{"id":"https://openalex.org/W2953322005","doi":"https://doi.org/10.1017/s1351324918000098","title":"Where to put the image in an image caption generator","display_name":"Where to put the image in an image caption generator","publication_year":2018,"publication_date":"2018-04-23","ids":{"openalex":"https://openalex.org/W2953322005","doi":"https://doi.org/10.1017/s1351324918000098","mag":"2953322005"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324918000098","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000098","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.09137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"MARC TANTI","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"MARC TANTI","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"ALBERT GATT","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"ALBERT GATT","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"KENNETH P. CAMILLERI","orcid":"https://orcid.org/0000-0003-0436-6408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"KENNETH P. CAMILLERI","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8246,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.95400657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"24","issue":"3","first_page":"467","last_page":"489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9642999768257141,"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":0.9642999768257141,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0203000009059906,"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/T10028","display_name":"Topic Modeling","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/merge","display_name":"Merge (version control)","score":0.6761000156402588},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6610000133514404},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6403999924659729},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5493999719619751},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.52920001745224},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5120000243186951},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4618000090122223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44679999351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8980000019073486},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6761000156402588},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6610000133514404},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6403999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169999837875366},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324918000098","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000098","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:arXiv.org:1703.09137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.09137","pdf_url":"https://arxiv.org/pdf/1703.09137","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.09137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.09137","pdf_url":"https://arxiv.org/pdf/1703.09137","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1938708284","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2091812280","https://openalex.org/W2107019937","https://openalex.org/W2108325777","https://openalex.org/W2108598243","https://openalex.org/W2122180654","https://openalex.org/W2123301721","https://openalex.org/W2134831400","https://openalex.org/W2139380585","https://openalex.org/W2159243025","https://openalex.org/W2173180041","https://openalex.org/W2185175083","https://openalex.org/W2282219577","https://openalex.org/W2302086703","https://openalex.org/W2372035825","https://openalex.org/W2430258811","https://openalex.org/W2509740913","https://openalex.org/W2513874664","https://openalex.org/W2514012460","https://openalex.org/W2515338206","https://openalex.org/W2558533273","https://openalex.org/W2575842049","https://openalex.org/W6616026489","https://openalex.org/W6631943919","https://openalex.org/W6685230081","https://openalex.org/W6898505805"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"When":[1],"a":[2,44,163],"recurrent":[3],"neural":[4,22],"network":[5,23],"(RNN)":[6],"language":[7,35,52],"model":[8,36,53],"is":[9,67,84,93],"used":[10,94],"for":[11,132],"caption":[12,133],"generation,":[13],"the":[14,21,30,34,47,51,64,74,109,127,141,156],"image":[15,39,56],"information":[16],"can":[17],"be":[18,137,160],"fed":[19],"to":[20,88,114,120,162],"either":[24],"by":[25,37,54,106,118,140],"directly":[26],"incorporating":[27],"it":[28,83],"in":[29,43,63,116,153],"RNN":[31,48,142],"\u2013":[32,41,49],"conditioning":[33,50,105],"\u2018injecting\u2019":[38],"features":[40],"or":[42,95],"layer":[45],"following":[46],"\u2018merging\u2019":[55],"features.":[57],"While":[58],"both":[59],"options":[60],"are":[61],"attested":[62],"literature,":[65],"there":[66],"as":[68,104,143],"yet":[69],"no":[70],"systematic":[71],"comparison":[72],"between":[73],"two.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"empirically":[80],"show":[81],"that":[82,126,144],"not":[85,136],"especially":[86],"detrimental":[87],"performance":[89],"whether":[90],"one":[91],"architecture":[92,99],"another.":[96],"The":[97],"merge":[98],"does":[100],"have":[101],"practical":[102],"advantages,":[103],"merging":[107],"allows":[108],"RNN\u2019s":[110],"hidden":[111],"state":[112],"vector":[113],"shrink":[115],"size":[117],"up":[119],"four":[121],"times.":[122],"Our":[123],"results":[124],"suggest":[125],"visual":[128],"and":[129],"linguistic":[130],"modalities":[131],"generation":[134],"need":[135],"jointly":[138],"encoded":[139],"yields":[145],"large,":[146],"memory-intensive":[147],"models":[148],"with":[149],"few":[150],"tangible":[151],"advantages":[152],"performance;":[154],"rather,":[155],"multimodal":[157],"integration":[158],"should":[159],"delayed":[161],"subsequent":[164],"stage.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-06-27T00:00:00"}