{"id":"https://openalex.org/W7221344348","doi":"https://doi.org/10.1016/j.mex.2026.104199","title":"C4DF: confidence calibrated contextual control for diverse and faithful image captioning","display_name":"C4DF: confidence calibrated contextual control for diverse and faithful image captioning","publication_year":2026,"publication_date":"2026-10-10","ids":{"openalex":"https://openalex.org/W7221344348","doi":"https://doi.org/10.1016/j.mex.2026.104199","pmid":"https://pubmed.ncbi.nlm.nih.gov/42926827","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13694804"},"language":"en","primary_location":{"id":"doi:10.1016/j.mex.2026.104199","doi":"https://doi.org/10.1016/j.mex.2026.104199","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mex.2026.104199","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2215016126004152/pdf","source":{"id":"https://openalex.org/S2898269294","display_name":"MethodsX","issn_l":"2215-0161","issn":["2215-0161"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","norway-1","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MethodsX","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S2215016126004152/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015715655","display_name":"Sharmila Kharat","orcid":"https://orcid.org/0000-0001-9876-8066","observed_orcids":["https://orcid.org/0000-0001-9876-8066"]},"institutions":[{"id":"https://openalex.org/I4387152970","display_name":"MIT Academy of Engineering","ror":"https://ror.org/05sjf8653","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387152970"]},{"id":"https://openalex.org/I878213199","display_name":"Savitribai Phule Pune University","ror":"https://ror.org/044g6d731","country_code":"IN","type":"education","lineage":["https://openalex.org/I878213199"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sharmila Kharat","raw_affiliation_strings":["Department of Computer Engineering, MIT Academy of Engineering, Affiliated to Savitribai Phule Pune University, Pune, India"],"raw_orcid":"https://orcid.org/0000-0001-9876-8066","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, MIT Academy of Engineering, Affiliated to Savitribai Phule Pune University, Pune, India","institution_ids":["https://openalex.org/I4387152970","https://openalex.org/I878213199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050409454","display_name":"Sunita Barve","orcid":"https://orcid.org/0000-0002-5679-6744","observed_orcids":["https://orcid.org/0000-0002-5679-6744"]},"institutions":[{"id":"https://openalex.org/I4387152970","display_name":"MIT Academy of Engineering","ror":"https://ror.org/05sjf8653","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387152970"]},{"id":"https://openalex.org/I878213199","display_name":"Savitribai Phule Pune University","ror":"https://ror.org/044g6d731","country_code":"IN","type":"education","lineage":["https://openalex.org/I878213199"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Barve","raw_affiliation_strings":["Department of Computer Engineering, MIT Academy of Engineering, Affiliated to Savitribai Phule Pune University, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, MIT Academy of Engineering, Affiliated to Savitribai Phule Pune University, Pune, India","institution_ids":["https://openalex.org/I4387152970","https://openalex.org/I878213199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015715655"],"corresponding_institution_ids":["https://openalex.org/I4387152970","https://openalex.org/I878213199"],"apc_list":{"value":1260,"currency":"USD","value_usd":1260},"apc_paid":{"value":1260,"currency":"USD","value_usd":1260},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6958965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"104199","last_page":"104199"},"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/caption-diversity","display_name":"caption diversity","score":0.8579999804496765},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.7850000262260437},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.9440000057220459}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.955299973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711000204086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5824999809265137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27959999442100525}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.mex.2026.104199","doi":"https://doi.org/10.1016/j.mex.2026.104199","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mex.2026.104199","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2215016126004152/pdf","source":{"id":"https://openalex.org/S2898269294","display_name":"MethodsX","issn_l":"2215-0161","issn":["2215-0161"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","norway-1","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MethodsX","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13694804","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13694804/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13694804/pdf/main.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MethodsX","raw_type":"Text"},{"id":"pmid:42926827","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42926827","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MethodsX","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:6181e289873646728620e058a4e6bc58","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/6181e289873646728620e058a4e6bc58","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MethodsX, Vol 17, Iss , Pp 104199- (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.mex.2026.104199","doi":"https://doi.org/10.1016/j.mex.2026.104199","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mex.2026.104199","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2215016126004152/pdf","source":{"id":"https://openalex.org/S2898269294","display_name":"MethodsX","issn_l":"2215-0161","issn":["2215-0161"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","norway-1","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MethodsX","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221344348.pdf","grobid_xml":"https://content.openalex.org/works/W7221344348.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2463955103","https://openalex.org/W2896348597","https://openalex.org/W4220798700"],"related_works":["https://openalex.org/W3007120620","https://openalex.org/W3047153790","https://openalex.org/W2893724244","https://openalex.org/W7131824506","https://openalex.org/W2954841306","https://openalex.org/W4366758555","https://openalex.org/W3097062010","https://openalex.org/W4413927382","https://openalex.org/W4410859483","https://openalex.org/W4407825355"],"abstract_inverted_index":{"Image":[0,47],"captioning":[1],"models":[2],"generate":[3,25],"coherent":[4],"descriptions":[5],"that":[6,22,53],"are":[7,17],"linguistically":[8],"fluent.":[9],"Because":[10],"of":[11],"similarity-based":[12],"training":[13],"objectives,":[14],"generated":[15],"captions":[16],"repetitive.":[18],"In":[19],"most":[20],"techniques":[21],"aim":[23],"to":[24,33,96],"diverse,":[26],"human-like":[27],"captions,":[28],"strong":[29],"language":[30],"priors":[31],"lead":[32],"visually":[34],"unsupported":[35],"entities.":[36],"This":[37],"paper":[38],"proposes":[39],"Confidence-Calibrated":[40],"Contextual":[41],"Control":[42],"for":[43],"Diverse":[44],"and":[45,60,113],"Faithful":[46],"Captions":[48],"(C4DF),":[49],"a":[50],"decoding-time":[51],"framework":[52],"reduces":[54],"hallucinated":[55],"objects":[56],"while":[57,76,98],"maintaining":[58],"diversity":[59,112],"fluency.":[61,119],"Image-specific":[62],"pseudo-context":[63],"adaptively":[64],"suppresses":[65],"tokens":[66],"guided":[67],"by":[68,104],"confidence":[69],"calibration.":[70],"Prefix":[71],"token":[72,78],"conditioning":[73],"controls":[74],"diversity,":[75],"confidence-calibrated":[77],"suppression":[79],"during":[80],"decoding":[81],"improves":[82],"grounding.":[83],"Experiments":[84],"on":[85,117],"the":[86,100],"benchmark":[87],"dataset":[88],"demonstrate":[89],"an":[90],"improvement":[91],"in":[92],"CIDEr":[93],"from":[94],"46.96":[95],"51.69":[97],"reducing":[99],"noun":[101],"non-context":[102],"rate":[103],"9.48%.":[105],"Qualitative":[106],"analysis":[107],"confirms":[108],"this":[109],"balance":[110],"between":[111],"faithfulness":[114],"without":[115],"compromising":[116],"linguistic":[118]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-11T00:00:00"}