{"id":"https://openalex.org/W2341725658","doi":"https://doi.org/10.18653/v1/w16-3201","title":"Automatic Annotation of Structured Facts in Images","display_name":"Automatic Annotation of Structured Facts in Images","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2341725658","doi":"https://doi.org/10.18653/v1/w16-3201","mag":"2341725658"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-3201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3201","pdf_url":"https://www.aclweb.org/anthology/W16-3201.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 5th Workshop on Vision and Language","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-3201.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["Adobe Research","Department of Computer Science, Rutgers University","Rutgers, The State University of New Jersey, New Brunswick, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, The State University of New Jersey, New Brunswick, United States","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055156362","display_name":"Scott Cohen","orcid":"https://orcid.org/0000-0002-3459-6899"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Cohen","raw_affiliation_strings":["Adobe Research","Adobe Systems (United States), San Jose, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Systems (United States), San Jose, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103861221","display_name":"Walter Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walter Chang","raw_affiliation_strings":["Adobe Research","Adobe Systems (United States), San Jose, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Systems (United States), San Jose, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110699179","display_name":"Brian Price","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Price","raw_affiliation_strings":["Adobe Research","Adobe Systems (United States), San Jose, United States"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Systems (United States), San Jose, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039640321","display_name":"Ahmed Elgammal","orcid":"https://orcid.org/0000-0003-2761-4822"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Ahmed Elgammal","raw_affiliation_strings":["Department of Computer Science, Rutgers University","Rutgers, The State University of New Jersey, New Brunswick, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, The State University of New Jersey, New Brunswick, United States","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085089542"],"corresponding_institution_ids":["https://openalex.org/I102322142","https://openalex.org/I1306409833","https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":0.5079,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71377004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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":0.9919999837875366,"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":0.786565363407135},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7246183753013611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099698543548584},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5622591376304626},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47277072072029114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47059357166290283},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4585719704627991},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4496656656265259},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.41837361454963684},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4139629304409027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786565363407135},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7246183753013611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099698543548584},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5622591376304626},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47277072072029114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47059357166290283},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4585719704627991},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4496656656265259},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.41837361454963684},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4139629304409027}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w16-3201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3201","pdf_url":"https://www.aclweb.org/anthology/W16-3201.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 5th Workshop on Vision and Language","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1604.00466","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.00466","pdf_url":"https://arxiv.org/pdf/1604.00466","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2341725658","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1604.00466.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1604.00466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1604.00466","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-3201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3201","pdf_url":"https://www.aclweb.org/anthology/W16-3201.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 5th Workshop on Vision and Language","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2341725658.pdf","grobid_xml":"https://content.openalex.org/works/W2341725658.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1529731474","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1964763677","https://openalex.org/W2017814585","https://openalex.org/W2081580037","https://openalex.org/W2081613070","https://openalex.org/W2111488410","https://openalex.org/W2112912048","https://openalex.org/W2123442489","https://openalex.org/W2949218037","https://openalex.org/W2949844032","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2952246170","https://openalex.org/W2962706528"],"related_works":["https://openalex.org/W2962986624","https://openalex.org/W2555042572","https://openalex.org/W2182738494","https://openalex.org/W2081267504","https://openalex.org/W2794503900","https://openalex.org/W2614174454","https://openalex.org/W3202591229","https://openalex.org/W2527820373","https://openalex.org/W2964286668","https://openalex.org/W2924975873","https://openalex.org/W2547327680","https://openalex.org/W825973156","https://openalex.org/W2186088780","https://openalex.org/W2314891720","https://openalex.org/W3194873939","https://openalex.org/W2941968815","https://openalex.org/W2340038952","https://openalex.org/W2183463257","https://openalex.org/W3089797718","https://openalex.org/W14923517"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"the":[2,54,73,136],"application":[3],"of":[4,16,56,81,83,89,126],"fact-level":[5],"image":[6,64],"understanding,":[7],"we":[8],"present":[9],"an":[10,63],"automatic":[11],"method":[12,75,96],"for":[13],"data":[14,137],"collection":[15],"structured":[17,25],"visual":[18,84,102,110],"facts":[19,26,111],"from":[20,112],"images":[21,113,120],"with":[22,87,114],"captions.":[23],"Example":[24],"include":[27],"attributed":[28],"objects":[29],"(e.g.,":[30,34,38,45],"<flower,":[31],"red>),":[32],"actions":[33],"<baby,":[35],"smile>),":[36],"interactions":[37],"<man,":[39],"walking,":[40,60],"dog>),":[41],"and":[42,62,105,116],"positional":[43],"information":[44],"<vase,":[46],"on,":[47],"table>).":[48],"The":[49],"collected":[50,98],"annotations":[51,86,104],"are":[52],"in":[53,119,121],"form":[55],"fact-image":[57],"pairs":[58],"(e.g.,<man,":[59],"dog>":[61],"region":[65],"containing":[66],"this":[67],"fact).":[68],"With":[69],"a":[70],"language":[71],"approach,":[72],"proposed":[74],"is":[76],"able":[77],"to":[78,92],"collect":[79],"hundreds":[80],"thousands":[82],"fact":[85,103],"accuracy":[88],"83%":[90],"according":[91],"human":[93],"judgment.":[94],"Our":[95],"automatically":[97],"more":[99,106],"than":[100,107,123],"380,000":[101],"110,000":[108],"unique":[109],"captions":[115],"localized":[117],"them":[118],"less":[122],"one":[124],"day":[125],"processing":[127],"time":[128],"on":[129],"standard":[130],"CPU":[131],"platforms.":[132],"We":[133],"will":[134],"make":[135],"publically":[138],"available.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
