{"id":"https://openalex.org/W2546190447","doi":"https://doi.org/10.1109/tpami.2017.2753232","title":"Cross-Modal Scene Networks","display_name":"Cross-Modal Scene Networks","publication_year":2017,"publication_date":"2017-09-18","ids":{"openalex":"https://openalex.org/W2546190447","doi":"https://doi.org/10.1109/tpami.2017.2753232","mag":"2546190447","pmid":"https://pubmed.ncbi.nlm.nih.gov/28922114"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2017.2753232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2753232","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/A5056410851","display_name":"Yusuf Aytar","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yusuf Aytar","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031988630","display_name":"Llu\u00eds Castrej\u00f3n","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lluis Castrejon","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103033393","display_name":"Carl Vondrick","orcid":"https://orcid.org/0000-0001-5676-2387"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Vondrick","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031860916","display_name":"Hamed Pirsiavash","orcid":"https://orcid.org/0000-0002-2528-3305"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Pirsiavash","raw_affiliation_strings":["University of Maryland Baltimore County, Baltimore, MD"],"affiliations":[{"raw_affiliation_string":"University of Maryland Baltimore County, Baltimore, MD","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio Torralba","orcid":"https://orcid.org/0000-0003-4915-0256"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056410851"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":5.6377,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":{"value":0.97524978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"40","issue":"10","first_page":"2303","last_page":"2314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9990000128746033,"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/modalities","display_name":"Modalities","score":0.8433282971382141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836910605430603},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8126053810119629},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.811582088470459},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7887815237045288},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.726458728313446},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6987122297286987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.633730411529541},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42064353823661804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36980748176574707}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8433282971382141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836910605430603},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8126053810119629},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.811582088470459},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7887815237045288},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.726458728313446},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6987122297286987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633730411529541},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42064353823661804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36980748176574707},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2017.2753232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2753232","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:28922114","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28922114","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":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W93016980","https://openalex.org/W848364640","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1722318740","https://openalex.org/W1732154880","https://openalex.org/W1852255964","https://openalex.org/W1892078565","https://openalex.org/W1899185266","https://openalex.org/W1934133592","https://openalex.org/W1982185844","https://openalex.org/W1982428585","https://openalex.org/W1996418862","https://openalex.org/W2017814585","https://openalex.org/W2031342017","https://openalex.org/W2100235303","https://openalex.org/W2102605133","https://openalex.org/W2104068492","https://openalex.org/W2106277773","https://openalex.org/W2107640784","https://openalex.org/W2115733720","https://openalex.org/W2115752676","https://openalex.org/W2123024445","https://openalex.org/W2124033848","https://openalex.org/W2125436662","https://openalex.org/W2128053425","https://openalex.org/W2134670479","https://openalex.org/W2144656844","https://openalex.org/W2145215286","https://openalex.org/W2150295085","https://openalex.org/W2153404544","https://openalex.org/W2155797815","https://openalex.org/W2155853132","https://openalex.org/W2155871590","https://openalex.org/W2155893237","https://openalex.org/W2159291411","https://openalex.org/W2163605009","https://openalex.org/W2171590421","https://openalex.org/W2184188583","https://openalex.org/W2187089797","https://openalex.org/W2210322478","https://openalex.org/W2214409633","https://openalex.org/W2296073425","https://openalex.org/W2962714319","https://openalex.org/W2964345931","https://openalex.org/W3143107425","https://openalex.org/W4293665662","https://openalex.org/W4294375521","https://openalex.org/W6603820874","https://openalex.org/W6624084161","https://openalex.org/W6629028937","https://openalex.org/W6630875275","https://openalex.org/W6631516269","https://openalex.org/W6637418260","https://openalex.org/W6637542466","https://openalex.org/W6639105354","https://openalex.org/W6639927594","https://openalex.org/W6640367237","https://openalex.org/W6645873477","https://openalex.org/W6677533783","https://openalex.org/W6678360021","https://openalex.org/W6678470764","https://openalex.org/W6679792166","https://openalex.org/W6681389334","https://openalex.org/W6682222085","https://openalex.org/W6682778277","https://openalex.org/W6682789604","https://openalex.org/W6683120131","https://openalex.org/W6683633756","https://openalex.org/W6684191040","https://openalex.org/W6686207219","https://openalex.org/W6687537536","https://openalex.org/W6729831399"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W2168054807"],"abstract_inverted_index":{"People":[0],"can":[1,41,91],"recognize":[2],"scenes":[3,43],"across":[4,24,53,95],"many":[5],"different":[6],"modalities":[7,96],"beyond":[8],"natural":[9],"images.":[10],"In":[11],"this":[12,28],"paper,":[13],"we":[14,30],"investigate":[15],"how":[16],"to":[17,65,112],"learn":[18,47],"cross-modal":[19,34,59,67],"scene":[20,35,89],"representations":[21,94],"that":[22,72,78,87,103,110],"transfer":[23,60,93],"modalities.":[25],"To":[26],"study":[27],"problem,":[29],"introduce":[31],"a":[32,75],"new":[33],"dataset.":[36],"While":[37],"convolutional":[38,68],"neural":[39,69],"networks":[40,70],"categorize":[42],"well,":[44],"they":[45,73],"also":[46],"an":[48],"intermediate":[49],"representation":[50,77,90,109],"not":[51],"aligned":[52],"modalities,":[54],"which":[55],"is":[56,79],"undesirable":[57],"for":[58,97],"applications.":[61],"We":[62],"present":[63],"methods":[64],"regularize":[66],"so":[71],"have":[74],"shared":[76,108],"agnostic":[80],"of":[81,118],"the":[82,107,119],"modality.":[83,120],"Our":[84],"experiments":[85],"suggest":[86,102],"our":[88,100],"help":[92],"retrieval.":[98],"Moreover,":[99],"visualizations":[101],"units":[104],"emerge":[105],"in":[106],"tend":[111],"activate":[113],"on":[114],"consistent":[115],"concepts":[116],"independently":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}