{"id":"https://openalex.org/W4417086740","doi":"https://doi.org/10.1109/wacv61042.2026.00310","title":"Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment","display_name":"Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417086740","doi":"https://doi.org/10.1109/wacv61042.2026.00310"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.04356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101827449","display_name":"Kai-Po Chang","orcid":"https://orcid.org/0009-0008-5182-2019"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Po Chang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109473821","display_name":"Wei-Yuan Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Yuan Cheng","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104259508","display_name":"Chi-Pin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Pin Huang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032964198","display_name":"Fu-En Yang","orcid":"https://orcid.org/0000-0003-0102-7101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu-En Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090045508","display_name":"Yu-Chiang Frank Wang","orcid":"https://orcid.org/0000-0002-2333-157X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.02732497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3172","last_page":"3181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6406999826431274,"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":0.6406999826431274,"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":0.14489999413490295,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0333000011742115,"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/object","display_name":"Object (grammar)","score":0.7529000043869019},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7497000098228455},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7321000099182129},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.6186000108718872},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7497000098228455},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7321000099182129},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068000197410583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590399980545044},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.435699999332428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2587999999523163}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.04356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.04356","pdf_url":"https://arxiv.org/pdf/2512.04356","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.04356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04356","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":"pmh:oai:arXiv.org:2512.04356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.04356","pdf_url":"https://arxiv.org/pdf/2512.04356","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancement":[1],"in":[2,25,103,145],"multimodal":[3],"LLMs":[4],"(MLLMs)":[5],"has":[6],"demonstrated":[7],"their":[8,131],"remarkable":[9],"capability":[10],"to":[11,96,111,122],"generate":[12],"descriptive":[13],"captions":[14,110],"for":[15,40,51,72],"input":[16],"videos.":[17],"However,":[18],"these":[19],"models":[20],"suffer":[21],"from":[22],"factual":[23],"inaccuracies":[24],"the":[26,80,85,98,104,108,112,124,155],"generated":[27],"descriptions,":[28],"causing":[29],"severe":[30],"hallucination":[31,156],"issues.":[32],"While":[33],"prior":[34],"works":[35],"have":[36],"explored":[37],"alleviating":[38,146],"hallucinations":[39,50,100],"static":[41],"images,":[42],"jointly":[43],"mitigating":[44],"visual":[45,88,133],"object":[46,74,147],"and":[47,57,75,83,106,127,134,148],"temporal":[48,135],"action":[49,76,149],"dynamic":[52],"videos":[53],"remains":[54],"a":[55,66,92,118],"challenging":[56],"unsolved":[58],"task.":[59],"To":[60],"tackle":[61],"this":[62],"challenge,":[63],"we":[64,116],"propose":[65],"Self-Augmented":[67],"Contrastive":[68],"Alignment":[69],"(SANTA)":[70],"framework":[71],"enabling":[73],"faithfulness":[77],"by":[78],"exempting":[79],"spurious":[81],"correlations":[82],"enforcing":[84],"emphasis":[86],"on":[87,154],"facts.":[89],"SANTA":[90,141],"employs":[91],"hallucinative":[93],"self-augmentation":[94],"scheme":[95],"identify":[97],"potential":[99],"that":[101,140],"lie":[102],"MLLM":[105],"transform":[107],"original":[109],"contrasted":[113],"negatives.":[114],"Furthermore,":[115],"develop":[117],"tracklet-phrase":[119],"contrastive":[120],"alignment":[121],"match":[123],"regional":[125],"objects":[126],"relation-guided":[128],"actions":[129],"with":[130],"corresponding":[132],"phrases.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"outperforms":[142],"existing":[143],"methods":[144],"hallucinations,":[150],"yielding":[151],"superior":[152],"performance":[153],"examination":[157],"benchmarks.":[158]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-06T00:00:00"}