{"id":"https://openalex.org/W4414578370","doi":"https://doi.org/10.1109/iccv51701.2025.02012","title":"Referring to Any Person","display_name":"Referring to Any Person","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414578370","doi":"https://doi.org/10.1109/iccv51701.2025.02012"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02012","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/2503.08507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071355076","display_name":"Qing Jiang","orcid":"https://orcid.org/0000-0001-8627-3234"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Jiang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101515905","display_name":"Lin Wu","orcid":"https://orcid.org/0000-0002-0510-1842"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Wu","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081985857","display_name":"Zhaoyang Zeng","orcid":"https://orcid.org/0000-0002-0648-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoyang Zeng","raw_affiliation_strings":["International Digital Economy Academy (IDEA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052555143","display_name":"Tianhe Ren","orcid":"https://orcid.org/0000-0003-3121-4020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhe Ren","raw_affiliation_strings":["International Digital Economy Academy (IDEA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100314904","display_name":"Yuda Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuda Xiong","raw_affiliation_strings":["International Digital Economy Academy (IDEA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732741","display_name":"Yihao Chen","orcid":"https://orcid.org/0000-0002-3317-1995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Chen","raw_affiliation_strings":["International Digital Economy Academy (IDEA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA)","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Qin","raw_affiliation_strings":["International Digital Economy Academy (IDEA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy (IDEA)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106578837","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-5305-8543"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21667","last_page":"21678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8555999994277954,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8555999994277954,"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/T12031","display_name":"Speech and dialogue systems","score":0.038600001484155655,"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/T10028","display_name":"Topic Modeling","score":0.037700001150369644,"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/task","display_name":"Task (project management)","score":0.7160000205039978},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5918999910354614},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5595999956130981},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45910000801086426},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.424699991941452},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3544999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7160000205039978},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103999972343445},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48019999265670776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2667999863624573}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02012","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:2503.08507","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08507","pdf_url":"https://arxiv.org/pdf/2503.08507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2503.08507","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08507","pdf_url":"https://arxiv.org/pdf/2503.08507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"are":[1,50],"undoubtedly":[2],"the":[3,11],"most":[4],"important":[5],"participants":[6],"in":[7,61,170],"computer":[8],"vision,":[9],"and":[10,47,79,90,109],"ability":[12],"to":[13,28,43,105,157,160,177],"detect":[14,161],"any":[15,29],"individual":[16],"given":[17],"a":[18,22,101,115,121,132],"natural":[19],"language":[20,124],"description,":[21],"task":[23,70,75],"we":[24,36,67,98,119],"define":[25],"as":[26],"referring":[27,134,172],"person,":[30],"holds":[31],"substantial":[32],"practical":[33],"value.":[34],"However,":[35],"find":[37],"that":[38,58,141],"existing":[39],"models":[40],"generally":[41],"fail":[42],"achieve":[44],"real-world":[45,112],"usability,":[46],"current":[48],"benchmarks":[49,150],"limited":[51],"by":[52],"their":[53,158],"focus":[54],"on":[55,147],"one-to-one":[56],"referring,":[57,180],"hinder":[59],"progress":[60],"this":[62,65,69,95],"area.":[63],"In":[64,164],"work,":[66],"revisit":[68],"from":[71],"three":[72,91],"critical":[73],"perspectives:":[74],"definition,":[76],"dataset":[77,103],"design,":[78],"model":[80,116,125,135],"architecture.":[81],"We":[82],"first":[83],"identify":[84],"five":[85],"aspects":[86],"of":[87,94],"referable":[88],"entities":[89],"distinctive":[92],"characteristics":[93],"task.":[96],"Next,":[97],"introduce":[99],"HumanRef,":[100],"novel":[102],"designed":[104],"tackle":[106],"these":[107],"challenges":[108],"better":[110],"reflect":[111],"applications.":[113],"From":[114],"design":[117],"perspective,":[118],"integrate":[120],"multimodal":[122],"large":[123],"with":[126,154],"an":[127],"object":[128,179],"detection":[129],"framework,":[130],"constructing":[131],"robust":[133],"named":[136],"RexSeek.":[137],"Experimental":[138],"results":[139],"reveal":[140],"state-of-the-art":[142],"models,":[143],"which":[144],"perform":[145],"well":[146],"commonly":[148],"used":[149],"like":[151],"RefCOCO/+/g,":[152],"struggle":[153],"HumanRef":[155],"due":[156],"inability":[159],"multiple":[162],"individuals.":[163],"contrast,":[165],"RexSeek":[166],"not":[167],"only":[168],"excels":[169],"human":[171],"but":[173],"also":[174],"generalizes":[175],"effectively":[176],"common":[178],"making":[181],"it":[182],"broadly":[183],"applicable":[184],"across":[185],"various":[186],"perception":[187],"tasks.":[188],"Code":[189],"is":[190],"available":[191],"at":[192],"https://github.com/IDEA-Research/RexSeek":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}