{"id":"https://openalex.org/W4400125901","doi":"https://doi.org/10.1007/s44267-024-00050-1","title":"Effectiveness assessment of recent large vision-language models","display_name":"Effectiveness assessment of recent large vision-language models","publication_year":2024,"publication_date":"2024-06-28","ids":{"openalex":"https://openalex.org/W4400125901","doi":"https://doi.org/10.1007/s44267-024-00050-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-024-00050-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00050-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00050-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00050-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058820413","display_name":"Yao Jiang","orcid":"https://orcid.org/0009-0006-0812-1036"},"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"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","CN"],"is_corresponding":false,"raw_author_name":"Yao Jiang","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","Sichuan University, Chengdu, 610065, China"],"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Sichuan University, Chengdu, 610065, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101959092","display_name":"Xinyu Yan","orcid":"https://orcid.org/0000-0002-5401-3304"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yan","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","Tianjin University, Tianjin, 300354, China"],"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Tianjin University, Tianjin, 300354, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001285878","display_name":"Ge-Peng Ji","orcid":"https://orcid.org/0000-0001-7092-2877"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ge-Peng Ji","raw_affiliation_strings":["Australian National University, Canberra, 2601, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, 2601, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042631401","display_name":"Keren Fu","orcid":"https://orcid.org/0000-0002-3195-2077"},"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":"Keren Fu","raw_affiliation_strings":["Sichuan University, Chengdu, 610065, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, 610065, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084555916","display_name":"Meijun Sun","orcid":"https://orcid.org/0000-0002-8691-8677"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meijun Sun","raw_affiliation_strings":["Tianjin University, Tianjin, 300354, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, 300354, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643588","display_name":"Huan Xiong","orcid":"https://orcid.org/0000-0001-5401-7834"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE","CN"],"is_corresponding":true,"raw_author_name":"Huan Xiong","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, 150001, China","Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056294284","display_name":"Deng-Ping Fan","orcid":"https://orcid.org/0000-0002-5245-7518"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng-Ping Fan","raw_affiliation_strings":["Nankai University, Tianjin, 300350, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, 300350, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE"],"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, 999041, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100643588"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":7.1507,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97938459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991000294685364,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9937000274658203,"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":0.7948562502861023},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6600818634033203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6057143211364746},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5074781775474548},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.4821626543998718},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.47220808267593384},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4199253022670746},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3999757468700409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3615058660507202},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.17485591769218445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948562502861023},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6600818634033203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057143211364746},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5074781775474548},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.4821626543998718},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.47220808267593384},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4199253022670746},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3999757468700409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3615058660507202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.17485591769218445},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-024-00050-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00050-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00050-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2410.04884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.04884","pdf_url":"https://arxiv.org/pdf/2410.04884","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s44267-024-00050-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00050-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00050-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2480149037","display_name":null,"funder_award_id":"070-63243150","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4709256565","display_name":null,"funder_award_id":"62176169","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400125901.