{"id":"https://openalex.org/W7138059938","doi":"https://doi.org/10.1609/aaai.v40i7.37440","title":"DISCODE: Distribution-Aware Score Decoder for Robust Automatic Evaluation of Image Captioning","display_name":"DISCODE: Distribution-Aware Score Decoder for Robust Automatic Evaluation of Image Captioning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138059938","doi":"https://doi.org/10.1609/aaai.v40i7.37440"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37440","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37440","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i7.37440","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129680071","display_name":"Nakamasa Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035761466","display_name":"Kanoko Goto","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kanoko Goto","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120846919","display_name":"Masanari Oi","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Masanari Oi","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120846920","display_name":"Martyna Gruszka","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Martyna Gruszka","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113315313","display_name":"Mahiro Ukai","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Mahiro Ukai","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113319829","display_name":"Takumi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Takumi Hirose","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129741865","display_name":"Yusuke Sekikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I67530263","display_name":"Denso (United States)","ror":"https://ror.org/02w314k38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132650","https://openalex.org/I67530263"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Sekikawa","raw_affiliation_strings":["DENSO IT Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DENSO IT Laboratory","institution_ids":["https://openalex.org/I67530263"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2461366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5248","last_page":"5256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9927999973297119,"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":0.9927999973297119,"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":0.0013000000035390258,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0006000000284984708,"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/closed-captioning","display_name":"Closed captioning","score":0.8436999917030334},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8162999749183655},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4666999876499176},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4311999976634979},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.38109999895095825},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.34950000047683716}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8436999917030334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8162999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961000204086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759000182151794},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37440","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37440","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37440","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37440","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"have":[4],"shown":[5],"impressive":[6],"performance":[7,138],"across":[8,53,144],"a":[9,39,76,111,140],"broad":[10],"range":[11],"of":[12,126],"multimodal":[13],"tasks.":[14],"However,":[15],"robust":[16,45],"image":[17,113],"caption":[18],"evaluation":[19,46,66,84,115,127,142],"using":[20,95],"LVLMs":[21],"remains":[22],"challenging,":[23],"particularly":[24],"under":[25],"domain-shift":[26],"scenarios.":[27],"To":[28],"address":[29],"this":[30],"issue,":[31],"we":[32,100,103,132],"introduce":[33,104],"the":[34,70,105,124],"Distribution-Aware":[35],"Score":[36],"Decoder":[37],"(DISCODE),":[38],"novel":[40],"finetuning-free":[41],"method":[42],"that":[43,99,134],"generates":[44],"scores":[47],"better":[48],"aligned":[49],"with":[50],"human":[51],"judgments":[52],"diverse":[54],"domains.":[55],"The":[56],"core":[57],"idea":[58],"behind":[59],"DISCODE":[60,135],"lies":[61],"in":[62,83],"its":[63],"test-time":[64],"adaptive":[65],"approach,":[67],"which":[68],"introduces":[69],"Adaptive":[71],"Test-Time":[72],"(ATT)":[73],"loss,":[74],"leveraging":[75],"Gaussian":[77],"prior":[78],"distribution":[79],"to":[80,122],"improve":[81],"robustness":[82,125],"score":[85],"estimation.":[86],"This":[87],"loss":[88],"is":[89],"efficiently":[90],"minimized":[91],"at":[92],"test":[93],"time":[94],"an":[96],"analytical":[97],"solution":[98],"derive.":[101],"Furthermore,":[102],"Multi-domain":[106],"Caption":[107],"Evaluation":[108],"(MCEval)":[109],"benchmark,":[110],"new":[112],"captioning":[114],"benchmark":[116],"covering":[117],"six":[118],"distinct":[119],"domains,":[120],"designed":[121],"assess":[123],"metrics.":[128],"In":[129],"our":[130],"experiments,":[131],"demonstrate":[133],"achieves":[136],"state-of-the-art":[137],"as":[139],"reference-free":[141],"metric":[143],"MCEval":[145],"and":[146],"four":[147],"representative":[148],"existing":[149],"benchmarks.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}