{"id":"https://openalex.org/W4402774238","doi":"https://doi.org/10.1109/cvpr52733.2024.01286","title":"PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs","display_name":"PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402774238","doi":"https://doi.org/10.1109/cvpr52733.2024.01286"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020630700","display_name":"Michael Dorkenwald","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Dorkenwald","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093931829","display_name":"Nimrod Barazani","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nimrod Barazani","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024508073","display_name":"Cees G. M. Snoek","orcid":"https://orcid.org/0000-0001-9092-1556"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G. M. Snoek","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102985946","display_name":"Yuki M. Asano","orcid":"https://orcid.org/0000-0002-8533-4020"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuki M. Asano","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3304,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88732196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13548","last_page":"13558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.95169997215271,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9156000018119812,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/insert","display_name":"Insert (composites)","score":0.708752453327179},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6616515517234802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.658519983291626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3790719509124756},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1314294934272766}],"concepts":[{"id":"https://openalex.org/C2780098074","wikidata":"https://www.wikidata.org/wiki/Q6037362","display_name":"Insert (composites)","level":2,"score":0.708752453327179},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6616515517234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.658519983291626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3790719509124756},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1314294934272766},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321008","display_name":"Universiteit van Amsterdam","ror":"https://ror.org/04dkp9463"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2167951155","https://openalex.org/W4244087614","https://openalex.org/W2355051413","https://openalex.org/W2024714645","https://openalex.org/W2372066122","https://openalex.org/W4255333527","https://openalex.org/W3179576741","https://openalex.org/W2010169578"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs),":[2],"such":[3],"as":[4],"Flamingo":[5],"and":[6,70,85,106,184],"GPT-4V,":[7],"have":[8],"shown":[9],"immense":[10],"potential":[11],"by":[12,96],"integrating":[13],"large":[14],"language":[15],"models":[16,22],"with":[17,58,64,150],"vision":[18,29],"systems.":[19],"Nevertheless,":[20],"these":[21,66],"face":[23],"challenges":[24],"in":[25,68,92],"the":[26,80,90,99,138,161],"fundamental":[27],"computer":[28],"task":[30,155],"of":[31,82,101,132,163,177],"object":[32,142],"localisation,":[33],"due":[34],"to":[35,52,78,88],"their":[36],"training":[37,56],"on":[38,156,174],"multi-modal":[39],"data":[40,158],"containing":[41,128],"mostly":[42],"captions":[43],"without":[44,159],"explicit":[45],"spa-tial":[46,126],"grounding.":[47],"While":[48],"it":[49],"is":[50,148],"possible":[51],"construct":[53],"custom,":[54],"supervised":[55,111],"pipelines":[57],"bounding":[59],"box":[60],"annotations":[61],"that":[62,134],"integrate":[63],"VLMs,":[65],"result":[67],"specialized":[69],"hard-to-scale":[71],"models.":[72],"In":[73],"this":[74,115],"paper,":[75],"we":[76,117],"aim":[77],"explore":[79],"limits":[81],"caption-based":[83,103],"VLMs":[84],"instead":[86],"propose":[87],"tackle":[89],"challenge":[91],"a":[93,102,124,129,151,175],"simpler":[94],"manner":[95],"i)":[97],"keeping":[98],"weights":[100],"VLM":[104],"frozen":[105,139],"ii)":[107],"not":[108],"using":[109],"any":[110],"detection":[112],"data.":[113],"To":[114],"end,":[116],"introduce":[118],"an":[119],"input-agnostic":[120],"Positional":[121],"Insert":[122],"(PIN),":[123],"learnable":[125],"prompt,":[127],"minimal":[130],"set":[131],"parameters":[133],"are":[135],"slid":[136],"inside":[137],"VLM,":[140],"unlocking":[141],"localisation":[143,172],"capabilities.":[144],"Our":[145,167],"PIN":[146],"module":[147],"trained":[149],"simple":[152],"next-token":[153],"prediction":[154],"synthetic":[157],"requiring":[160],"introduction":[162],"new":[164],"output":[165],"heads.":[166],"experiments":[168],"demonstrate":[169],"strong":[170],"zero-shot":[171],"performances":[173],"variety":[176],"images,":[178],"including":[179],"Pascal":[180],"VOC,":[181],"COCO,":[182],"LVIS,":[183],"diverse":[185],"images":[186],"like":[187],"paintings":[188],"or":[189],"cartoons.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}