{"id":"https://openalex.org/W7137819658","doi":"https://doi.org/10.1609/aaai.v40i13.38084","title":"Retrieval-driven Reasoning for Deliberative Visual Classification","display_name":"Retrieval-driven Reasoning for Deliberative Visual Classification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137819658","doi":"https://doi.org/10.1609/aaai.v40i13.38084"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38084","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129670604","display_name":"Jianye Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianye Xie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714809","display_name":"Lianyong Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianyong Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738283","display_name":"Fan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379001","display_name":"Anqi Wang","orcid":"https://orcid.org/0000-0003-1378-0379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anqi Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008124931","display_name":"Wenjuan Gong","orcid":"https://orcid.org/0000-0001-7805-3629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjuan Gong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697794","display_name":"Danxin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danxin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129676742","display_name":"Wanchun Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanchun Dou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129734625","display_name":"Yang Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034495880","display_name":"Shichao Pei","orcid":"https://orcid.org/0000-0002-0802-1506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichao Pei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129712935","display_name":"Xiaokang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaokang Zhou","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129670604"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03281133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"11060","last_page":"11068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9397000074386597,"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":0.9397000074386597,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010099999606609344,"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/generalization","display_name":"Generalization","score":0.6313999891281128},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.41429999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6347000002861023},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5454000234603882},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.2711000144481659},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38084","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38084","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6893283724784851,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1,73],"(VLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"in":[7,31],"visual":[8,57],"classification":[9,58,63],"tasks.":[10],"Existing":[11],"methods":[12,37],"for":[13,116],"enhancing":[14],"VLMs":[15],"on":[16,22,132,143],"this":[17],"task":[18,59],"often":[19],"rely":[20],"heavily":[21],"direct":[23],"category-to-image":[24],"matching,":[25],"which":[26],"limits":[27],"generalization":[28,157],"and":[29,69,98,111,127,156],"results":[30],"suboptimal":[32],"performance.":[33],"In":[34],"addition,":[35],"these":[36,50],"provide":[38],"no":[39],"understanding":[40],"of":[41],"why":[42],"a":[43,54,86,113],"specific":[44],"category":[45,100,139],"is":[46],"chosen.":[47],"To":[48],"address":[49],"limitations,":[51],"we":[52,84],"introduce":[53],"new":[55],"deliberative":[56,67,99,125],"that":[60,147],"decomposes":[61],"the":[62,80,133,138],"process":[64],"into":[65],"multiple":[66,124,144],"steps":[68,126],"leverages":[70,105],"Large":[71],"Language":[72],"(LLMs)":[74],"to":[75,107,136],"perform":[76],"explicit":[77,129],"reasoning":[78,130],"before":[79],"final":[81],"decision.":[82],"Specifically,":[83],"propose":[85],"Retrieval-driven":[87],"Reasoning":[88],"model":[89],"(RdR)":[90],"with":[91],"two":[92],"components,":[93],"i.e.,":[94],"retrieval":[95,114],"database":[96,115],"construction":[97],"prediction.":[101,140],"The":[102,120],"first":[103],"component":[104,122],"LLMs":[106],"extract":[108],"category-relevant":[109],"descriptors":[110,135],"constructs":[112],"effective":[117],"image\u2013descriptor":[118],"matching.":[119],"second":[121],"facilitates":[123],"performs":[128],"based":[131],"retrieved":[134],"augment":[137],"Extensive":[141],"experiments":[142],"datasets":[145],"demonstrate":[146],"RdR":[148],"consistently":[149],"outperforms":[150],"strong":[151],"baselines,":[152],"highlighting":[153],"its":[154],"robustness":[155],"ability.":[158]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}