{"id":"https://openalex.org/W4415537764","doi":"https://doi.org/10.1145/3746027.3755320","title":"Collaboration Wins More: Dual-Modal Collaborative Attention Reinforcement for Mitigating Large Vision Language Models Hallucination","display_name":"Collaboration Wins More: Dual-Modal Collaborative Attention Reinforcement for Mitigating Large Vision Language Models Hallucination","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537764","doi":"https://doi.org/10.1145/3746027.3755320"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112928183","display_name":"Jiye Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiye Xie","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and vivo AI Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-5606-1091","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and vivo AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804187","display_name":"Yifei Gao","orcid":"https://orcid.org/0009-0006-0436-5930"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Gao","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0006-0436-5930","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112788668","display_name":"L. H. You","orcid":null},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangliang You","raw_affiliation_strings":["North China Electric Power University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8900-5313","affiliations":[{"raw_affiliation_string":"North China Electric Power University, Beijing, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044478867","display_name":"Xiang Xu","orcid":"https://orcid.org/0000-0002-0626-7609"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0626-7609","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoran Xu","orcid":"https://orcid.org/0000-0003-2091-6158"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2091-6158","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089186967","display_name":"Zhiqiang Kou","orcid":"https://orcid.org/0000-0002-3335-3959"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Kou","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3335-3959","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006567056","display_name":"Kexue Fu","orcid":"https://orcid.org/0000-0003-1204-0942"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexue Fu","raw_affiliation_strings":["Qilu University of Technology, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-1204-0942","affiliations":[{"raw_affiliation_string":"Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040772796","display_name":"Youyang Qu","orcid":"https://orcid.org/0000-0002-2944-4647"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyang Qu","raw_affiliation_strings":["Qilu University of Technology, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-2944-4647","affiliations":[{"raw_affiliation_string":"Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736643","display_name":"Wenjie Yang","orcid":"https://orcid.org/0000-0001-7483-1817"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Yang","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7483-1817","affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016717473","display_name":"Jianwei Guo","orcid":"https://orcid.org/0000-0002-3376-1725"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Guo","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3376-1725","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112127114","display_name":"Weiliang Meng","orcid":"https://orcid.org/0000-0002-3221-4981"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiliang Meng","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3221-4981","affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012293028","display_name":"Longxiang Gao","orcid":"https://orcid.org/0000-0002-3026-7537"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longxiang Gao","raw_affiliation_strings":["Qilu University of Technology, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-3026-7537","affiliations":[{"raw_affiliation_string":"Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029111448","display_name":"Haoran Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Yang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7612-2122","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020628396","display_name":"Changwei Wang","orcid":"https://orcid.org/0000-0001-8259-7717"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changwei Wang","raw_affiliation_strings":["Qilu University of Technology, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8259-7717","affiliations":[{"raw_affiliation_string":"Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433786","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0008-6938-204X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-6938-204X","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5112928183"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90273578,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4137","last_page":"4146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9936000108718872,"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":0.9936000108718872,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9878000020980835,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9563000202178955,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.48089998960494995},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4426000118255615},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.40849998593330383},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.367900013923645},{"id":"https://openalex.org/keywords/joint-attention","display_name":"Joint attention","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6051999926567078},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4496999979019165},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4426000118255615},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4000999927520752},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3885999917984009},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32120001316070557},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6075121767","display_name":null,"funder_award_id":"No.2022ZD0116800","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2962735233","https://openalex.org/W4401362547","https://openalex.org/W4402670231","https://openalex.org/W4402670859","https://openalex.org/W4402683883","https://openalex.org/W4402726948","https://openalex.org/W4402727851","https://openalex.org/W4402754134","https://openalex.org/W4404781537","https://openalex.org/W4405596328"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8,27,120,159,168],"visual-language":[9],"understanding":[10],"for":[11],"downstream":[12],"multimodal":[13,102],"tasks.":[14],"However,":[15],"these":[16,112],"models":[17],"often":[18],"generate":[19],"descriptions":[20],"containing":[21],"objects":[22],"or":[23],"details":[24],"not":[25],"present":[26],"the":[28,101,108,140,169],"input":[29],"image,":[30],"a":[31],"phenomenon":[32],"commonly":[33],"referred":[34],"to":[35,63],"as":[36],"''hallucination''.":[37],"Existing":[38],"methods":[39],"focus":[40],"solely":[41],"on":[42,139],"single-side":[43],"hallucination":[44,144],"mitigation:":[45],"Intra-modal-only":[46],"reinforcement":[47],"(e.g.":[48],"visual":[49,61,91,113,125,133],"attention":[50,109,129],"enhancement)":[51],"ignores":[52],"prompt-based":[53],"guidance;":[54],"Inter-modal-only":[55],"correlation":[56],"correction":[57],"may":[58],"introduce":[59],"low-information":[60],"tokens":[62,92],"mislead":[64],"reasoning.":[65],"To":[66],"tackle":[67],"this":[68],"challenge,":[69],"we":[70],"propose":[71],"Dual-Modal":[72],"Collaborative":[73],"Attention":[74],"Reinforcement":[75],"(DuCAR).":[76],"Specifically,":[77],"DuCAR":[78,105,121],"is":[79,166],"equipped":[80],"with":[81],"intra-visual":[82],"CLS-driven":[83],"sampling":[84,116],"and":[85,96,117,127,142,155],"cross-modal":[86],"dynamic":[87],"sampling,":[88],"extracting":[89],"important":[90],"guided":[93],"by":[94,162],"intra-":[95],"inter-modal":[97],"joint":[98],"information.":[99,134],"During":[100],"fusion":[103],"stage,":[104],"adaptively":[106],"enhances":[107],"weights":[110],"of":[111],"tokens.":[114],"Our":[115],"enhancement":[118],"strategies":[119],"simultaneously":[122],"reinforces":[123],"informative":[124],"tokens,":[126],"suppresses":[128],"dispersion":[130],"towards":[131],"question-irrelevant":[132],"We":[135],"conduct":[136],"extensive":[137],"experiments":[138],"POPE":[141],"CHAIR":[143],"benchmarks,":[145],"demonstrating":[146],"that":[147],"our":[148],"method":[149],"outperforms":[150],"existing":[151],"state-of-the-art":[152],"mitigation":[153],"baselines":[154],"effectively":[156],"reduces":[157],"hallucinations":[158],"text":[160],"generated":[161],"LVLMs.":[163],"The":[164],"code":[165],"available":[167],"https://github.com/xjy2020/DuCAR.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}