{"id":"https://openalex.org/W4404649616","doi":"https://doi.org/10.1109/iccv51701.2025.00893","title":"Teaching VLMs to Localize Specific Objects from In-Context Examples","display_name":"Teaching VLMs to Localize Specific Objects from In-Context Examples","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404649616","doi":"https://doi.org/10.1109/iccv51701.2025.00893"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00893","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.13317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016502423","display_name":"Sivan Doveh","orcid":"https://orcid.org/0000-0003-2431-0620"},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sivan Doveh","raw_affiliation_strings":["Weizmann Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science","institution_ids":["https://openalex.org/I53964585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011071587","display_name":"Nimrod Shabtay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nimrod Shabtay","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054401063","display_name":"Eli Schwartz","orcid":"https://orcid.org/0000-0002-3393-8666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eli Schwartz","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011795407","display_name":"Hilde Kuehne","orcid":"https://orcid.org/0000-0003-1079-4441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hilde Kuehne","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072571599","display_name":"Raja Giryes","orcid":"https://orcid.org/0000-0002-2830-0297"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Raja Giryes","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052325109","display_name":"Rog\u00e9rio Feris","orcid":"https://orcid.org/0000-0001-6399-0679"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rogerio Feris","raw_affiliation_strings":["MIT-IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020676344","display_name":"Leonid Karlinsky","orcid":"https://orcid.org/0000-0003-2524-2068"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Leonid Karlinsky","raw_affiliation_strings":["MIT-IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077154012","display_name":"James M. Glass","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036051790","display_name":"Assaf Arbelle","orcid":"https://orcid.org/0000-0001-6559-2316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assaf Arbelle","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076637753","display_name":"Shimon Ullman","orcid":"https://orcid.org/0000-0003-4331-298X"},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shimon Ullman","raw_affiliation_strings":["Weizmann Institute of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science","institution_ids":["https://openalex.org/I53964585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125505468","display_name":"M. Jehanzeb Mirza","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Jehanzeb Mirza","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.00094201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9572","last_page":"9582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.7803000211715698,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7803000211715698,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.7721999883651733,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7605999708175659,"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/context","display_name":"Context (archaeology)","score":0.6760737895965576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45703235268592834},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.2415667474269867},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.13931328058242798}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6760737895965576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45703235268592834},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2415667474269867},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.13931328058242798}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00893","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:2411.13317","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13317","pdf_url":"https://arxiv.org/pdf/2411.13317","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.2411.13317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.13317","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:2411.13317","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13317","pdf_url":"https://arxiv.org/pdf/2411.13317","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"remarkable":[5],"capabilities":[6],"across":[7,169],"diverse":[8],"visual":[9,200],"tasks,":[10],"including":[11],"image":[12],"recognition,":[13],"video":[14,156],"understanding,":[15],"and":[16,89,93,245,259],"Visual":[17],"Question":[18],"Answering":[19],"(VQA)":[20],"when":[21],"explicitly":[22],"trained":[23],"for":[24,250,263],"these":[25,28],"tasks.":[26],"Despite":[27],"advances,":[29],"we":[30,61,143,172,183],"find":[31],"that":[32,120,129,148,176,189],"present-day":[33,257],"VLMs":[34,216,251],"(including":[35],"the":[36,56,64,98,166,196,210,241],"proprietary":[37],"GPT-4o)":[38],"lack":[39],"a":[40,50,71,75,86,103,124,145,185,261],"fundamental":[41],"cognitive":[42],"ability:":[43],"learning":[44],"to":[45,123,132,220,243],"localize":[46],"specific":[47],"objects":[48,119],"in":[49,102,112,141,222,256,266],"scene":[51],"by":[52],"taking":[53],"into":[54],"account":[55],"context.":[57],"In":[58],"this":[59],"work,":[60],"focus":[62],"on":[63,199,229],"task":[65],"of":[66,78,114,116,163,214],"few-shot":[67,211,248],"personalized":[68,138,235,247],"localization,":[69],"where":[70],"model":[72,197],"is":[73,94,130,240],"given":[74],"small":[76],"set":[77],"annotated":[79],"images":[80],"(in-context":[81],"examples)":[82],"--":[83,92,252],"each":[84],"with":[85,96,134,193],"category":[87],"label":[88],"bounding":[90],"box":[91],"tasked":[95],"localizing":[97],"same":[99,167],"object":[100,128,157,168,191],"type":[101],"query":[104],"image.":[105],"Personalized":[106],"localization":[107,139,212,236,249],"can":[108,121],"be":[109],"particularly":[110],"important":[111],"cases":[113],"ambiguity":[115],"several":[117,230],"related":[118],"respond":[122],"text":[125],"or":[126],"an":[127],"hard":[131],"describe":[133],"words.":[135],"To":[136,180],"provoke":[137],"abilities":[140],"models,":[142],"present":[144],"data-centric":[146],"solution":[147],"fine-tunes":[149],"them":[150],"using":[151],"carefully":[152],"curated":[153],"data":[154],"from":[155,218],"tracking":[158,165],"datasets.":[159],"By":[160],"leveraging":[161],"sequences":[162],"frames":[164],"multiple":[170],"shots,":[171],"simulate":[173],"instruction-tuning":[174],"dialogues":[175],"promote":[177],"context":[178,201],"awareness.":[179],"reinforce":[181],"this,":[182],"introduce":[184],"novel":[186],"regularization":[187],"technique":[188],"replaces":[190],"labels":[192],"pseudo-names,":[194],"ensuring":[195],"relies":[198],"rather":[202],"than":[203],"prior":[204],"knowledge.":[205],"Our":[206],"method":[207],"significantly":[208],"enhances":[209],"performance":[213],"recent":[215],"ranging":[217],"7B":[219],"72B":[221],"size,":[223],"without":[224],"sacrificing":[225],"generalization,":[226],"as":[227],"demonstrated":[228],"benchmarks":[231],"tailored":[232],"towards":[233],"evaluating":[234],"abilities.":[237],"This":[238],"work":[239],"first":[242],"explore":[244],"benchmark":[246],"exposing":[253],"critical":[254],"weaknesses":[255],"VLMs,":[258],"laying":[260],"foundation":[262],"future":[264],"research":[265],"context-driven":[267],"vision-language":[268],"applications.":[269]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}