{"id":"https://openalex.org/W4415348219","doi":"https://doi.org/10.1109/iccv51701.2025.02239","title":"Vision-Language Models Can't See the Obvious","display_name":"Vision-Language Models Can't See the Obvious","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415348219","doi":"https://doi.org/10.1109/iccv51701.2025.02239"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.04741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120063697","display_name":"Yasser Dahou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Yasser Dahou","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091058234","display_name":"Ngoc Dung Huynh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ngoc Dung Huynh","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120063699","display_name":"Phuc H. Le-Khac","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Phuc H. Le-Khac","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120063700","display_name":"Wamiq Reyaz Para","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Wamiq Reyaz Para","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088041020","display_name":"Ankit Singh","orcid":"https://orcid.org/0000-0002-1610-6235"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ankit Singh","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090466272","display_name":"Sanath Narayan","orcid":"https://orcid.org/0009-0001-7880-3239"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sanath Narayan","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32778136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24159","last_page":"24169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.2304999977350235,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.2304999977350235,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8215000033378601},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7006999850273132},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.4927999973297119},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48730000853538513},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4431999921798706},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8215000033378601},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6952000260353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6463000178337097},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.4927999973297119},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2983008078","wikidata":"https://www.wikidata.org/wiki/Q863495","display_name":"Grid cell","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.02239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04741","pdf_url":"https://arxiv.org/pdf/2507.04741","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.04741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04741","pdf_url":"https://arxiv.org/pdf/2507.04741","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,97],"present":[1],"Saliency":[2],"Benchmark":[3],"(SalBench),":[4],"a":[5,31,35,99,111,133],"novel":[6,80],"benchmark":[7,41],"designed":[8],"to":[9,27,54,116],"assess":[10],"the":[11,84,124,144,151],"capability":[12],"of":[13,37,61,87,102,146,154],"Large":[14],"Vision-Language":[15],"Models":[16],"(LVLM)":[17],"in":[18,142],"detecting":[19],"visually":[20],"salient":[21],"features":[22,45],"that":[23,63,148],"are":[24,52],"readily":[25],"apparent":[26],"humans,":[28],"such":[29,132],"as":[30],"large":[32],"circle":[33],"amidst":[34],"grid":[36],"smaller":[38],"ones.":[39],"This":[40],"focuses":[42],"on":[43,131],"low-level":[44],"including":[46],"color,":[47],"intensity,":[48],"and":[49,72,93,107],"orientation,":[50],"which":[51],"fundamental":[53],"human":[55,75,155],"visual":[56,120],"processing.":[57],"Our":[58],"SalBench":[59,106,136],"consists":[60],"images":[62],"highlight":[64],"rare,":[65],"unusual,":[66],"or":[67],"unexpected":[68],"elements":[69],"within":[70],"scenes,":[71],"naturally":[73],"draw":[74],"attention.":[76,156],"It":[77],"comprises":[78],"three":[79],"tasks":[81],"for":[82],"evaluating":[83],"perceptual":[85],"capabilities":[86,145],"LVLM:":[88],"Odd-One-Out":[89],"Detection,":[90],"Referring":[91,95],"Odd-One-Out,":[92],"Visual":[94],"Odd-One-Out.":[96],"perform":[98],"comprehensive":[100],"evaluation":[101],"state-of-the-art":[103],"LVLM":[104,114,147],"using":[105],"our":[108],"findings":[109],"reveal":[110],"surprising":[112],"limitation:":[113],"struggle":[115],"identify":[117],"seemingly":[118],"obvious":[119],"anomalies,":[121],"with":[122,150],"even":[123],"advanced":[125],"GPT-4o":[126],"achieving":[127],"only":[128],"47.6\\%":[129],"accuracy":[130],"simple":[134],"task.":[135],"will":[137],"be":[138],"an":[139],"important":[140],"step":[141],"measuring":[143],"align":[149],"subtle":[152],"definition":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-20T00:00:00"}
