{"id":"https://openalex.org/W2947912915","doi":"https://doi.org/10.48550/arxiv.1906.00717","title":"Masked Non-Autoregressive Image Captioning","display_name":"Masked Non-Autoregressive Image Captioning","publication_year":2019,"publication_date":"2019-06-03","ids":{"openalex":"https://openalex.org/W2947912915","doi":"https://doi.org/10.48550/arxiv.1906.00717","mag":"2947912915"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1906.00717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.00717","pdf_url":"https://arxiv.org/pdf/1906.00717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.00717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016259963","display_name":"Junlong Gao","orcid":"https://orcid.org/0000-0002-8734-1021","observed_orcids":["https://orcid.org/0000-0002-8734-1021"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Junlong","raw_affiliation_strings":["Peking University Shenzhen Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng, Xi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X","observed_orcids":["https://orcid.org/0000-0002-3583-959X","https://orcid.org/0000-0002-8944-6580","https://orcid.org/0009-0002-1271-2964"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wang, Shiqi","raw_affiliation_strings":["Department of Computer Science , City University of Hong Kong , Hong Kong","Institute of Digital Media , Peking University","Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , City University of Hong Kong , Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Institute of Digital Media , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050217287","display_name":"Xia Li","orcid":"https://orcid.org/0000-0002-5178-8059","observed_orcids":["https://orcid.org/0000-0002-5178-8059"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xia","raw_affiliation_strings":["Peking University Shenzhen Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385183","display_name":"Shanshe Wang","orcid":"https://orcid.org/0000-0002-7665-7434","observed_orcids":["https://orcid.org/0000-0002-7665-7434"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wang, Shanshe","raw_affiliation_strings":["Department of Computer Science , City University of Hong Kong , Hong Kong","Institute of Digital Media , Peking University","Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , City University of Hong Kong , Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Institute of Digital Media , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403","observed_orcids":["https://orcid.org/0000-0002-2731-5403"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Siwei","raw_affiliation_strings":["Institute of Digital Media , Peking University","Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Digital Media , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042721210","display_name":"Wen Gao","orcid":"https://orcid.org/0000-0001-9923-068X","observed_orcids":["https://orcid.org/0000-0001-9923-068X"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Wen","raw_affiliation_strings":["Institute of Digital Media , Peking University","Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Digital Media , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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":0.0008999999845400453,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0007999999797903001,"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/image-captioning","display_name":"image captioning","score":0.9210000038146973},{"id":"https://openalex.org/keywords/non-autoregressive-decoding","display_name":"non-autoregressive decoding","score":0.9860000014305115},{"id":"https://openalex.org/keywords/autoregressive-decoding","display_name":"autoregressive decoding","score":0.8489999771118164},{"id":"https://openalex.org/keywords/caption-diversity","display_name":"caption diversity","score":0.7580000162124634},{"id":"https://openalex.org/keywords/multimodality","display_name":"multimodality","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.9217066764831543},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8821561932563782},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8507429957389832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114737629890442},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7101917266845703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.533589243888855},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4818631112575531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4445810317993164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40511706471443176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448742628097534},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2400304675102234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1556956171989441},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1388089954853058},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1906.00717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.00717","pdf_url":"https://arxiv.org/pdf/1906.00717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.1906.00717","doi":"https://doi.org/10.48550/arxiv.1906.00717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.00717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.00717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.00717","pdf_url":"https://arxiv.org/pdf/1906.00717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1574901103","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2542835211","https://openalex.org/W2575842049","https://openalex.org/W2607768201","https://openalex.org/W2626778328","https://openalex.org/W2737766105","https://openalex.org/W2745461083","https://openalex.org/W2767206889","https://openalex.org/W2768401321","https://openalex.org/W2890550430","https://openalex.org/W2962968835","https://openalex.org/W2963341956"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4389471172"],"abstract_inverted_index":{"Existing":[0],"captioning":[1],"models":[2],"often":[3],"adopt":[4],"the":[5,9,25,68,72,85,105],"encoder-decoder":[6],"architecture,":[7],"where":[8],"decoder":[10],"uses":[11],"autoregressive":[12,30,89],"decoding":[13,31,49,82,90],"to":[14,53,67,83,122],"generate":[15,111,145],"captions,":[16],"such":[17,35],"that":[18],"each":[19],"token":[20],"is":[21],"generated":[22,27],"sequentially":[23],"given":[24],"preceding":[26],"tokens.":[28],"However,":[29],"results":[32],"in":[33,114,127],"issues":[34,86],"as":[36],"sequential":[37],"error":[38],"accumulation,":[39],"slow":[40,55],"generation,":[41],"improper":[42],"semantics":[43],"and":[44,91,110,143],"lack":[45],"of":[46,71,87,102,104],"diversity.":[47],"Non-autoregressive":[48],"has":[50],"been":[51],"proposed":[52,135],"tackle":[54,84],"generation":[56],"for":[57],"neural":[58],"machine":[59],"translation":[60],"but":[61],"suffers":[62],"from":[63,117],"multimodality":[64],"problem":[65],"due":[66],"indirect":[69],"modeling":[70],"target":[73],"distribution.":[74],"In":[75,94],"this":[76],"paper,":[77],"we":[78,98],"propose":[79],"masked":[80,95,120],"non-autoregressive":[81,92,96],"both":[88],"decoding.":[93],"decoding,":[97],"mask":[99],"several":[100,115],"kinds":[101],"ratios":[103],"input":[106],"sequences":[107],"during":[108,131],"training,":[109],"captions":[112],"parallelly":[113],"stages":[116],"a":[118,123,128],"totally":[119,124],"sequence":[121,126],"non-masked":[125],"compositional":[129],"manner":[130],"inference.":[132],"Experimentally":[133],"our":[134],"model":[136],"can":[137,144],"preserve":[138],"semantic":[139],"content":[140],"more":[141,146],"effectively":[142],"diverse":[147],"captions.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}