{"id":"https://openalex.org/W4375868765","doi":"https://doi.org/10.1109/icassp49357.2023.10095338","title":"End-to-End Non-Autoregressive Image Captioning","display_name":"End-to-End Non-Autoregressive Image Captioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868765","doi":"https://doi.org/10.1109/icassp49357.2023.10095338"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095338","doi":"https://doi.org/10.1109/icassp49357.2023.10095338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095338","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5102728606","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0003-4807-1812","observed_orcids":["https://orcid.org/0000-0003-4807-1812"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["Dalian University of Technology,School of Software","School of Software, Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067164185","display_name":"Yuanqiu Liu","orcid":"https://orcid.org/0009-0006-7676-2599","observed_orcids":["https://orcid.org/0009-0006-7676-2599"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqiu Liu","raw_affiliation_strings":["Dalian University of Technology,School of Software","School of Software, Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Baokun Qi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baokun Qi","raw_affiliation_strings":["Dalian University of Technology,School of Software","School of Software, Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008940823","display_name":"Zhao-Long Hu","orcid":"https://orcid.org/0000-0002-4548-8674","observed_orcids":["https://orcid.org/0000-0002-4548-8674"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaolong Hu","raw_affiliation_strings":["Dalian University of Technology,School of Software","School of Software, Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349041","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-3051-1990","observed_orcids":["https://orcid.org/0000-0002-3051-1990"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Dalian University of Technology,School of Software","School of Software, Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.7566,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80379369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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":0.9430000185966492},{"id":"https://openalex.org/keywords/non-autoregressive-decoding","display_name":"non-autoregressive decoding","score":0.9829999804496765},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.7889999747276306},{"id":"https://openalex.org/keywords/swin-transformer","display_name":"Swin Transformer","score":0.8019999861717224},{"id":"https://openalex.org/keywords/image-feature-extraction","display_name":"image feature extraction","score":0.8169999718666077},{"id":"https://openalex.org/keywords/inference-acceleration","display_name":"inference acceleration","score":0.8790000081062317}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9364278316497803},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.9095338582992554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880392074584961},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7003106474876404},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.602584719657898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539406418800354},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.48183929920196533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4080143868923187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4007093012332916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37344664335250854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26154470443725586},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.145661860704422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10917437076568604},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.10228413343429565}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095338","doi":"https://doi.org/10.1109/icassp49357.2023.10095338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095338","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2745461083","https://openalex.org/W2947912915","https://openalex.org/W2963736842","https://openalex.org/W2996677910","https://openalex.org/W3035284526","https://openalex.org/W3035463379","https://openalex.org/W3138516171","https://openalex.org/W3174046981","https://openalex.org/W3174377922","https://openalex.org/W3176587734","https://openalex.org/W3205981128","https://openalex.org/W3210150990","https://openalex.org/W4221147537"],"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/W2097707447"],"abstract_inverted_index":{"Most":[0],"of":[1,48,70,90,118],"the":[2,8,20,32,46,71,75,79,82,107,123],"existing":[3],"image":[4,62,95,101],"captioning":[5],"models":[6],"use":[7],"autoregressive":[9,83],"approach":[10],"to":[11,16,41,45,64,93],"generate":[12],"captions,":[13],"which":[14,29],"leads":[15,40],"high":[17],"latency":[18],"in":[19,27],"inference":[21,34,130],"process.":[22],"Non-autoregressive":[23],"decoding":[24,38],"generates":[25],"words":[26],"parallel,":[28],"greatly":[30],"improves":[31],"model":[33,113],"speed.":[35],"However,":[36],"non-autoregressive":[37,72,80],"usually":[39],"performance":[42,76],"loss":[43,47],"due":[44],"word":[49],"input.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,86],"propose":[55],"a":[56],"semantic":[57,66],"retrieval":[58],"module":[59],"that":[60,111],"uses":[61],"features":[63],"retrieve":[65],"information":[67],"as":[68],"input":[69],"decoder,":[73],"narrowing":[74],"gap":[77],"between":[78],"and":[81],"model.":[84,103],"Furthermore,":[85],"adopt":[87],"Swin-Transformer":[88],"instead":[89],"Faster":[91],"R-CNN":[92],"extract":[94],"features,":[96],"thus":[97],"building":[98],"an":[99],"end-to-end":[100],"caption":[102],"Experiments":[104],"conducted":[105],"on":[106,122],"MSCOCO":[108],"dataset":[109],"show":[110],"our":[112],"achieves":[114],"new":[115],"state-of-the-art":[116],"performances":[117],"122.6%":[119],"CIDEr":[120],"score":[121],"\u2019Karpathy\u2019":[124],"offline":[125],"test":[126],"split":[127],"with":[128],"37\u00d7":[129],"speedup.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}