{"id":"https://openalex.org/W2742182751","doi":"https://doi.org/10.18653/v1/w17-3506","title":"What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?","display_name":"What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2742182751","doi":"https://doi.org/10.18653/v1/w17-3506","mag":"2742182751"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-3506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3506","pdf_url":"https://www.aclweb.org/anthology/W17-3506.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 10th International Conference on Natural Language Generation","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/W17-3506.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048549686","display_name":"Marc Tanti","orcid":"https://orcid.org/0000-0002-7156-0596"},"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":"Marc Tanti","raw_affiliation_strings":["University of Malta, Imsida, Malta"],"affiliations":[{"raw_affiliation_string":"University of Malta, Imsida, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027041248","display_name":"Albert Gatt","orcid":"https://orcid.org/0000-0001-6388-8244"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Albert Gatt","raw_affiliation_strings":["University of Aberdeen, Aberdeen, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Aberdeen, Aberdeen, United Kingdom","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077265318","display_name":"Kenneth P. Camilleri","orcid":"https://orcid.org/0000-0003-0436-6408"},"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":"Kenneth Camilleri","raw_affiliation_strings":["University of Malta, Imsida, Malta"],"affiliations":[{"raw_affiliation_string":"University of Malta, Imsida, Malta","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048549686"],"corresponding_institution_ids":["https://openalex.org/I197854408"],"apc_list":null,"apc_paid":null,"fwci":0.3697,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.69062316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"60"},"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":0.9937000274658203,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9926000237464905,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.9303346872329712},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7788724303245544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7330523133277893},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6960002779960632},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6080085039138794},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6031103134155273},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5839635133743286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627779960632324},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5350284576416016},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5097536444664001},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45807337760925293},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43364790081977844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3509136438369751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32317084074020386},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3215043246746063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3043705224990845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15280184149742126},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11384803056716919},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.062321633100509644}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.9303346872329712},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7788724303245544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330523133277893},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6960002779960632},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6080085039138794},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6031103134155273},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5839635133743286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627779960632324},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5350284576416016},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5097536444664001},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45807337760925293},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43364790081977844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3509136438369751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32317084074020386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3215043246746063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3043705224990845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15280184149742126},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11384803056716919},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.062321633100509644},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":5,"locations":[{"id":"doi:10.18653/v1/w17-3506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3506","pdf_url":"https://www.aclweb.org/anthology/W17-3506.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 10th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.02043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.02043","pdf_url":"https://arxiv.org/pdf/1708.02043","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":null,"raw_type":"text"},{"id":"mag:2742182751","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.02043.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":"pmh:oai:www.um.edu.mt:123456789/22385","is_oa":true,"landing_page_url":"https://www.um.edu.mt/library/oar//handle/123456789/22385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400782","display_name":"OAR@UM (University of Malta)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I197854408","host_organization_name":"University of Malta","host_organization_lineage":["https://openalex.org/I197854408"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1708.02043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.02043","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/w17-3506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3506","pdf_url":"https://www.aclweb.org/anthology/W17-3506.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 10th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G3998201246","display_name":null,"funder_award_id":"Social","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"}],"funders":[{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2742182751.pdf","grobid_xml":"https://content.openalex.org/works/W2742182751.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W196214544","https://openalex.org/W956551720","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1645937837","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2038475577","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2109586012","https://openalex.org/W2123301721","https://openalex.org/W2143449221","https://openalex.org/W2149557440","https://openalex.org/W2159243025","https://openalex.org/W2171361956","https://openalex.org/W2173180041","https://openalex.org/W2407414618","https://openalex.org/W2430258811","https://openalex.org/W2515338206","https://openalex.org/W2558533273","https://openalex.org/W2919115771","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2951991713","https://openalex.org/W2952469094","https://openalex.org/W2953022248","https://openalex.org/W3037785019","https://openalex.org/W3105531629","https://openalex.org/W3110909889"],"related_works":["https://openalex.org/W3105531629","https://openalex.org/W2800737156","https://openalex.org/W3015437081","https://openalex.org/W3028109246","https://openalex.org/W3183698554","https://openalex.org/W2400801499","https://openalex.org/W2945223572","https://openalex.org/W3214477194","https://openalex.org/W3193497775","https://openalex.org/W2771570769","https://openalex.org/W3167712632","https://openalex.org/W3192161500","https://openalex.org/W2251503060","https://openalex.org/W2896034938","https://openalex.org/W2964189376","https://openalex.org/W3006155351","https://openalex.org/W2994155911","https://openalex.org/W2888338951","https://openalex.org/W3108682411","https://openalex.org/W2781602461"],"abstract_inverted_index":{"In":[0],"neural":[1,7],"image":[2,23,80],"captioning":[3],"systems,":[4],"a":[5,83],"recurrent":[6],"network":[8],"(RNN)":[9],"is":[10,32],"typically":[11],"viewed":[12,47,106],"as":[13,48,107],"the":[14,22,29,35,39,42,51,59,72,79],"primary":[15],"`generation'":[16],"component.":[17],"This":[18,31,55,86],"view":[19,37,56],"suggests":[20,57],"that":[21,58,70,102],"features":[24,68,81],"should":[25,61,75],"be":[26,46,63,76],"`injected'":[27],"into":[28],"RNN.":[30],"in":[33,38,95],"fact":[34],"dominant":[36],"literature.":[40],"Alternatively,":[41],"RNN":[43,60],"can":[44],"instead":[45],"only":[49,62,71],"encoding":[50],"previously":[52],"generated":[53],"words.":[54],"used":[64],"to":[65],"encode":[66],"linguistic":[67],"and":[69],"final":[73],"representation":[74],"`merged'":[77],"with":[78],"at":[82],"later":[84],"stage.":[85],"paper":[87],"compares":[88],"these":[89],"two":[90],"architectures.":[91],"We":[92],"find":[93],"that,":[94],"general,":[96],"late":[97],"merging":[98],"outperforms":[99],"injection,":[100],"suggesting":[101],"RNNs":[103],"are":[104],"better":[105],"encoders,":[108],"rather":[109],"than":[110],"generators.":[111]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}