{"id":"https://openalex.org/W6929316993","doi":"https://doi.org/10.48550/arxiv.2504.14988","title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","display_name":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W6929316993","doi":"https://doi.org/10.48550/arxiv.2504.14988"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.14988","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.14988","pdf_url":"https://arxiv.org/pdf/2504.14988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.14988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152493347","display_name":"Hongtao Yu","orcid":"https://orcid.org/0009-0006-1671-2311","observed_orcids":["https://orcid.org/0009-0006-1671-2311"]},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Hong-Tao","raw_affiliation_strings":["School of Computer Science and Engineering , Southeast University , China","School of Computer Science and Engineering and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications , Southeast University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Southeast University , China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications , Southeast University , China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125551177","display_name":"Yuxin Peng","orcid":null,"observed_orcids":[]},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Yuxin","raw_affiliation_strings":["Wangxuan Institute of Computer Technology , Peking University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology , Peking University , China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018609918","display_name":"Serge Belongie","orcid":"https://orcid.org/0000-0002-0388-5217","observed_orcids":["https://orcid.org/0000-0002-0388-5217"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Belongie, Serge","raw_affiliation_strings":["University of Copenhagen","University of Copenhagen , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"University of Copenhagen , Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei, Xiu-Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Xiu-Shen","raw_affiliation_strings":["School of Computer Science and Engineering , Southeast University , China","School of Computer Science and Engineering and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications , Southeast University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Southeast University , China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications , Southeast University , China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/large-vision-language-models","display_name":"large vision-language models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/evaluation-benchmark","display_name":"evaluation benchmark","score":0.7580000162124634},{"id":"https://openalex.org/keywords/semantic-recognition","display_name":"semantic recognition","score":0.8029999732971191},{"id":"https://openalex.org/keywords/modality-alignment","display_name":"modality alignment","score":0.9150000214576721},{"id":"https://openalex.org/keywords/training-paradigms","display_name":"training paradigms","score":0.7580000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708899974822998},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7081999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.3709999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.14988","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.14988","pdf_url":"https://arxiv.org/pdf/2504.14988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.14988","doi":"https://doi.org/10.48550/arxiv.2504.14988","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.14988","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.14988","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.14988","pdf_url":"https://arxiv.org/pdf/2504.14988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2028278801","display_name":null,"funder_award_id":"4009002401","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3509253272","display_name":null,"funder_award_id":"62432001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3740420203","display_name":null,"funder_award_id":"2242025K30024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4894062418","display_name":null,"funder_award_id":"62272231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6078352744","display_name":null,"funder_award_id":"62132001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8190739672","display_name":null,"funder_award_id":"62525201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320943","display_name":"Danmarks Grundforskningsfond","ror":"https://ror.org/00znyv691"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6929316993.pdf","grobid_xml":"https://content.openalex.org/works/W6929316993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,129],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"have":[7,20],"demonstrated":[8],"remarkable":[9],"multimodal":[10],"perception":[11],"capabilities,":[12],"garnering":[13],"significant":[14],"attention.":[15],"While":[16],"numerous":[17],"evaluation":[18,47,60],"studies":[19],"emerged,":[21],"assessing":[22],"LVLMs":[23,63,118],"both":[24,65],"holistically":[25],"and":[26,55,67,75,101,119,126,140],"on":[27,71,83,105],"specialized":[28],"tasks,":[29],"fine-grained":[30,46,76,102],"image":[31],"tasks-fundamental":[32],"to":[33],"computer":[34],"vision-remain":[35],"largely":[36],"unexplored.":[37],"To":[38],"fill":[39],"this":[40],"gap,":[41],"we":[42,87],"introduce":[43],"a":[44],"comprehensive":[45],"benchmark,":[48],"i.e.,":[49],"FG-BMK,":[50],"comprising":[51],"1.01":[52],"million":[53,57],"questions":[54],"0.33":[56],"images.":[58],"Our":[59,136],"systematically":[61],"examines":[62],"from":[64],"human-oriented":[66],"machine-oriented":[68],"perspectives,":[69],"focusing":[70],"their":[72],"semantic":[73],"recognition":[74],"feature":[77],"representation":[78],"capabilities.":[79],"Through":[80],"extensive":[81],"experiments":[82],"twelve":[84],"representative":[85],"LVLMs/VLMs,":[86],"uncover":[88],"key":[89],"findings":[90],"regarding":[91],"the":[92,114,130],"influence":[93],"of":[94,116,132],"training":[95],"paradigms,":[96],"modality":[97],"alignment,":[98],"perturbation":[99],"susceptibility,":[100],"category":[103],"reasoning":[104],"task":[106],"performance.":[107],"This":[108],"work":[109],"provides":[110],"critical":[111],"insights":[112],"into":[113],"limitations":[115],"current":[117],"offers":[120],"guidance":[121],"for":[122],"future":[123],"data":[124],"construction":[125],"model":[127],"design":[128],"development":[131],"more":[133],"advanced":[134],"LVLMs.":[135],"code":[137],"is":[138],"open-source":[139],"available":[141],"at":[142],"https://github.com/SEU-VIPGroup/FG-BMK.":[143]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-10T00:00:00"}