{"id":"https://openalex.org/W7138022909","doi":"https://doi.org/10.1609/aaai.v40i14.38166","title":"Endowing Vision-Language Models with System 2 Thinking for Fine-grained Visual Recognition","display_name":"Endowing Vision-Language Models with System 2 Thinking for Fine-grained Visual Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138022909","doi":"https://doi.org/10.1609/aaai.v40i14.38166"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i14.38166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38166/42128","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38166/42128","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129641284","display_name":"Yutong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Yang","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648049","display_name":"Lifu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lifu Huang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662023","display_name":"Yijie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Lin","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738595","display_name":"Xi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119692","display_name":"Numerical Method (China)","ror":"https://ror.org/02ns8zp42","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210119692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Peng","raw_affiliation_strings":["Sichuan University,\nNational Key Laboratory of Fundamental Algorithms and Models for Engineering Numerical Simulation, Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,\nNational Key Laboratory of Fundamental Algorithms and Models for Engineering Numerical Simulation, Sichuan University","institution_ids":["https://openalex.org/I4210119692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051406229","display_name":"Mouxing Yang","orcid":"https://orcid.org/0000-0001-8544-6375"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mouxing Yang","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24306948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11802","last_page":"11810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.754800021648407,"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":0.754800021648407,"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":0.058400001376867294,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04439999908208847,"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/discriminative-model","display_name":"Discriminative model","score":0.7839000225067139},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7734000086784363},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.515500009059906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36239999532699585},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.350600004196167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7839000225067139},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7734000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519000172615051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.667900025844574},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.329800009727478},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i14.38166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38166/42128","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"},{"id":"pmh:oai:ojs.aaai.org:article/38166","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38166","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38166","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38166/42128","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/10","display_name":"Reduced inequalities","score":0.7604193687438965}],"awards":[{"id":"https://openalex.org/G1545039845","display_name":null,"funder_award_id":"62472295","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2570225771","display_name":null,"funder_award_id":"62176171","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3635681223","display_name":null,"funder_award_id":"CJ202303","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5032578210","display_name":null,"funder_award_id":"CJ202403","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138022909.pdf","grobid_xml":"https://content.openalex.org/works/W7138022909.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"excel":[3],"at":[4],"extracting":[5],"salient":[6,139],"visual":[7,15,140],"features":[8,141],"from":[9,44,142,150],"query":[10,123],"images,":[11],"thus":[12],"exhibiting":[13],"promising":[14],"recognition":[16,61,167],"performance.":[17],"However,":[18],"VLMs":[19,70,102],"would":[20],"encounter":[21],"significant":[22],"degradation":[23],"in":[24,31,155],"fine-grained":[25,60,166],"scenarios":[26],"due":[27],"to":[28,58,127],"their":[29],"deficiency":[30],"distinguishing":[32],"nuanced":[33,105,147],"differences":[34,148],"among":[35],"candidate":[36,78,120],"categories.":[37],"As":[38],"a":[39,96],"remedy,":[40],"we":[41,67,89],"draw":[42],"inspiration":[43],"the":[45,56,87,114,118,138,146,174],"``System":[46],"1":[47,144],"&":[48],"System":[49,74,143,151],"2\"":[50],"cognitive":[51],"theory":[52],"of":[53,104,178],"humans,":[54],"paving":[55],"way":[57],"achieve":[59],"for":[62,117],"VLMs.":[63],"To":[64],"be":[65],"specific,":[66],"observe":[68],"that":[69,100],"naturally":[71],"align":[72],"with":[73,145,157],"1,":[75],"quickly":[76],"identifying":[77],"categories":[79,121],"but":[80],"leaving":[81],"easily-confused":[82],"ones":[83],"unresolved.":[84],"Based":[85],"on":[86,162],"observation,":[88],"propose":[90],"System-2":[91],"enhanCed":[92],"visuAl":[93],"recogNition":[94],"(SCAN),":[95],"novel":[97],"plug-and-play":[98],"approach":[99],"makes":[101],"aware":[103],"differences.":[106],"In":[107],"brief,":[108],"SCAN":[109,135],"first":[110],"specifies":[111],"and":[112,122,176],"abstracts":[113],"discriminative":[115],"attributes":[116],"confused":[119],"images":[124],"by":[125],"resorting":[126],"off-the-shelf":[128],"large":[129],"foundation":[130],"models,":[131],"respectively.":[132],"After":[133],"that,":[134],"adaptively":[136],"integrates":[137],"derived":[149],"2,":[152],"resolving":[153],"confusion":[154],"candidates":[156],"estimated":[158],"uncertainty.":[159],"Extensive":[160],"experiments":[161],"eight":[163],"widely":[164],"used":[165],"benchmarks":[168],"against":[169],"10":[170],"state-of-the-art":[171],"baselines":[172],"verify":[173],"effectiveness":[175],"superiority":[177],"SCAN.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}