{"id":"https://openalex.org/W4402353855","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650020","title":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis","display_name":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353855","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650020"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5113407769","display_name":"Aishik Nagar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aishik Nagar","raw_affiliation_strings":["ASUS Global Pte. Ltd.,ASUS Intelligent Cloud Services (AICS),Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASUS Global Pte. Ltd.,ASUS Intelligent Cloud Services (AICS),Singapore,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038373579","display_name":"Shantanu Jaiswal","orcid":"https://orcid.org/0000-0002-9987-487X"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shantanu Jaiswal","raw_affiliation_strings":["Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073326796","display_name":"Cheston Tan","orcid":"https://orcid.org/0000-0003-1248-4906"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheston Tan","raw_affiliation_strings":["Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC),Agency for Science, Technology and Research (A*STAR)","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9894000291824341,"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":0.9624999761581421,"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":0.6795189380645752},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.634998083114624},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6327491998672485},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5956395268440247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5355591177940369},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35541194677352905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33844834566116333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11833921074867249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6795189380645752},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.634998083114624},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6327491998672485},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5956395268440247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5355591177940369},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35541194677352905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33844834566116333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11833921074867249},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":48,"referenced_works":["https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2606220156","https://openalex.org/W2741631785","https://openalex.org/W2947312908","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2963690694","https://openalex.org/W2970231061","https://openalex.org/W3091588028","https://openalex.org/W3207493267","https://openalex.org/W3214326397","https://openalex.org/W4221143046","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4226278401","https://openalex.org/W4281557260","https://openalex.org/W4281690148","https://openalex.org/W4283026156","https://openalex.org/W4292779060","https://openalex.org/W4296605665","https://openalex.org/W4307079201","https://openalex.org/W4318718936","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4377130677","https://openalex.org/W4378189609","https://openalex.org/W4385565405","https://openalex.org/W4386071687","https://openalex.org/W4389520282","https://openalex.org/W4395091069","https://openalex.org/W6736400098","https://openalex.org/W6778883912","https://openalex.org/W6804142907","https://openalex.org/W6809646742","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6838461927","https://openalex.org/W6838865847","https://openalex.org/W6839193947","https://openalex.org/W6843405348","https://openalex.org/W6847076894","https://openalex.org/W6849177959","https://openalex.org/W6849590751","https://openalex.org/W6850071225","https://openalex.org/W6850625674","https://openalex.org/W6853465110"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3,38],"shown":[4],"impressive":[5],"zero-and":[6],"few-shot":[7],"performance":[8,58],"on":[9,108,184],"real-world":[10],"visual":[11,21,31,56,69,82,114,126,156,175,222,249,261],"question":[12],"answering":[13],"(VQA)":[14],"benchmarks,":[15],"alluding":[16],"to":[17,61,67,133,151,172],"their":[18],"capabilities":[19,84],"as":[20,124],"reasoning":[22,32,46,57,70,83,104,223],"engines.":[23],"However,":[24],"the":[25,80,118,134,141,146,160,185,202,216,240,253],"benchmarks":[26],"being":[27,173],"used":[28],"conflate":[29],"\"pure\"":[30],"with":[33],"world":[34,63,93,231],"knowledge,":[35,64,94],"and":[36,78,95,143,208,244,251],"also":[37,189],"questions":[39],"that":[40,90,159,191,256],"involve":[41],"a":[42,53,100],"limited":[43],"number":[44],"of":[45,85,103,112,120,140,148,218,242],"steps.":[47,105],"Thus,":[48],"it":[49],"remains":[50],"unclear":[51],"whether":[52],"VLM\u2019s":[54],"apparent":[55],"is":[59,182,233],"due":[60,66],"its":[62],"or":[65,128],"actual":[68],"capabilities.To":[71],"clarify":[72],"this":[73],"ambiguity,":[74],"we":[75,236],"systematically":[76],"benchmark":[77],"dissect":[79],"zero-shot":[81,113,155],"VLMs":[86,243],"through":[87],"synthetic":[88],"datasets":[89],"require":[91],"minimal":[92],"allow":[96],"for":[97,154,201,211,221,246],"analysis":[98],"over":[99],"broad":[101],"range":[102],"We":[106,188],"focus":[107],"two":[109],"novel":[110],"aspects":[111],"reasoning:":[115],"i)":[116],"evaluating":[117],"impact":[119],"conveying":[121],"scene":[122,131,166],"information":[123],"either":[125],"embeddings":[127],"purely":[129],"textual":[130,165],"descriptions":[132],"underlying":[135,161],"large":[136,204],"language":[137],"model":[138],"(LLM)":[139],"VLM,":[142],"ii)":[144],"comparing":[145],"effectiveness":[147],"chain-of-thought":[149],"prompting":[150,153,193,199],"standard":[152,198],"reasoning.We":[157],"find":[158,237],"LLMs,":[162],"when":[163,230],"provided":[164,174],"descriptions,":[167],"consistently":[168],"perform":[169],"better":[170,196],"compared":[171],"embeddings.":[176],"In":[177],"particular,":[178],"18%":[179],"higher":[180],"accuracy":[181],"achieved":[183],"PTR":[186],"dataset.":[187],"\u223cfind":[190],"CoT":[192,219],"performs":[194],"marginally":[195],"than":[197],"only":[200],"comparatively":[203],"GPT-3.5-Turbo":[205],"(175B)":[206],"model,":[207],"does":[209],"worse":[210],"smaller-scale":[212],"models.":[213],"This":[214],"suggests":[215],"emergence":[217],"abilities":[220,241],"in":[224,239,260],"LLMs":[225,245,257],"at":[226],"larger":[227],"scales":[228],"even":[229],"knowledge":[232],"limited.":[234],"Overall,":[235],"limitations":[238],"more":[247],"complex":[248],"reasoning,":[250],"highlight":[252],"important":[254],"role":[255],"can":[258],"play":[259],"reasoning.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}