{"id":"https://openalex.org/W4404313209","doi":"https://doi.org/10.48550/arxiv.2410.19808","title":"LocateBench: Evaluating the Locating Ability of Vision Language Models","display_name":"LocateBench: Evaluating the Locating Ability of Vision Language Models","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4404313209","doi":"https://doi.org/10.48550/arxiv.2410.19808"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.19808","pdf_url":"http://arxiv.org/pdf/2410.19808","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2410.19808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075993628","display_name":"Ting-Rui Chiang","orcid":"https://orcid.org/0000-0002-8398-8944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chiang, Ting-Rui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084800356","display_name":"Joshua A. Robinson","orcid":"https://orcid.org/0000-0002-1513-7187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robinson, Joshua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098617","display_name":"Xinyan Yu","orcid":"https://orcid.org/0000-0002-8286-3306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xinyan Velocity","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060347694","display_name":"Dani Yogatama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yogatama, Dani","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8987,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8987,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8834,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7742,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48136693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42993465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39508906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39491197},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3672488},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12991658}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.19808","pdf_url":"http://arxiv.org/pdf/2410.19808","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.19808","pdf_url":"http://arxiv.org/pdf/2410.19808","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4391913857","https://openalex.org/W4391375266","https://openalex.org/W3204019825","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,10,30],"locate":[3],"an":[4,7],"object":[5],"in":[6],"image":[8],"according":[9],"natural":[11],"language":[12,48],"instructions":[13],"is":[14],"crucial":[15],"for":[16],"many":[17],"real-world":[18],"applications.":[19],"In":[20],"this":[21,32],"work":[22],"we":[23],"propose":[24],"LocateBench,":[25],"a":[26],"high-quality":[27],"benchmark":[28],"dedicated":[29],"evaluating":[31],"ability.":[33],"We":[34,50],"experiment":[35],"with":[36],"multiple":[37],"prompting":[38],"approaches,":[39],"and":[40],"measure":[41],"the":[42,54,57],"accuracy":[43,55,64],"of":[44,56],"several":[45],"large":[46],"vision":[47],"models.":[49],"find":[51],"that":[52],"even":[53],"strongest":[58],"model,":[59],"GPT-4o,":[60],"lags":[61],"behind":[62],"human":[63],"by":[65],"more":[66],"than":[67],"10%.":[68]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4404313209","counts_by_year":[],"updated_date":"2025-04-03T11:17:39.787549","created_date":"2024-11-14"}