{"id":"https://openalex.org/W2789474369","doi":"https://doi.org/10.1162/tacl_a_00010","title":"Learning Representations Specialized in Spatial Knowledge: Leveraging Language and Vision","display_name":"Learning Representations Specialized in Spatial Knowledge: Leveraging Language and Vision","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2789474369","doi":"https://doi.org/10.1162/tacl_a_00010","mag":"2789474369"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00010","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00010","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00010","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059014800","display_name":"Guillem Collell","orcid":"https://orcid.org/0000-0003-1998-8621"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Guillem Collell","raw_affiliation_strings":["Department of Computer Science, KU Leuven, 3001 Heverlee, Belgium,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, 3001 Heverlee, Belgium,","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075796989","display_name":"Marie\u2010Francine Moens","orcid":"https://orcid.org/0000-0002-3732-9323"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Marie-Francine Moens","raw_affiliation_strings":["Department of Computer Science, KU Leuven, 3001 Heverlee, Belgium,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, 3001 Heverlee, Belgium,","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059014800","https://openalex.org/A5075796989"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.6243,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.72859275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"133","last_page":"144"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9811999797821045,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9772999882698059,"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/computer-science","display_name":"Computer science","score":0.837376594543457},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7077383399009705},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6607570648193359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.621326208114624},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6182106733322144},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5940302014350891},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5781276822090149},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5767046809196472},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4836024343967438},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.446321964263916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43953168392181396},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10787239670753479},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06804385781288147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837376594543457},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7077383399009705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6607570648193359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621326208114624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6182106733322144},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5940302014350891},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5781276822090149},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5767046809196472},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4836024343967438},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.446321964263916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43953168392181396},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10787239670753479},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06804385781288147},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl_a_00010","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00010","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00010","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/602802","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/602802","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, vol. 6, (133-144)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:bbf169f2493f4031a5df0c4b9619844e","is_oa":false,"landing_page_url":"https://doaj.org/article/bbf169f2493f4031a5df0c4b9619844e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Transactions of the Association for Computational Linguistics, Vol 6 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00010","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00010","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00010","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6103890907","display_name":"MUltimodal processing of Spatial and TEmporal expRessions","funder_award_id":"ANR-15-CHR2-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2789474369.pdf","grobid_xml":"https://content.openalex.org/works/W2789474369.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1768359841","https://openalex.org/W1924121366","https://openalex.org/W1965202754","https://openalex.org/W1989436473","https://openalex.org/W2006354339","https://openalex.org/W2024271606","https://openalex.org/W2037227137","https://openalex.org/W2060491487","https://openalex.org/W2117539524","https://openalex.org/W2143449221","https://openalex.org/W2146062060","https://openalex.org/W2163490908","https://openalex.org/W2170682101","https://openalex.org/W2250539671","https://openalex.org/W2250742840","https://openalex.org/W2250879510","https://openalex.org/W2251507550","https://openalex.org/W2251874715","https://openalex.org/W2256323257","https://openalex.org/W2277195237","https://openalex.org/W2296613180","https://openalex.org/W2399799767","https://openalex.org/W2568389463","https://openalex.org/W2963173190","https://openalex.org/W2963655897","https://openalex.org/W4232356575"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W2044769131","https://openalex.org/W2520082489","https://openalex.org/W1751031993","https://openalex.org/W2362913948","https://openalex.org/W2116266067","https://openalex.org/W2364189591","https://openalex.org/W2028237718"],"abstract_inverted_index":{"Spatial":[0],"understanding":[1,200],"is":[2,80],"crucial":[3],"in":[4,27,39,73,118,130,169,204],"many":[5],"real-world":[6],"problems,":[7],"yet":[8],"little":[9],"progress":[10],"has":[11],"been":[12],"made":[13],"towards":[14,192],"building":[15,193],"representations":[16,33,116],"that":[17,60,69,78,145,162,180],"capture":[18],"spatial":[19,43,85,115,138,170,182,195,202],"knowledge.":[20],"Here,":[21],"we":[22,122,173],"move":[23],"one":[24],"step":[25],"forward":[26],"this":[28,74,187],"direction":[29],"and":[30,54,106,126,152,161],"learn":[31],"such":[32],"by":[34],"leveraging":[35],"a":[36,55,124,127,131],"task":[37,63,75,125],"consisting":[38,129],"predicting":[40,83],"continuous":[41],"2D":[42],"arrangements":[44,86,183],"of":[45,82,97,133,137,158,184,201],"objects":[46,89,99],"given":[47],"object-relationship-object":[48],"instances":[49],"(e.g.,":[50],"\u201ccat":[51],"under":[52],"chair\u201d)":[53],"simple":[56],"neural":[57,149],"network":[58],"model":[59,71,179],"learns":[61],"the":[62,70,98,114,119,178,190,199],"from":[64],"annotated":[65],"images.":[66],"We":[67,143],"show":[68],"succeeds":[72],"and,":[76],"furthermore,":[77],"it":[79],"capable":[81],"correct":[84],"for":[87,140],"unseen":[88],"if":[90,172],"either":[91],"CNN":[92,147],"features":[93,108,151],"or":[94],"word":[95,153],"embeddings":[96,154],"are":[100,109],"provided.":[101],"The":[102],"differences":[103],"between":[104],"visual":[105],"linguistic":[107],"discussed.":[110],"Next,":[111],"to":[112,198],"evaluate":[113],"learned":[117],"previous":[120],"task,":[121],"introduce":[123],"dataset":[128],"set":[132],"crowdsourced":[134],"human":[135,156],"ratings":[136],"similarity":[139,159],"object":[141],"pairs.":[142],"find":[144],"both":[146],"(convolutional":[148],"network)":[150],"predict":[155],"judgments":[157],"well":[160],"these":[163],"vectors":[164],"can":[165],"be":[166],"further":[167],"specialized":[168],"knowledge":[171],"update":[174],"them":[175],"when":[176],"training":[177],"predicts":[181],"objects.":[185],"Overall,":[186],"paper":[188],"paves":[189],"way":[191],"distributed":[194],"representations,":[196],"contributing":[197],"expressions":[203],"language.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}