{"id":"https://openalex.org/W2143449221","doi":"https://doi.org/10.18653/v1/d13-1128","title":"Image Description using Visual Dependency Representations","display_name":"Image Description using Visual Dependency Representations","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2143449221","doi":"https://doi.org/10.18653/v1/d13-1128","mag":"2143449221"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1128","pdf_url":"https://aclanthology.org/D13-1128.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1128.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010165733","display_name":"Desmond Elliott","orcid":"https://orcid.org/0000-0003-3112-7904"},"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":"Desmond Elliott","raw_affiliation_strings":["School of Informatics University of Edinburgh School of Informatics University of Edinburgh","School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh School of Informatics University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362"},"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":"Frank Keller","raw_affiliation_strings":["School of Informatics University of Edinburgh School of Informatics University of Edinburgh","School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh School of Informatics University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":294,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1292","last_page":"1302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"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":0.7885992527008057},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7269773483276367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7034370303153992},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6499477624893188},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6084586381912231},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5854235887527466},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5683495998382568},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5543684363365173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5090200901031494},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44456619024276733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4358504116535187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.371155321598053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885992527008057},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7269773483276367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7034370303153992},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6499477624893188},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6084586381912231},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5854235887527466},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5683495998382568},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5543684363365173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5090200901031494},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44456619024276733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4358504116535187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.371155321598053},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/d13-1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1128","pdf_url":"https://aclanthology.org/D13-1128.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","pdf_url":"https://www.research.ed.ac.uk/files/18911854/Elliott_Keller_2013_Image_Description_using_Visual_Dependency_Representations.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Elliott, D & Keller, F 2013, Image Description using Visual Dependency Representations. in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL. pp. 1292-1302. < http://aclweb.org/anthology/D/D13/D13-1128.pdf >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","pdf_url":"https://www.pure.ed.ac.uk/ws/files/18911854/Elliott_Keller_2013_Image_Description_using_Visual_Dependency_Representations.pdf","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":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/24d2468e-2dcc-4cd9-8808-a49dc8b62f17","pdf_url":"https://www.pure.ed.ac.uk/ws/files/18911854/Elliott_Keller_2013_Image_Description_using_Visual_Dependency_Representations.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Elliott, D & Keller, F 2013, Image Description using Visual Dependency Representations. in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL. pp. 1292-1302. < http://aclweb.org/anthology/D/D13/D13-1128.pdf >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.3878","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.3878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1128.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.686.1333","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.686.1333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/keller/publications/emnlp13a.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1128","pdf_url":"https://aclanthology.org/D13-1128.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143449221.pdf","grobid_xml":"https://content.openalex.org/works/W2143449221.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W1687846465","https://openalex.org/W1858383477","https://openalex.org/W1897761818","https://openalex.org/W2066134726","https://openalex.org/W2108325777","https://openalex.org/W2109586012","https://openalex.org/W2110764733","https://openalex.org/W2116410915","https://openalex.org/W2149172860","https://openalex.org/W2168356304","https://openalex.org/W2293778248"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2067317451","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2154771632","https://openalex.org/W2383687187","https://openalex.org/W4211085505","https://openalex.org/W1834370135"],"abstract_inverted_index":{"Describing":[0],"the":[1,9,14,47,50],"main":[2],"event":[3],"of":[4,25,72],"an":[5,53,95],"image":[6,62,96],"involves":[7],"identifying":[8],"objects":[10,51],"depicted":[11],"and":[12,55,80,121],"predicting":[13],"relationships":[15,35,48],"between":[16,36,49],"them.Previous":[17],"approaches":[18,105],"have":[19],"represented":[20],"images":[21],"as":[22],"unstructured":[23],"bags":[24],"regions,":[26],"which":[27],"makes":[28],"it":[29],"difficult":[30],"to":[31,45,114],"accurately":[32],"predict":[33],"meaningful":[34],"regions.In":[37],"this":[38,58,65],"paper,":[39],"we":[40,99],"introduce":[41],"visual":[42,77,92],"dependency":[43,78,93],"representations":[44,79],"capture":[46],"in":[52],"image,":[54],"hypothesize":[56],"that":[57,89,101,106],"representation":[59],"can":[60],"improve":[61],"description.We":[63],"test":[64],"hypothesis":[66],"using":[67],"a":[68],"new":[69],"data":[70],"set":[71],"region-annotated":[73],"images,":[74],"associated":[75],"with":[76],"gold-standard":[81],"descriptions.We":[82],"describe":[83],"two":[84],"template-based":[85],"description":[86,97],"generation":[87],"models":[88,103],"operate":[90],"over":[91],"representations.In":[94],"task,":[98],"find":[100],"these":[102],"outperform":[104],"rely":[107],"on":[108,117,122],"object":[109],"proximity":[110],"or":[111],"corpus":[112],"information":[113],"generate":[115],"descriptions":[116],"both":[118],"automatic":[119],"measures":[120],"human":[123],"judgements.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":37},{"year":2018,"cited_by_count":43},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
