{"id":"https://openalex.org/W2740126391","doi":"https://doi.org/10.18653/v1/w17-2002","title":"The Use of Object Labels and Spatial Prepositions as Keywords in a Web-Retrieval-Based Image Caption Generation System","display_name":"The Use of Object Labels and Spatial Prepositions as Keywords in a Web-Retrieval-Based Image Caption Generation System","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740126391","doi":"https://doi.org/10.18653/v1/w17-2002","mag":"2740126391"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2002","pdf_url":"https://www.aclweb.org/anthology/W17-2002.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002088191","display_name":"Brandon Birmingham","orcid":"https://orcid.org/0000-0002-3006-3526"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":true,"raw_author_name":"Brandon Birmingham","raw_affiliation_strings":["Communications & Computer Engineering University of Malta Msida MSD 2080, Malta"],"affiliations":[{"raw_affiliation_string":"Communications & Computer Engineering University of Malta Msida MSD 2080, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052348633","display_name":"Adrian Muscat","orcid":"https://orcid.org/0000-0002-9157-2818"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Adrian Muscat","raw_affiliation_strings":["Communications & Computer Engineering University of Malta Msida MSD 2080, Malta"],"affiliations":[{"raw_affiliation_string":"Communications & Computer Engineering University of Malta Msida MSD 2080, Malta","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002088191"],"corresponding_institution_ids":["https://openalex.org/I197854408"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09630977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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":0.8619833588600159},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7232510447502136},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6557031869888306},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5993944406509399},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5924068689346313},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.49802231788635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4977565109729767},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41270190477371216},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4124767780303955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3789123594760895},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2811332046985626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619833588600159},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7232510447502136},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6557031869888306},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5993944406509399},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5924068689346313},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.49802231788635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977565109729767},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41270190477371216},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4124767780303955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3789123594760895},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2811332046985626}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2002","pdf_url":"https://www.aclweb.org/anthology/W17-2002.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2002","pdf_url":"https://www.aclweb.org/anthology/W17-2002.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740126391.pdf","grobid_xml":"https://content.openalex.org/works/W2740126391.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W639708223","https://openalex.org/W825973156","https://openalex.org/W956551720","https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895989618","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2114841702","https://openalex.org/W2120101509","https://openalex.org/W2126384256","https://openalex.org/W2131179926","https://openalex.org/W2133459682","https://openalex.org/W2149557440","https://openalex.org/W2150824314","https://openalex.org/W2153579005","https://openalex.org/W2250842428","https://openalex.org/W2251174801","https://openalex.org/W2251848082","https://openalex.org/W2282219577","https://openalex.org/W2613718673","https://openalex.org/W2962835968","https://openalex.org/W3005285208","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W3211744874","https://openalex.org/W1994626569","https://openalex.org/W2368686738"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,68,95],"retrieval-based":[4],"caption":[5,63,69,109],"generation":[6,110],"system":[7,111],"that":[8,135],"searches":[9],"the":[10,39,42,51,62,79,83,103,108,115,130,136,153],"web":[11,26,36],"for":[12,29],"suitable":[13],"image":[14,159],"descriptions":[15,43],"is":[16,20,44,58,99,118],"studied.":[17],"Google's":[18],"search-by-image":[19],"used":[21,127],"to":[22,46,60,101,128],"find":[23],"potentially":[24],"relevant":[25],"multimedia":[27],"content":[28],"query":[30],"images.":[31],"Sentences":[32],"are":[33,88,126],"extracted":[34,147],"from":[35,50,148],"pages":[37],"and":[38,73,94,123,171],"likelihood":[40],"of":[41,71,78,168],"computed":[45],"select":[47],"one":[48],"sentence":[49],"retrieved":[52,131],"text":[53,81,117],"documents.":[54],"The":[55,85,105],"search":[56],"mechanism":[57],"modified":[59],"replace":[61],"generated":[64,116],"by":[65],"Google":[66],"with":[67,145,157,164],"composed":[70,167],"labels":[72,87,170],"spatial":[74],"prepositions":[75],"as":[76],"part":[77],"query's":[80],"alongside":[82],"image.":[84],"object":[86,169],"obtained":[89],"using":[90,114],"an":[91],"offthe-shelf":[92],"R-CNN":[93],"machine":[96],"learning":[97],"model":[98],"developed":[100],"predict":[102],"prepositions.":[104,172],"effect":[106],"on":[107],"performance":[112],"when":[113,141],"investigated.":[119],"Both":[120],"human":[121],"evaluations":[122],"automatic":[124],"metrics":[125],"evaluate":[129],"descriptions.":[132],"Results":[133],"show":[134],"web-retrieval-based":[137],"approach":[138],"performed":[139],"better":[140,162],"describing":[142],"single-object":[143],"images":[144,156],"sentences":[146,166],"stock":[149],"photography":[150],"websites.":[151],"On":[152],"other":[154],"hand,":[155],"two":[158],"objects":[160],"were":[161],"described":[163],"template-generated":[165]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}