{"id":"https://openalex.org/W4415707815","doi":"https://doi.org/10.1109/icme59968.2025.11209300","title":"CLAP: Overcoming Language Priors via Contrastive Learning and Answer Perturbation","display_name":"CLAP: Overcoming Language Priors via Contrastive Learning and Answer Perturbation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707815","doi":"https://doi.org/10.1109/icme59968.2025.11209300"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086844626","display_name":"Haoquan Wang","orcid":"https://orcid.org/0009-0002-0742-2946"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Haoquan Wang","raw_affiliation_strings":["Nanchang University,School of Software"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang University,School of Software","institution_ids":["https://openalex.org/I141649914","https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454448","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0003-1678-1537"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Nanchang University,School of Software"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang University,School of Software","institution_ids":["https://openalex.org/I141649914","https://openalex.org/I97750245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062618254","display_name":"Shengbo Chen","orcid":"https://orcid.org/0000-0002-9026-8128"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Shengbo Chen","raw_affiliation_strings":["Nanchang University,School of Software"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang University,School of Software","institution_ids":["https://openalex.org/I141649914","https://openalex.org/I97750245"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100813758","display_name":"Hong Rao","orcid":"https://orcid.org/0000-0002-7467-7108"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]},{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Hong Rao","raw_affiliation_strings":["Nanchang University,School of Software"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang University,School of Software","institution_ids":["https://openalex.org/I141649914","https://openalex.org/I97750245"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7457000017166138,"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":0.7457000017166138,"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":0.18330000340938568,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02630000002682209,"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/prior-probability","display_name":"Prior probability","score":0.6991000175476074},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6714000105857849},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.5759000182151794},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3244999945163727},{"id":"https://openalex.org/keywords/prior-information","display_name":"Prior information","score":0.3174999952316284},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.29580000042915344}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6991000175476074},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6527000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161999702453613},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.5759000182151794},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5526000261306763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2963140463","https://openalex.org/W2963644680","https://openalex.org/W2970019270","https://openalex.org/W2983256121","https://openalex.org/W2997072136","https://openalex.org/W3034287395","https://openalex.org/W3035517717","https://openalex.org/W3099884329","https://openalex.org/W3104788521","https://openalex.org/W3110575265","https://openalex.org/W3154781046","https://openalex.org/W3177934633","https://openalex.org/W3201957104","https://openalex.org/W3202778561","https://openalex.org/W4214648142","https://openalex.org/W4320188728","https://openalex.org/W4385574019","https://openalex.org/W4386065611","https://openalex.org/W4393149638"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"question":[1],"answering":[2],"models":[3],"often":[4],"rely":[5],"on":[6,98,122],"language":[7],"priors":[8],"in":[9],"the":[10,59,63,69,102,119,136],"training":[11],"set,":[12],"which":[13],"affects":[14],"their":[15],"generalization":[16,30,138],"ability":[17],"when":[18],"dealing":[19],"with":[20,50,81],"out-of-distribution":[21],"test":[22],"data.":[23],"While":[24],"existing":[25,74],"research":[26],"has":[27],"improved":[28],"model":[29,38,86,103],"by":[31,68,92],"reducing":[32],"biased":[33],"samples,":[34],"they":[35],"may":[36],"compromise":[37],"performance.":[39,148],"Contrastive":[40,79],"learning":[41,60],"is":[42,151],"a":[43,54],"promising":[44],"solution":[45],"that":[46,132],"uses":[47],"positive":[48,64,90],"samples":[49,65,91],"high":[51],"similarity":[52],"to":[53,57,84,104,117],"given":[55],"text":[56],"guide":[58],"process.":[61],"However,":[62],"are":[66],"constrained":[67],"size":[70],"and":[71,107,126,139,145],"diversity":[72],"of":[73],"datasets.":[75],"We":[76],"propose":[77],"CLAP,":[78],"Learning":[80],"Answer":[82],"Perturbation,":[83],"enhance":[85,127],"robustness.":[87],"CLAP":[88,113,133],"generates":[89],"constructing":[93],"an":[94],"answer":[95,115],"dictionary":[96],"based":[97],"question-image":[99],"pairs,":[100],"enabling":[101],"effectively":[105],"cluster":[106],"differentiate":[108],"various":[109],"sample":[110],"features.":[111],"Additionally,":[112],"introduces":[114],"perturbation":[116],"reduce":[118],"model\u2019s":[120,137],"reliance":[121],"potential":[123],"statistical":[124],"shortcuts":[125],"logical":[128],"reasoning.":[129],"Experiments":[130],"demonstrate":[131],"significantly":[134],"improves":[135],"robustness":[140],"while":[141],"maintaining":[142],"strong":[143],"performance":[144],"achieving":[146],"competitive":[147],"Our":[149],"code":[150],"available":[152],"at":[153],"https://github.com/chenyong-cpu/CLAP.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}