{"id":"https://openalex.org/W4403662556","doi":"https://doi.org/10.48550/arxiv.2408.03940","title":"How Well Can Vision Language Models See Image Details?","display_name":"How Well Can Vision Language Models See Image Details?","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4403662556","doi":"https://doi.org/10.48550/arxiv.2408.03940"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.03940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03940","pdf_url":"https://arxiv.org/pdf/2408.03940","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.03940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015639938","display_name":"Chenhui Gou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gou, Chenhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020354129","display_name":"Abdulwahab Felemban","orcid":"https://orcid.org/0000-0002-7612-1349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felemban, Abdulwahab","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063344807","display_name":"Faizan Farooq Khan","orcid":"https://orcid.org/0000-0002-3645-603X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Faizan Farooq","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082616743","display_name":"Deyao Zhu","orcid":"https://orcid.org/0000-0001-8014-7309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Deyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635804","display_name":"Jianfei Cai","orcid":"https://orcid.org/0000-0002-9444-3763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Jianfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034608678","display_name":"Hamid Rezatofighi","orcid":"https://orcid.org/0000-0002-8659-8773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rezatofighi, Hamid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elhoseiny, Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T12694","display_name":"Categorization, perception, and language","score":0.7171000242233276,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12694","display_name":"Categorization, perception, and language","score":0.7171000242233276,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.685699999332428,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6020697951316833},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5448383092880249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47321194410324097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46655505895614624},{"id":"https://openalex.org/keywords/optometry","display_name":"Optometry","score":0.3331904113292694},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0818103551864624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6020697951316833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5448383092880249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47321194410324097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46655505895614624},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.3331904113292694},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0818103551864624}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.03940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03940","pdf_url":"https://arxiv.org/pdf/2408.03940","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,"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.2408.03940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.03940","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,"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:2408.03940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03940","pdf_url":"https://arxiv.org/pdf/2408.03940","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662556.pdf","grobid_xml":"https://content.openalex.org/works/W4403662556.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Large":[0],"Language":[1,48],"Model-based":[2],"Vision-Language":[3],"Models":[4,49],"(LLM-based":[5],"VLMs)":[6],"have":[7],"demonstrated":[8],"impressive":[9],"results":[10],"in":[11,57],"various":[12],"vision-language":[13],"understanding":[14,145],"tasks.":[15],"However,":[16],"how":[17],"well":[18],"these":[19,62],"VLMs":[20,56,80,89],"can":[21],"see":[22],"image":[23,149,154],"detail":[24],"beyond":[25],"the":[26,82,99,112,130],"semantic":[27],"level":[28],"remains":[29],"unclear.":[30],"In":[31],"our":[32,119],"study,":[33],"we":[34,85],"introduce":[35],"a":[36,65,70,75],"pixel":[37,94,124],"value":[38,125],"prediction":[39,106,126],"task":[40],"(PVP)":[41],"to":[42,54,91],"explore":[43],"\"How":[44],"Well":[45],"Can":[46],"Vision":[47],"See":[50],"Image":[51],"Details?\"":[52],"and":[53,74,102,104,134,162,173],"assist":[55],"perceiving":[58],"more":[59],"details.":[60],"Typically,":[61],"models":[63],"comprise":[64],"frozen":[66],"CLIP":[67],"visual":[68],"encoder,":[69],"large":[71],"language":[72],"model,":[73],"connecting":[76],"module.":[77],"After":[78],"fine-tuning":[79,98],"on":[81,142,175],"PVP":[83],"task,":[84],"find:":[86],"1)":[87],"existing":[88],"struggle":[90],"predict":[92],"precise":[93],"values":[95],"by":[96],"only":[97],"connection":[100],"module":[101],"LLM;":[103],"2)":[105],"precision":[107],"is":[108,115],"significantly":[109],"improved":[110],"when":[111],"vision":[113,135],"encoder":[114,136],"also":[116],"adapted.":[117],"Additionally,":[118],"research":[120],"reveals":[121],"that":[122],"incorporating":[123],"as":[127,152],"one":[128],"of":[129,171],"VLM":[131,140],"pre-training":[132],"tasks":[133,146],"adaptation":[137],"markedly":[138],"boosts":[139],"performance":[141],"downstream":[143],"image-language":[144],"requiring":[147],"detailed":[148],"perception,":[150],"such":[151],"referring":[153],"segmentation":[155],"(with":[156,167],"an":[157],"average":[158,168],"+10.19":[159],"cIoU":[160],"improvement)":[161],"video":[163],"game":[164],"decision":[165],"making":[166],"score":[169],"improvements":[170],"+80.34":[172],"+70.54":[174],"two":[176],"games,":[177],"respectively).":[178]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}