{"id":"https://openalex.org/W4408345984","doi":"https://doi.org/10.1109/icassp49660.2025.10890521","title":"Non-Autoregressive Image Captioning with Multi-Label Classification and Self-Critical Sequence Training","display_name":"Non-Autoregressive Image Captioning with Multi-Label Classification and Self-Critical Sequence Training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345984","doi":"https://doi.org/10.1109/icassp49660.2025.10890521"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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/A5067164185","display_name":"Yuanqiu Liu","orcid":"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,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003746498","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0003-0667-8413"},"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,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712362","display_name":"Hui Li","orcid":"https://orcid.org/0000-0002-3800-5435"},"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":"Hui Li","raw_affiliation_strings":["Dalian University of Technology,School of Software,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092276172","display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0009-0007-6723-1195"},"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":"Xiaotong Zhang","raw_affiliation_strings":["Dalian University of Technology,School of Software,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001008172","display_name":"Xin Han","orcid":"https://orcid.org/0000-0002-1694-7712"},"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":"Xin Han","raw_affiliation_strings":["Dalian University of Technology,School of Software,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448105","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-6618-1380"},"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,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software,Dalian,China","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9836000204086304,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9599999785423279,"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/closed-captioning","display_name":"Closed captioning","score":0.93104088306427},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7997264266014099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082476615905762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6289452910423279},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5820893049240112},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5776540637016296},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5360278487205505},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.49601778388023376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47725793719291687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42604219913482666},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16189149022102356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13297423720359802},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08096423745155334}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.93104088306427},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7997264266014099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082476615905762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6289452910423279},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5820893049240112},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5776540637016296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5360278487205505},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.49601778388023376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47725793719291687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42604219913482666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16189149022102356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13297423720359802},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08096423745155334},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336581","display_name":"Chunhui Project Foundation of the Education Department of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2952122856","https://openalex.org/W2963084599","https://openalex.org/W2963434219","https://openalex.org/W2963736842","https://openalex.org/W3035284526","https://openalex.org/W3035463379","https://openalex.org/W3093394956","https://openalex.org/W3174046981","https://openalex.org/W3176587734","https://openalex.org/W3205981128","https://openalex.org/W3210150990","https://openalex.org/W4293363567","https://openalex.org/W4312289196","https://openalex.org/W4312561350","https://openalex.org/W4313131769","https://openalex.org/W4375868765","https://openalex.org/W4382240730","https://openalex.org/W4385245566","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6746208923","https://openalex.org/W6763677924","https://openalex.org/W6771550610","https://openalex.org/W6784094891","https://openalex.org/W6792155083","https://openalex.org/W6838282907","https://openalex.org/W6858550665"],"related_works":["https://openalex.org/W2606910468","https://openalex.org/W3116827148","https://openalex.org/W3120843198","https://openalex.org/W2154965898","https://openalex.org/W2036704594","https://openalex.org/W4226315710","https://openalex.org/W3083782034","https://openalex.org/W4287185323","https://openalex.org/W2117809914","https://openalex.org/W2995801509"],"abstract_inverted_index":{"Most":[0],"current":[1],"image":[2,45,108,116],"captioning":[3,46,109,117],"models":[4,47,62,78],"rely":[5],"on":[6],"the":[7,41,58,106,115,127,135,161],"autoregressive":[8,44],"approach,":[9],"which":[10,68,124],"unfortunately":[11],"results":[12],"in":[13,57,177],"significant":[14],"inference":[15,31,178],"delays":[16],"that":[17,149,169],"hinder":[18],"their":[19],"practical":[20],"use.":[21],"In":[22,89,134],"contrast,":[23],"non-autoregressive":[24,42,77,107],"methods":[25],"show":[26,168],"promising":[27],"potential":[28],"for":[29,104,126,154],"increasing":[30],"speeds.":[32],"However,":[33],"there":[34],"is":[35],"often":[36],"a":[37,94,120,173],"performance":[38,176],"gap":[39],"between":[40],"and":[43,54,73,167,180],"due":[48],"to":[49,81,99,143],"issues":[50],"like":[51],"word":[52],"repetition":[53],"semantic":[55],"inconsistencies":[56],"generated":[59],"captions.":[60,75,133],"Autoregressive":[61],"benefit":[63,82],"from":[64,83],"self-critical":[65,101,155],"sequence":[66,102,156],"training,":[67],"helps":[69],"produce":[70],"more":[71],"coherent":[72],"fluid":[74],"While":[76],"are":[79],"difficult":[80],"as":[84,119,151],"they":[85],"predict":[86],"words":[87],"independently.":[88],"this":[90],"paper,":[91],"we":[92,138],"introduce":[93],"two-stage":[95],"training":[96,103],"strategy":[97],"designed":[98],"harness":[100],"enhancing":[105],"model.":[110],"Our":[111],"approach":[112],"initially":[113],"treats":[114],"task":[118],"multi-label":[121],"classification":[122],"problem,":[123],"allows":[125],"stable":[128],"production":[129],"of":[130,163],"multiple":[131],"candidate":[132,141],"second":[136],"stage,":[137],"employ":[139],"these":[140],"captions":[142],"compute":[144],"sequence-level":[145],"evaluation":[146],"metric":[147],"scores":[148,153],"serve":[150],"reward":[152],"training.":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"effectiveness":[162],"our":[164,170],"proposed":[165],"method":[166],"model":[171],"achieves":[172],"new":[174],"state-of-the-art":[175],"accuracy":[179],"speed.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}