{"id":"https://openalex.org/W4414359975","doi":"https://doi.org/10.24963/ijcai.2025/252","title":"VQCounter: Designing Visual Prompt Queue for Accurate Open-World Counting","display_name":"VQCounter: Designing Visual Prompt Queue for Accurate Open-World Counting","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359975","doi":"https://doi.org/10.24963/ijcai.2025/252"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/252","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5091517421","display_name":"Fanfan Ye","orcid":"https://orcid.org/0000-0002-9431-6414"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fanfan Ye","raw_affiliation_strings":["Hikvision Research Institute","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiqi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiqi Fan","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047098807","display_name":"Qiaoyong Zhong","orcid":"https://orcid.org/0000-0002-5944-1818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaoyong Zhong","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056516274","display_name":"Shicai Yang","orcid":"https://orcid.org/0000-0002-9260-1334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shicai Yang","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636142","display_name":"Di Xie","orcid":"https://orcid.org/0000-0001-8065-5901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xie","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738939","display_name":"Jie Song","orcid":"https://orcid.org/0000-0002-3267-8348"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042449002","display_name":"Mingli Song","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091517421"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21924403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2260","last_page":"2268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9101999998092651,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9101999998092651,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.6599000096321106},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6340000033378601},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6273999810218811},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/voronoi-diagram","display_name":"Voronoi diagram","score":0.5695000290870667},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5485000014305115},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674999833106995},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6273999810218811},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C24881265","wikidata":"https://www.wikidata.org/wiki/Q757267","display_name":"Voronoi diagram","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/252","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Class-agnostic":[0],"counting":[1],"enables":[2],"enumerating":[3],"arbitrary":[4],"object":[5],"classes":[6],"beyond":[7],"those":[8],"seen":[9],"during":[10,74],"training.":[11],"Recent":[12],"studies":[13],"attempted":[14],"to":[15,60,76,97,102],"exploit":[16],"the":[17,27,35,62,110,133],"potential":[18],"of":[19,38,64,86,119],"visual":[20,39,55,65,81],"foundation":[21],"models":[22],"such":[23],"as":[24],"GroundingDINO.":[25],"Despite":[26],"considerable":[28],"progress,":[29],"we":[30,49,113],"observe":[31],"certain":[32],"shortcomings,":[33],"including":[34],"limited":[36],"diversity":[37,63],"prompts":[40],"and":[41,80,105,135,147],"suboptimal":[42],"training":[43,75],"regimen.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"introduce":[50],"VQCounter,":[51],"which":[52,124],"incorporates":[53],"a":[54,90,116],"prompt":[56],"queue":[57],"mechanism":[58],"designed":[59,96],"enrich":[61],"prompts.":[66],"A":[67],"random":[68],"modality":[69],"switching":[70],"strategy":[71],"is":[72,95],"proposed":[73],"strengthen":[77],"both":[78,145],"textual":[79],"modalities.":[82],"Besides,":[83],"in":[84,144],"light":[85],"weak":[87],"point":[88,126],"supervision,":[89],"Voronoi":[91,111],"diagram-based":[92],"cost":[93],"(VoronoiCost)":[94],"improve":[98],"Hungarian":[99],"matching,":[100],"leading":[101],"more":[103,120],"stable":[104],"faster":[106],"convergence.":[107],"Building":[108],"upon":[109],"diagram,":[112],"also":[114],"propose":[115],"novel":[117],"set":[118],"stringent":[121],"evaluation":[122],"metrics,":[123],"take":[125],"localization":[127],"into":[128],"account.":[129],"Extensive":[130],"experiments":[131],"on":[132],"FSC-147":[134],"CARPK":[136],"datasets":[137],"demonstrate":[138],"that":[139],"VQCounter":[140],"achieves":[141],"state-of-the-art":[142],"performance":[143],"zero-shot":[146],"few-shot":[148],"settings,":[149],"significantly":[150],"outperforming":[151],"existing":[152],"methods":[153],"across":[154],"nearly":[155],"all":[156],"evaluations.":[157]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}