{"id":"https://openalex.org/W2963267809","doi":"https://doi.org/10.1109/cvpr.2018.00896","title":"SemStyle: Learning to Generate Stylised Image Captions Using Unaligned Text","display_name":"SemStyle: Learning to Generate Stylised Image Captions Using Unaligned Text","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963267809","doi":"https://doi.org/10.1109/cvpr.2018.00896","mag":"2963267809"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"preprint","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/A5056294268","display_name":"A. P. Mathews","orcid":"https://orcid.org/0000-0002-7133-904X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Alexander Mathews","raw_affiliation_strings":["Australian National University, Canberra, ACT, AU"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, AU","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049449495","display_name":"Lexing Xie","orcid":"https://orcid.org/0000-0001-8319-0118"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lexing Xie","raw_affiliation_strings":["Australian National University, Canberra, ACT, AU"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, AU","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015970030","display_name":"Xuming He","orcid":"https://orcid.org/0000-0003-2150-1237"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming He","raw_affiliation_strings":["ShanghaiTech University"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056294268"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":8.1805,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.98175228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8591","last_page":"8600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9758999943733215,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9740999937057495,"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":0.8232877254486084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6807957291603088},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6286394000053406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5909006595611572},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5015039443969727},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47496840357780457},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43107494711875916},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4222145080566406},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4152463972568512},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3259214162826538},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16796529293060303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232877254486084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6807957291603088},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6286394000053406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909006595611572},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5015039443969727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47496840357780457},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43107494711875916},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4222145080566406},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4152463972568512},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3259214162826538},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16796529293060303},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2018.00896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/241634","is_oa":false,"landing_page_url":"https://openresearch-repository.anu.edu.au/bitstream/1885/241634/3/SemStyle_Learning_to_Generate_Stylised_Image_Captions_Using_Unaligned_Text.pdf.jpg","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1486649854","https://openalex.org/W1521626219","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1566289585","https://openalex.org/W1811254738","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1972820248","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2072828027","https://openalex.org/W2089159047","https://openalex.org/W2096472197","https://openalex.org/W2101105183","https://openalex.org/W2110485445","https://openalex.org/W2112796928","https://openalex.org/W2114030807","https://openalex.org/W2115792525","https://openalex.org/W2117539524","https://openalex.org/W2119595472","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133459682","https://openalex.org/W2139380585","https://openalex.org/W2141440284","https://openalex.org/W2145903624","https://openalex.org/W2157331557","https://openalex.org/W2160176417","https://openalex.org/W2173180041","https://openalex.org/W2183341477","https://openalex.org/W2250591306","https://openalex.org/W2250616809","https://openalex.org/W2251332263","https://openalex.org/W2294821440","https://openalex.org/W2329847998","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2525778437","https://openalex.org/W2550821151","https://openalex.org/W2552161745","https://openalex.org/W2560645892","https://openalex.org/W2561658355","https://openalex.org/W2563845258","https://openalex.org/W2625940279","https://openalex.org/W2949376505","https://openalex.org/W2949433733","https://openalex.org/W2962706528","https://openalex.org/W2962788902","https://openalex.org/W2963062932","https://openalex.org/W2963088515","https://openalex.org/W2963241138","https://openalex.org/W2963410018","https://openalex.org/W2963842982","https://openalex.org/W2963918688","https://openalex.org/W2964121744","https://openalex.org/W4250089123","https://openalex.org/W4254816979","https://openalex.org/W4300032027","https://openalex.org/W6621543089","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6679436768","https://openalex.org/W6680768788","https://openalex.org/W6685145238","https://openalex.org/W6687286152","https://openalex.org/W6691077208","https://openalex.org/W6691425247","https://openalex.org/W6725318829","https://openalex.org/W6898505805","https://openalex.org/W7058186782"],"related_works":["https://openalex.org/W4391150403","https://openalex.org/W2081749821","https://openalex.org/W1968572830","https://openalex.org/W2090814745","https://openalex.org/W2029896371","https://openalex.org/W2116246834","https://openalex.org/W4288263119","https://openalex.org/W3015724364","https://openalex.org/W2967994095","https://openalex.org/W4285240985"],"abstract_inverted_index":{"Linguistic":[0],"style":[1,152],"is":[2,90,99],"an":[3],"essential":[4],"part":[5],"of":[6,32,76,85,168],"written":[7],"communication,":[8],"with":[9,57,127],"the":[10,30,166,173],"power":[11],"to":[12,28,52,66,91,160],"affect":[13],"both":[14,38,137],"clarity":[15],"and":[16,23,41,94,102,113,131,139,150],"attractiveness.":[17],"With":[18],"recent":[19],"advances":[20],"in":[21],"vision":[22],"language,":[24],"we":[25,118],"can":[26],"start":[27],"tackle":[29],"problem":[31],"generating":[33],"image":[34,146,163],"captions":[35,50,56,71,142],"that":[36,64,124],"are":[37,148,151],"visually":[39,68],"grounded":[40],"appropriately":[42],"styled.":[43],"Existing":[44],"approaches":[45],"either":[46],"require":[47],"styled":[48,70,77],"training":[49],"aligned":[51,80],"images":[53],"or":[54],"generate":[55,67],"low":[58],"relevance.":[59],"We":[60],"develop":[61,119],"a":[62,73,100,120],"model":[63,123],"learns":[65],"relevant":[69],"from":[72,143,165],"large":[74],"corpus":[75],"text":[78],"without":[79],"images.":[81],"The":[82],"core":[83],"idea":[84],"this":[86,156],"model,":[87],"called":[88],"SemStyle,":[89],"separate":[92],"semantics":[93],"style.":[95],"One":[96],"key":[97],"component":[98],"novel":[101],"concise":[103],"semantic":[104],"term":[105],"representation":[106],"generated":[107],"using":[108],"natural":[109],"language":[110,122],"processing":[111],"techniques":[112],"frame":[114],"semantics.":[115],"In":[116],"addition,":[117],"unified":[121],"decodes":[125],"sentences":[126],"diverse":[128],"word":[129],"choices":[130],"syntax":[132],"for":[133],"different":[134],"styles.":[135],"Evaluations,":[136],"automatic":[138],"manual,":[140],"show":[141],"SemStyle":[144],"preserve":[145],"semantics,":[147],"descriptive,":[149],"shifted.":[153],"More":[154],"broadly,":[155],"work":[157],"provides":[158],"possibilities":[159],"learn":[161],"richer":[162],"descriptions":[164],"plethora":[167],"linguistic":[169],"data":[170],"available":[171],"on":[172],"web.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}