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1982075130","https://openalex.org/W2021088830","https://openalex.org/W2285968993","https://openalex.org/W2346705140","https://openalex.org/W2602856279","https://openalex.org/W2740248187","https://openalex.org/W2740667773","https://openalex.org/W2793847580","https://openalex.org/W2914304175","https://openalex.org/W2944209449","https://openalex.org/W2950579554","https://openalex.org/W3016673627","https://openalex.org/W3044711955","https://openalex.org/W3080122069","https://openalex.org/W3092630514","https://openalex.org/W3094502228","https://openalex.org/W3118600296","https://openalex.org/W3124372372","https://openalex.org/W3126725132","https://openalex.org/W3164098653","https://openalex.org/W3207804100","https://openalex.org/W3210073375","https://openalex.org/W4234552385","https://openalex.org/W4281556902","https://openalex.org/W4289433371","https://openalex.org/W4297792979","https://openalex.org/W4301409532","https://openalex.org/W4319323799","https://openalex.org/W4362597616","https://openalex.org/W4363671707","https://openalex.org/W4367681098","https://openalex.org/W4379259189","https://openalex.org/W4385966081","https://openalex.org/W4386286066","https://openalex.org/W4386302907","https://openalex.org/W4386973901","https://openalex.org/W4389523832","https://openalex.org/W4403237161","https://openalex.org/W4411517540","https://openalex.org/W6674505857","https://openalex.org/W6775857102","https://openalex.org/W6778883912","https://openalex.org/W6800280738","https://openalex.org/W6851578965","https://openalex.org/W6851592950","https://openalex.org/W6853218656"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W3049116993","https://openalex.org/W1541884709","https://openalex.org/W2589081601","https://openalex.org/W2226037301","https://openalex.org/W2026855223","https://openalex.org/W2070708245"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"advent":[2],"of":[3,39,54,102,214],"large":[4],"vision-language":[5],"models":[6],"(LVLMs)":[7],"represents":[8],"a":[9,51],"remarkable":[10],"advance":[11],"in":[12,23,42,62,70,118,138,166,171,188,198],"the":[13,20,37,100,127,211],"quest":[14],"for":[15,210,220],"artificial":[16],"general":[17,27,45,139,172,222],"intelligence.":[18],"However,":[19],"models\u2019":[21],"effectiveness":[22,61],"both":[24,113,221],"specialized":[25,43,63,167,189,224],"and":[26,44,77,94,110,116,151,180,195,223],"tasks":[28,69,81,140,168],"warrants":[29],"further":[30],"investigation.":[31],"This":[32],"paper":[33],"endeavors":[34],"to":[35,49],"evaluate":[36],"competency":[38],"popular":[40],"LVLMs":[41,129,160,219],"tasks,":[46,64,190],"respectively,":[47],"aiming":[48],"offer":[50],"comprehensive":[52],"understanding":[53,136],"these":[55,119,159],"novel":[56],"models.":[57],"To":[58],"gauge":[59],"their":[60,134],"we":[65,122],"employ":[66],"six":[67,80],"challenging":[68],"three":[71,103],"different":[72],"application":[73],"scenarios:":[74],"natural,":[75],"healthcare,":[76],"industrial.":[78],"These":[79],"include":[82],"salient/camouflaged/transparent":[83],"object":[84,142,191],"detection,":[85,90,93],"as":[86,88],"well":[87],"polyp":[89],"skin":[91],"lesion":[92],"industrial":[95],"anomaly":[96],"detection.":[97],"We":[98,174,201],"examine":[99],"performance":[101],"recent":[104],"open-source":[105],"LVLMs,":[106,215],"including":[107,141,185],"MiniGPT-v2,":[108],"LLaVA-1.5,":[109],"Shikra,":[111],"on":[112],"visual":[114],"recognition":[115],"localization":[117],"tasks.":[120,173],"Moreover,":[121],"conduct":[123],"empirical":[124],"investigations":[125,156],"utilizing":[126],"aforementioned":[128],"together":[130],"with":[131],"GPT-4V,":[132],"assessing":[133],"multi-modal":[135],"capabilities":[137],"counting,":[143],"absurd":[144],"question":[145],"answering,":[146],"affordance":[147],"reasoning,":[148],"attribute":[149],"recognition,":[150],"spatial":[152],"relation":[153],"reasoning.":[154],"Our":[155],"reveal":[157],"that":[158,203],"demonstrate":[161],"limited":[162,186],"proficiency":[163],"not":[164],"only":[165],"but":[169],"also":[170],"delve":[175],"deep":[176],"into":[177],"this":[178,204],"inadequacy":[179],"uncover":[181],"several":[182],"potential":[183],"factors,":[184],"cognition":[187],"hallucination,":[192],"text-to-image":[193],"interference,":[194],"decreased":[196],"robustness":[197],"complex":[199],"problems.":[200],"hope":[202],"study":[205],"can":[206],"provide":[207],"useful":[208],"insights":[209],"future":[212],"development":[213],"helping":[216],"researchers":[217],"improve":[218],"applications.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}