalex.org/W1871180460","https://openalex.org/W1890834058","https://openalex.org/W1923162067","https://openalex.org/W1982428585","https://openalex.org/W1995820507","https://openalex.org/W2003938193","https://openalex.org/W2005876975","https://openalex.org/W2008340903","https://openalex.org/W2008732654","https://openalex.org/W2017399882","https://openalex.org/W2024254345","https://openalex.org/W2034295546","https://openalex.org/W2034455548","https://openalex.org/W2048530921","https://openalex.org/W2051688318","https://openalex.org/W2063978378","https://openalex.org/W2065180801","https://openalex.org/W2072529824","https://openalex.org/W2075606539","https://openalex.org/W2097892672","https://openalex.org/W2105464873","https://openalex.org/W2107917162","https://openalex.org/W2112447569","https://openalex.org/W2117115175","https://openalex.org/W2118099552","https://openalex.org/W2118781169","https://openalex.org/W2120824855","https://openalex.org/W2121058967","https://openalex.org/W2123987305","https://openalex.org/W2124807415","https://openalex.org/W2128532956","https://openalex.org/W2130399002","https://openalex.org/W2135046866","https://openalex.org/W2138615112","https://openalex.org/W2145743319","https://openalex.org/W2152984213","https://openalex.org/W2153915542","https://openalex.org/W2161969291","https://openalex.org/W2165644552","https://openalex.org/W2181691731","https://openalex.org/W2183759028","https://openalex.org/W2222512263","https://openalex.org/W2236233024","https://openalex.org/W2294130536","https://openalex.org/W2295002716","https://openalex.org/W2296399167","https://openalex.org/W2399832578","https://openalex.org/W2887159755","https://openalex.org/W2963811219","https://openalex.org/W3100316037","https://openalex.org/W4206310440","https://openalex.org/W4237938692","https://openalex.org/W4285719527","https://openalex.org/W4391218419","https://openalex.org/W6600593648","https://openalex.org/W6612358476","https://openalex.org/W6637727759","https://openalex.org/W6639239318","https://openalex.org/W6640071036","https://openalex.org/W6676727762","https://openalex.org/W6677419484","https://openalex.org/W6677564776","https://openalex.org/W6678025836","https://openalex.org/W6680970901","https://openalex.org/W6682983702","https://openalex.org/W6683167905","https://openalex.org/W6686282464","https://openalex.org/W6690047748","https://openalex.org/W6713210107","https://openalex.org/W7011438494"],"related_works":["https://openalex.org/W3095531775","https://openalex.org/W1526190050","https://openalex.org/W4251923961","https://openalex.org/W2477397717","https://openalex.org/W2010490241","https://openalex.org/W2500457737","https://openalex.org/W2020521331","https://openalex.org/W101162712","https://openalex.org/W4256618828","https://openalex.org/W2786691313"],"abstract_inverted_index":{"Various":[0],"perceptual":[1,58],"domains":[2,59],"have":[3,114,167],"underlying":[4],"compositional":[5,22,30,95,129,143],"semantics":[6],"that":[7,48,60],"are":[8],"rarely":[9],"captured":[10],"in":[11,39,145,182,195],"current":[12],"models.":[13,27],"We":[14],"suspect":[15],"this":[16,94],"is":[17,131,136,152],"because":[18],"directly":[19],"learning":[20],"the":[21,29,124,128,139,142,183,189],"structure":[23,31,122],"has":[24],"evaded":[25],"these":[26,82],"Yet,":[28],"of":[32,123,141,178,191],"a":[33,40,52,72,158,169],"given":[34],"domain":[35,42],"can":[36,87,101],"be":[37,102],"grounded":[38],"separate":[41],"thereby":[43],"simplifying":[44],"its":[45],"learning.":[46],"To":[47,162],"end,":[49],"we":[50,154,166],"propose":[51],"new":[53,170],"approach":[54],"to":[55,89],"modeling":[56,150],"bimodal":[57,73,171],"explicitly":[61,155,192],"relates":[62],"distinct":[63,83],"projections":[64,84,125],"across":[65,81],"each":[66],"modality":[67],"and":[68,85,107,118,126,175,198],"then":[69],"jointly":[70],"learns":[71],"sparse":[74],"representation.":[75],"The":[76,121],"resulting":[77],"model":[78,100],"enables":[79],"compositionality":[80,194],"hence":[86,127],"generalize":[88],"unobserved":[90],"percepts":[91],"spanned":[92],"by":[93],"basis.":[96],"For":[97],"example,":[98],"our":[99,149,164],"trained":[103],"on":[104,138,157],"red":[105,116],"triangles":[106],"blue":[108,119],"squares;":[109],"yet,":[110],"implicitly":[111],"will":[112],"also":[113],"learned":[115,132],"squares":[117],"triangles.":[120],"basis":[130],"automatically;":[133],"no":[134],"assumption":[135],"made":[137],"ordering":[140],"elements":[144],"either":[146],"modality.":[147],"Although":[148],"paradigm":[151],"general,":[153],"focus":[156],"tabletop":[159,184],"building-blocks":[160],"setting.":[161,185],"test":[163],"model,":[165],"acquired":[168],"dataset":[172],"comprising":[173],"images":[174],"spoken":[176],"utterances":[177],"colored":[179],"shapes":[180],"(blocks)":[181],"Our":[186],"experiments":[187],"demonstrate":[188],"benefits":[190],"leveraging":[193],"both":[196],"quantitative":[197],"human":[199],"evaluation":[200],"studies.":[201]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}