{"id":"https://openalex.org/W3034339250","doi":"https://doi.org/10.24963/ijcai.2020/92","title":"Human Consensus-Oriented Image Captioning","display_name":"Human Consensus-Oriented Image Captioning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034339250","doi":"https://doi.org/10.24963/ijcai.2020/92","mag":"3034339250"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/92","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/92","pdf_url":"https://www.ijcai.org/proceedings/2020/0092.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0092.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100389369","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0002-0107-7347"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["The University of Queensland, Australia","School of Information Technology and Electrical Engineering The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"School of Information Technology and Electrical Engineering The University of Queensland, Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["The University of Queensland, Australia","School of Information Technology and Electrical Engineering The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"School of Information Technology and Electrical Engineering The University of Queensland, Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063603492","display_name":"Yadan Luo","orcid":"https://orcid.org/0000-0001-6272-2971"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yadan Luo","raw_affiliation_strings":["The University of Queensland, Australia","School of Information Technology and Electrical Engineering The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"School of Information Technology and Electrical Engineering The University of Queensland, Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100389369"],"corresponding_institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":1.6609,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8629306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"659","last_page":"665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9962999820709229,"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":0.9947999715805054,"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":0.9558733701705933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8525363206863403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6331745982170105},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5761312246322632},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5435544848442078},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5310150980949402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5052571892738342},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4789726734161377},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4638630747795105},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4315783381462097},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4279630184173584},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35882753133773804}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9558733701705933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525363206863403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331745982170105},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5761312246322632},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5435544848442078},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5310150980949402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5052571892738342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4789726734161377},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4638630747795105},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4315783381462097},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4279630184173584},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35882753133773804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/92","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/92","pdf_url":"https://www.ijcai.org/proceedings/2020/0092.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/92","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/92","pdf_url":"https://www.ijcai.org/proceedings/2020/0092.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034339250.pdf","grobid_xml":"https://content.openalex.org/works/W3034339250.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2302086703","https://openalex.org/W2549599535","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2884561390","https://openalex.org/W2887712318","https://openalex.org/W2897964062","https://openalex.org/W2938603906","https://openalex.org/W2950018712","https://openalex.org/W2962861647","https://openalex.org/W2962958773","https://openalex.org/W2963084599","https://openalex.org/W2963349562","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2982210816","https://openalex.org/W3002761551","https://openalex.org/W3002949995","https://openalex.org/W4288329833","https://openalex.org/W4385245566"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Image":[0,164],"captioning":[1],"aims":[2],"to":[3,34,85,100,153],"describe":[4],"an":[5,17],"image":[6],"with":[7,28,44,105,122],"a":[8,29],"concise,":[9],"accurate,":[10],"and":[11,57,95,118,180],"interesting":[12],"sentence.":[13],"To":[14],"build":[15],"such":[16,48],"automatic":[18],"neural":[19],"captioner,":[20],"the":[21,25,39,62,69,74,87,98,109,115,140,145,154,168,177],"traditional":[22],"models":[23],"align":[24],"generated":[26],"words":[27],"number":[30],"of":[31,54,73,89,139],"human-annotated":[32],"sentences":[33],"mimic":[35],"human-like":[36],"captions.":[37],"However,":[38],"crowd-sourced":[40],"annotations":[41,70],"inevitably":[42],"come":[43],"data":[45,75],"quality":[46,88,103],"issues":[47],"as":[49],"grammatical":[50],"errors,":[51],"wrong":[52],"identification":[53],"visual":[55],"objects":[56],"sub-optimal":[58],"sentence":[59],"focus.":[60],"During":[61],"model":[63,99,181],"training,":[64],"existing":[65,141],"methods":[66],"treat":[67],"all":[68],"equally":[71],"regardless":[72],"quality.":[76],"In":[77],"this":[78],"work,":[79],"we":[80],"explicitly":[81],"engage":[82],"human":[83,170],"consensus":[84,132],"measure":[86],"ground":[90],"truth":[91],"captions":[92,104],"in":[93],"advance,":[94],"directly":[96],"encourage":[97],"learn":[101],"high":[102,106],"priority.":[107],"Therefore,":[108],"proposed":[110,169],"consensus-oriented":[111,171],"method":[112,173],"can":[113,134,174],"accelerate":[114],"training":[116,172,178],"process":[117],"achieve":[119],"superior":[120],"performance":[121,147],"only":[123],"supervised":[124],"objective":[125],"without":[126],"time-consuming":[127],"reinforcement":[128],"learning.":[129],"The":[130],"novel":[131],"loss":[133],"be":[135],"implemented":[136],"into":[137],"most":[138],"state-of-the-art":[142],"methods,":[143],"boosting":[144],"BLEU-4":[146],"by":[148],"maximum":[149],"relative":[150],"12.47%":[151],"comparing":[152],"conventional":[155],"cross-entropy":[156],"loss.":[157],"Extensive":[158],"experiments":[159],"are":[160],"conducted":[161],"on":[162],"MS-COCO":[163],"Captioning":[165],"dataset":[166],"demonstrating":[167],"significantly":[175],"improve":[176],"efficiency":[179],"effectiveness.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}