{"id":"https://openalex.org/W4414359427","doi":"https://doi.org/10.24963/ijcai.2025/605","title":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","display_name":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359427","doi":"https://doi.org/10.24963/ijcai.2025/605"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/605","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5102219437","display_name":"Xin Huang","orcid":"https://orcid.org/0000-0001-7180-7002"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]},{"id":"https://openalex.org/I4210115684","display_name":"Gezhouba Explosive (China)","ror":"https://ror.org/02bsc8781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115684"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Huang","raw_affiliation_strings":["Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","institution_ids":["https://openalex.org/I4210115684"]},{"raw_affiliation_string":"School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079630580","display_name":"Ruibin Li","orcid":"https://orcid.org/0000-0001-6471-7658"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]},{"id":"https://openalex.org/I4210115684","display_name":"Gezhouba Explosive (China)","ror":"https://ror.org/02bsc8781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115684"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibin Li","raw_affiliation_strings":["Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","institution_ids":["https://openalex.org/I4210115684"]},{"raw_affiliation_string":"School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069358025","display_name":"Tong Jia","orcid":"https://orcid.org/0000-0002-5946-9829"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Jia","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444845","display_name":"Wei Zheng","orcid":"https://orcid.org/0009-0005-3692-017X"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]},{"id":"https://openalex.org/I4210115684","display_name":"Gezhouba Explosive (China)","ror":"https://ror.org/02bsc8781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115684"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zheng","raw_affiliation_strings":["Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","institution_ids":["https://openalex.org/I4210115684"]},{"raw_affiliation_string":"School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100306502","display_name":"Wang Ya","orcid":"https://orcid.org/0009-0008-2900-2807"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]},{"id":"https://openalex.org/I4210115684","display_name":"Gezhouba Explosive (China)","ror":"https://ror.org/02bsc8781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115684"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Wang","raw_affiliation_strings":["Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Intelligent Explosion-proof Equipment, Henan, China","institution_ids":["https://openalex.org/I4210115684"]},{"raw_affiliation_string":"School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Henan, China","institution_ids":["https://openalex.org/I4210110718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"5435","last_page":"5443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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":0.9884999990463257,"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/margin","display_name":"Margin (machine learning)","score":0.5920000076293945},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5264000296592712},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.42879998683929443},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4284000098705292},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.374099999666214},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34150001406669617},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.2985999882221222},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.2971999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685999989509583},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/605","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"are":[3,65],"essential":[4],"for":[5,118],"multimodal":[6,136],"tasks,":[7,12],"especially":[8],"compositional":[9],"reasoning":[10],"(CR)":[11],"which":[13,44,82],"require":[14],"distinguishing":[15],"fine-grained":[16],"semantic":[17],"differences":[18],"between":[19],"visual":[20,51,110],"and":[21,53,74,151],"textual":[22],"embeddings.":[23],"However,":[24],"existing":[25],"methods":[26],"primarily":[27],"fine-tune":[28],"the":[29,38,50,56,60,75,109,120,142,158,167],"model":[30],"by":[31],"generating":[32],"text-based":[33,105],"hard":[34,106,137,146],"negative":[35,42,63,138],"samples,":[36,43],"neglecting":[37],"importance":[39],"of":[40,49,59,77,145,169],"image-based":[41,116],"results":[45],"in":[46,86],"insufficient":[47],"training":[48,119],"encoder":[52],"ultimately":[54],"impacts":[55],"overall":[57,125],"performance":[58,185],"model.":[61],"Moreover,":[62],"samples":[64,79],"typically":[66],"treated":[67],"uniformly,":[68],"without":[69],"considering":[70],"their":[71],"difficulty":[72,164],"levels,":[73],"alignment":[76],"positive":[78],"is":[80,193],"insufficient,":[81],"leads":[83],"to":[84,112,140,162,165],"challenges":[85],"aligning":[87],"difficult":[88],"sample":[89,163,171],"pairs.":[90,172],"To":[91],"address":[92],"these":[93],"issues,":[94],"we":[95],"propose":[96],"Adaptive":[97],"Hard":[98],"Negative":[99],"Perturbation":[100],"Learning":[101],"(AHNPL).":[102],"AHNPL":[103,127],"translates":[104],"negatives":[107,117,147],"into":[108],"domain":[111],"generate":[113],"semantically":[114],"disturbed":[115],"model,":[121],"thereby":[122],"enhancing":[123],"its":[124],"performance.":[126],"also":[128],"introduces":[129],"a":[130,135,152],"contrastive":[131,159],"learning":[132],"approach":[133],"using":[134],"loss":[139,155],"improve":[141],"model's":[143],"discrimination":[144],"within":[148],"each":[149],"modality":[150],"dynamic":[153],"margin":[154,160],"that":[156,179],"adjusts":[157],"according":[161],"enhance":[166],"distinction":[168],"challenging":[170],"Experiments":[173],"on":[174,186],"three":[175],"public":[176],"datasets":[177],"demonstrate":[178],"our":[180],"method":[181],"effectively":[182],"boosts":[183],"VLMs'":[184],"complex":[187],"CR":[188],"tasks.":[189],"The":[190],"source":[191],"code":[192],"available":[194],"at":[195],"https://github.com/nynu-BDAI/AHNPL.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}