{"id":"https://openalex.org/W2794676802","doi":"https://doi.org/10.1017/s1351324918000104","title":"Understanding visual scenes","display_name":"Understanding visual scenes","publication_year":2018,"publication_date":"2018-03-28","ids":{"openalex":"https://openalex.org/W2794676802","doi":"https://doi.org/10.1017/s1351324918000104","mag":"2794676802"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324918000104","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000104","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/b51c6d44-373c-43d7-8f26-a0a15fd228c5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069341505","display_name":"Carina Silberer","orcid":"https://orcid.org/0000-0002-5047-1869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"CARINA SILBERER","raw_affiliation_strings":["DTCL, Universitat Pompeu Fabra, Roc Boronat 138, 08018 Barcelona, Spain e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DTCL, Universitat Pompeu Fabra, Roc Boronat 138, 08018 Barcelona, Spain e-mail:","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020938231","display_name":"Jasper Uijlings","orcid":"https://orcid.org/0000-0002-3288-7377"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"JASPER UIJLINGS","raw_affiliation_strings":["School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK e-mail:","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"MIRELLA LAPATA","raw_affiliation_strings":["ILCC, School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILCC, School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK e-mail:","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3121,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60115351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"3","first_page":"441","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9923999905586243,"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":0.8972716331481934},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6893607378005981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6284478902816772},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5820644497871399},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5654398202896118},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.535107433795929},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.530129611492157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5191552042961121},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4920472800731659},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41637295484542847},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41411516070365906},{"id":"https://openalex.org/keywords/tree-kernel","display_name":"Tree kernel","score":0.4118630588054657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.405487596988678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33698081970214844},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.22077181935310364},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10401749610900879}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8972716331481934},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6893607378005981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284478902816772},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5820644497871399},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5654398202896118},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.535107433795929},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.530129611492157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5191552042961121},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4920472800731659},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41637295484542847},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41411516070365906},{"id":"https://openalex.org/C140417398","wikidata":"https://www.wikidata.org/wiki/Q16933942","display_name":"Tree kernel","level":5,"score":0.4118630588054657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.405487596988678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33698081970214844},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.22077181935310364},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10401749610900879},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324918000104","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000104","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b51c6d44-373c-43d7-8f26-a0a15fd228c5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b51c6d44-373c-43d7-8f26-a0a15fd228c5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Silberer, C, Uijlings, J & Lapata, M 2018, 'Understanding visual scenes', Natural Language Engineering, vol. 24, no. 3, pp. 441\u2013465. https://doi.org/10.1017/S1351324918000104","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b51c6d44-373c-43d7-8f26-a0a15fd228c5","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/b51c6d44-373c-43d7-8f26-a0a15fd228c5","pdf_url":"https://www.research.ed.ac.uk/en/publications/b51c6d44-373c-43d7-8f26-a0a15fd228c5","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/b51c6d44-373c-43d7-8f26-a0a15fd228c5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b51c6d44-373c-43d7-8f26-a0a15fd228c5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Silberer, C, Uijlings, J & Lapata, M 2018, 'Understanding visual scenes', Natural Language Engineering, vol. 24, no. 3, pp. 441\u2013465. https://doi.org/10.1017/S1351324918000104","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W5598288","https://openalex.org/W8316075","https://openalex.org/W224064951","https://openalex.org/W1510052640","https://openalex.org/W1514535095","https://openalex.org/W1536680647","https://openalex.org/W1547225229","https://openalex.org/W1551928752","https://openalex.org/W1556531089","https://openalex.org/W1587871245","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1694858705","https://openalex.org/W1706899115","https://openalex.org/W1734113335","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1965680834","https://openalex.org/W1981636936","https://openalex.org/W2017927472","https://openalex.org/W2066134726","https://openalex.org/W2068676460","https://openalex.org/W2077069816","https://openalex.org/W2088049833","https://openalex.org/W2100751297","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2120814856","https://openalex.org/W2124225821","https://openalex.org/W2124807415","https://openalex.org/W2127713198","https://openalex.org/W2138304862","https://openalex.org/W2141362318","https://openalex.org/W2141440284","https://openalex.org/W2143449221","https://openalex.org/W2148809531","https://openalex.org/W2156985047","https://openalex.org/W2158847908","https://openalex.org/W2185175083","https://openalex.org/W2250378130","https://openalex.org/W2250379249","https://openalex.org/W2256253998","https://openalex.org/W2277195237","https://openalex.org/W2317752800","https://openalex.org/W2397198482","https://openalex.org/W2423576022","https://openalex.org/W2442626797","https://openalex.org/W2462848072","https://openalex.org/W2489434015","https://openalex.org/W2568262903","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2963311793","https://openalex.org/W3037785019","https://openalex.org/W6637665129","https://openalex.org/W6645883562","https://openalex.org/W6740017710","https://openalex.org/W6898505805","https://openalex.org/W6904025548"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"Abstract":[0],"A":[1],"growing":[2],"body":[3],"of":[4,12,18,38,60,80,128],"recent":[5],"work":[6],"focuses":[7],"on":[8,122],"the":[9,36,43,81,126,129],"challenging":[10],"problem":[11],"scene":[13],"understanding":[14],"using":[15],"a":[16],"variety":[17],"cross-modal":[19],"methods":[20,107],"which":[21],"fuse":[22],"techniques":[23],"from":[24],"image":[25,54,77,114],"and":[26,48,65,85,104,117],"text":[27],"processing.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,99],"develop":[33],"representations":[34,68],"for":[35,93,113],"semantics":[37],"scenes":[39],"by":[40],"explicitly":[41],"encoding":[42],"objects":[44],"detected":[45],"in":[46,108],"them":[47],"their":[49],"spatial":[50],"relations.":[51],"We":[52,96],"represent":[53],"content":[55],"via":[56],"two":[57],"well-known":[58],"types":[59],"tree":[61,105],"representations,":[62],"namely":[63],"constituents":[64],"dependencies.":[66],"Our":[67],"are":[69,86],"created":[70],"deterministically,":[71],"can":[72,100],"be":[73],"applied":[74],"to":[75,88,110],"any":[76],"dataset":[78],"irrespective":[79],"task":[82],"at":[83],"hand,":[84],"amenable":[87],"standard":[89],"NLP":[90],"tools":[91],"developed":[92],"tree-based":[94],"structures.":[95],"show":[97],"that":[98],"apply":[101],"syntax-based":[102],"SMT":[103],"kernel":[106],"order":[109],"build":[111],"models":[112],"description":[115],"generation":[116],"image-based":[118],"retrieval.":[119],"Experimental":[120],"results":[121],"real-world":[123],"images":[124],"demonstrate":[125],"effectiveness":[127],"framework.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}