{"id":"https://openalex.org/W2892087592","doi":"https://doi.org/10.18653/v1/d18-1437","title":"Object Hallucination in Image Captioning","display_name":"Object Hallucination in Image Captioning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2892087592","doi":"https://doi.org/10.18653/v1/d18-1437","mag":"2892087592"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1437","pdf_url":"https://www.aclweb.org/anthology/D18-1437.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1437.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037747070","display_name":"Anna Rohrbach","orcid":"https://orcid.org/0000-0003-1161-6006"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210086037","display_name":"Max Planck Innovation","ror":"https://ror.org/00d0v0049","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210086037"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Anna Rohrbach","raw_affiliation_strings":["UC Berkeley,","Max Planck Society, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"Max Planck Society, Munich, Germany","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210086037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020758501","display_name":"Lisa Anne Hendricks","orcid":"https://orcid.org/0000-0001-9340-5143"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Anne Hendricks","raw_affiliation_strings":["UC Berkeley,","University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074014720","display_name":"Kaylee Burns","orcid":"https://orcid.org/0000-0001-5713-2774"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaylee Burns","raw_affiliation_strings":["UC Berkeley,","University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["UC Berkeley,","University of California, Berkeley, Berkeley, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University","Boston University, Boston, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]},{"raw_affiliation_string":"Boston University, Boston, United States","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2169,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89130997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4035","last_page":"4045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9767000079154968,"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":0.9514999985694885,"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/hallucinating","display_name":"Hallucinating","score":0.9691027402877808},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8786087036132812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.674745500087738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6745249032974243},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5941776037216187},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5744642615318298},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5694460868835449},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5677802562713623},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5154898762702942},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5020897388458252},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.497452050447464},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47078651189804077},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.46526598930358887},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44188398122787476},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.4142162799835205},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39863619208335876},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39521944522857666},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.22148731350898743},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11520379781723022}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9691027402877808},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8786087036132812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.674745500087738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6745249032974243},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5941776037216187},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5744642615318298},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5694460868835449},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5677802562713623},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5154898762702942},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5020897388458252},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.497452050447464},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47078651189804077},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46526598930358887},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44188398122787476},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.4142162799835205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39863619208335876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39521944522857666},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.22148731350898743},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11520379781723022},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1437","pdf_url":"https://www.aclweb.org/anthology/D18-1437.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.02156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02156","pdf_url":"https://arxiv.org/pdf/1809.02156","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2892087592","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1809.02156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.02156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.02156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1437","pdf_url":"https://www.aclweb.org/anthology/D18-1437.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892087592.pdf","grobid_xml":"https://content.openalex.org/works/W2892087592.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2123301721","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2578190051","https://openalex.org/W2604178507","https://openalex.org/W2737766105","https://openalex.org/W2790600496","https://openalex.org/W2795151422","https://openalex.org/W2914699769","https://openalex.org/W2950178297","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2964042428"],"related_works":["https://openalex.org/W2962735233","https://openalex.org/W2101105183","https://openalex.org/W1956340063","https://openalex.org/W1895577753","https://openalex.org/W1514535095","https://openalex.org/W3202965415","https://openalex.org/W2745461083","https://openalex.org/W2506483933","https://openalex.org/W2277195237","https://openalex.org/W2194775991","https://openalex.org/W2154652894","https://openalex.org/W1889081078","https://openalex.org/W1861492603","https://openalex.org/W2963084599","https://openalex.org/W2953106684","https://openalex.org/W2626778328","https://openalex.org/W2123301721","https://openalex.org/W2064675550","https://openalex.org/W1522301498","https://openalex.org/W2607818926"],"abstract_inverted_index":{"Despite":[0],"continuously":[1],"improving":[2],"performance,":[3],"contemporary":[4],"image":[5,38,47,85,107],"captioning":[6,68,108],"models":[7,53,125,141],"are":[8,14],"prone":[9],"to":[10,29,50,75,84,146],"\"hallucinating\"":[11],"objects":[12],"that":[13,23,124,140],"not":[15,35,134],"actually":[16],"in":[17],"a":[18,45,112],"scene.":[19],"One":[20],"problem":[21],"is":[22,81],"standard":[24,106,130],"metrics":[25,96,132],"only":[26],"measure":[27],"similarity":[28],"ground":[30],"truth":[31],"captions":[32],"and":[33,58,71,90,139],"may":[34],"fully":[36],"capture":[37,97],"relevance.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"propose":[44],"new":[46],"relevance":[48],"metric":[49],"evaluate":[51],"current":[52,94],"with":[54],"veridical":[55],"visual":[56],"labels":[57],"assess":[59,91],"their":[60],"rate":[61],"of":[62,115],"object":[63,76,98],"hallucination.":[64,99],"We":[65,100],"analyze":[66],"how":[67,92],"model":[69],"architectures":[70],"learning":[72],"objectives":[73],"contribute":[74],"hallucination,":[77],"explore":[78],"when":[79],"hallucination":[80,138],"likely":[82],"due":[83],"misclassification":[86],"or":[87],"language":[88,151],"priors,":[89],"well":[93],"sentence":[95,131],"investigate":[101],"these":[102],"questions":[103],"on":[104,129],"the":[105],"benchmark,":[109],"MSCOCO,":[110],"using":[111],"diverse":[113],"set":[114],"models.":[116],"Our":[117],"analysis":[118],"yields":[119],"several":[120],"interesting":[121],"findings,":[122],"including":[123],"which":[126,142],"score":[127],"best":[128],"do":[133],"always":[135],"have":[136],"lower":[137],"hallucinate":[143],"more":[144],"tend":[145],"make":[147],"errors":[148],"driven":[149],"by":[150],"priors.":[152],"*":[153],"Denotes":[154],"equal":[155],"contribution.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}