{"id":"https://openalex.org/W4413144618","doi":"https://doi.org/10.1109/cvpr52734.2025.01363","title":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models","display_name":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144618","doi":"https://doi.org/10.1109/cvpr52734.2025.01363"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101513992","display_name":"Hao Yin","orcid":"https://orcid.org/0000-0002-1543-9273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yin","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064686557","display_name":"Guoliang Si","orcid":"https://orcid.org/0000-0001-5809-3818"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gunagzong Si","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376572","display_name":"Zilei Wang","orcid":"https://orcid.org/0000-0003-1822-3731"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilei Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0702,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98674501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14625","last_page":"14634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9538000226020813,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9538000226020813,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.9023000001907349,"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/computer-science","display_name":"Computer science","score":0.6933234930038452},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5469872355461121},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5058269500732422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48900020122528076},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4700906276702881},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.45388537645339966},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3414115905761719},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16430306434631348},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08986786007881165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933234930038452},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5469872355461121},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5058269500732422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48900020122528076},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4700906276702881},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.45388537645339966},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3414115905761719},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16430306434631348},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08986786007881165},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4300000071525574,"display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2419430421","https://openalex.org/W2334811251","https://openalex.org/W2386464051","https://openalex.org/W32883749","https://openalex.org/W2308791691","https://openalex.org/W1972094787","https://openalex.org/W1971933602","https://openalex.org/W39816624","https://openalex.org/W2002427771","https://openalex.org/W2949208013"],"abstract_inverted_index":{"Contrastive":[0],"decoding":[1,40],"strategies":[2,23],"are":[3],"widely":[4],"used":[5],"to":[6,107],"mitigate":[7],"object":[8],"hallucinations":[9,143],"in":[10,31,156],"multimodal":[11],"large":[12],"language":[13,20,69,134],"models":[14],"(MLLMs).":[15],"By":[16],"reducing":[17,129],"over-reliance":[18],"on":[19],"priors,":[21],"these":[22,60,93],"ensure":[24],"that":[25,104,139],"generated":[26,77,157],"content":[27],"remains":[28],"closely":[29],"grounded":[30],"visual":[32,108,127],"inputs,":[33],"producing":[34],"contextually":[35],"accurate":[36],"outputs.":[37,158],"Since":[38],"contrastive":[39,82],"requires":[41],"no":[42],"additional":[43],"training":[44],"or":[45],"external":[46],"tools,":[47],"it":[48,56],"offers":[49],"both":[50],"computational":[51,85],"efficiency":[52],"and":[53,74,79,154],"versatility,":[54],"making":[55],"highly":[57],"attractive.":[58],"However,":[59],"methods":[61],"present":[62],"two":[63],"main":[64],"limitations:":[65],"(1)":[66],"bluntly":[67],"suppressing":[68],"priors":[70],"can":[71],"compromise":[72],"coherence":[73,153],"accuracy":[75,155],"of":[76,126],"content,":[78],"(2)":[80],"processing":[81],"inputs":[83],"adds":[84],"load,":[86],"significantly":[87,141],"slowing":[88],"inference":[89,149],"speed.":[90],"To":[91],"address":[92],"challenges,":[94],"we":[95],"propose":[96],"Visual":[97],"Amplification":[98],"Fusion":[99],"(VAF),":[100],"a":[101],"plug-and-play":[102],"technique":[103],"enhances":[105],"attention":[106],"signals":[109],"within":[110],"the":[111,130],"model\u2019s":[112,131],"middle":[113],"layers,":[114],"where":[115],"modality":[116],"fusion":[117],"predominantly":[118],"occurs.":[119],"This":[120],"approach":[121],"enables":[122],"more":[123],"effective":[124],"capture":[125],"features,":[128],"bias":[132],"toward":[133],"modality.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"VAF":[140],"reduces":[142],"across":[144],"various":[145],"MLLMs":[146],"without":[147],"affecting":[148],"speed,":[150],"while":[151],"maintaining":[152],"The":[159],"code":[160],"is":[161],"available":[162],"at":[163],"https://github.com/ustc-hyin/ClearSight.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}