{"id":"https://openalex.org/W2791321184","doi":"https://doi.org/10.1017/s1351324918000116","title":"The role of image representations in vision to language tasks","display_name":"The role of image representations in vision to language tasks","publication_year":2018,"publication_date":"2018-03-21","ids":{"openalex":"https://openalex.org/W2791321184","doi":"https://doi.org/10.1017/s1351324918000116","mag":"2791321184"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324918000116","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000116","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055155740","display_name":"Pranava Madhyastha","orcid":"https://orcid.org/0000-0002-4438-8161"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"PRANAVA MADHYASTHA","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031749307","display_name":"Josiah Wang","orcid":"https://orcid.org/0000-0003-0048-3893"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"JOSIAH WANG","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053217291","display_name":"Lucia Specia","orcid":"https://orcid.org/0000-0002-5495-3128"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"LUCIA SPECIA","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello St., Sheffield S1 4DP, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055155740"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.3187,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60709886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"24","issue":"3","first_page":"415","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.991100013256073,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9847000241279602,"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/computer-science","display_name":"Computer science","score":0.8843060731887817},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8785848617553711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6403431296348572},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.624941349029541},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5919837951660156},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5883034467697144},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5670824646949768},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.53240567445755},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5314653515815735},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5217189192771912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4869481325149536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4633937478065491},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.441385418176651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8843060731887817},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8785848617553711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403431296348572},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.624941349029541},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5919837951660156},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5883034467697144},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5670824646949768},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.53240567445755},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5314653515815735},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5217189192771912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4869481325149536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4633937478065491},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.441385418176651},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324918000116","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000116","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:eprints.whiterose.ac.uk:129793","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/63807","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/63807","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"439","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W114341944","https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1687846465","https://openalex.org/W1749884237","https://openalex.org/W1783830328","https://openalex.org/W1858383477","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W2062118960","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2109586012","https://openalex.org/W2110485445","https://openalex.org/W2117539524","https://openalex.org/W2119775030","https://openalex.org/W2128856065","https://openalex.org/W2133459682","https://openalex.org/W2134670479","https://openalex.org/W2144715671","https://openalex.org/W2149172860","https://openalex.org/W2149557440","https://openalex.org/W2155541015","https://openalex.org/W2163605009","https://openalex.org/W2171361956","https://openalex.org/W2171928131","https://openalex.org/W2176412452","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2189070436","https://openalex.org/W2194775991","https://openalex.org/W2250379249","https://openalex.org/W2282219577","https://openalex.org/W2293344577","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2417549359","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2509282593","https://openalex.org/W2512381898","https://openalex.org/W2513263213","https://openalex.org/W2516756687","https://openalex.org/W2552161745","https://openalex.org/W2564590796","https://openalex.org/W2570343428","https://openalex.org/W2593341061","https://openalex.org/W2605714793","https://openalex.org/W2623411141","https://openalex.org/W2732026016","https://openalex.org/W2752172973","https://openalex.org/W2949447259","https://openalex.org/W2949888546","https://openalex.org/W2950133940","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2963331233","https://openalex.org/W2963344439","https://openalex.org/W2963565375","https://openalex.org/W2963881583","https://openalex.org/W2963909453","https://openalex.org/W2963988211","https://openalex.org/W2964018924","https://openalex.org/W2964258722","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Abstract":[0],"Tasks":[1],"that":[2,126],"require":[3],"modeling":[4,82],"of":[5,27,46,74,88,91,105,111],"both":[6],"language":[7,41,63,101],"and":[8,84,108,124,134],"visual":[9],"information,":[10],"such":[11],"as":[12],"image":[13,28,59,76,92,106],"captioning,":[14],"have":[15],"become":[16],"very":[17],"popular":[18,98],"in":[19,43,78],"recent":[20],"years.":[21],"Most":[22],"state-of-the-art":[23],"approaches":[24,128],"make":[25],"use":[26],"representations":[29,60],"obtained":[30],"from":[31],"a":[32,44,131],"deep":[33],"neural":[34,81],"network,":[35],"which":[36],"are":[37],"used":[38],"to":[39,62,100,138],"generate":[40,139],"information":[42],"variety":[45],"ways":[47],"with":[48],"end-to-end":[49,80,127],"neural-network-based":[50],"models.":[51],"However,":[52],"it":[53],"is":[54],"not":[55],"clear":[56],"how":[57],"different":[58,89],"contribute":[61],"generation":[64],"tasks.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"probe":[70],"the":[71,75,86,109,121,136],"representational":[72,122],"contribution":[73],"features":[77],"an":[79],"framework":[83],"study":[85],"properties":[87,123],"types":[90],"representations.":[93],"We":[94],"focus":[95],"on":[96],"two":[97],"vision":[99],"problems:":[102],"The":[103],"task":[104,110],"captioning":[107],"multimodal":[112],"machine":[113],"translation.":[114],"Our":[115],"analysis":[116],"provides":[117],"interesting":[118],"insights":[119],"into":[120],"suggests":[125],"implicitly":[129],"learn":[130],"visual-semantic":[132],"subspace":[133,137],"exploit":[135],"captions.":[140]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}