{"id":"https://openalex.org/W4413145408","doi":"https://doi.org/10.1109/cvpr52734.2025.02304","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","display_name":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145408","doi":"https://doi.org/10.1109/cvpr52734.2025.02304"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017235581","display_name":"Yuzhong Zhao","orcid":"https://orcid.org/0000-0002-2425-6786"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhong Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007029093","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-7828-2090"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320012","display_name":"Yue Liu","orcid":"https://orcid.org/0000-0001-5880-4923"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079934230","display_name":"Mingxiang Liao","orcid":"https://orcid.org/0000-0003-1853-1419"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxiang Liao","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389824","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0001-9305-6908"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Gong","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015317495","display_name":"Qixiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052317536","display_name":"Fang Wan","orcid":"https://orcid.org/0000-0002-8083-9257"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Wan","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24742","last_page":"24752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.878000020980835,"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/T12031","display_name":"Speech and dialogue systems","score":0.878000020980835,"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/computer-science","display_name":"Computer science","score":0.6680625081062317},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4879297912120819},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3800727128982544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34808963537216187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680625081062317},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4879297912120819},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3800727128982544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34808963537216187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"One":[0],"fundamental":[1],"task":[2,110],"of":[3,25,55,66,71,81,129],"multimodal":[4,67,93,131,160],"models":[5],"is":[6,167],"to":[7,12,31,45,119],"translate":[8],"referred":[9,86],"image":[10,108],"regions":[11],"human":[13,56,122],"preferred":[14],"language":[15,35,64],"descriptions.":[16,36],"Existing":[17],"methods,":[18],"however,":[19],"ignore":[20],"the":[21,52,85,103,114,126],"resolution":[22,53],"adaptability":[23,54,128],"needs":[24],"different":[26],"tasks,":[27],"which":[28,74],"hinders":[29],"them":[30],"find":[32],"out":[33],"precise":[34],"In":[37],"this":[38],"study,":[39],"we":[40],"propose":[41],"a":[42,79,163],"DynRefer":[43,61,90,136,153],"approach,":[44],"pursue":[46],"high-accuracy":[47],"region-level":[48,130,144,159],"referring":[49,94,118],"through":[50],"mimicking":[51],"visual":[57,115],"cognition.":[58],"During":[59,88],"training,":[60],"stochastically":[62],"aligns":[63],"descriptions":[65],"tasks":[68,101,142,161],"with":[69],"images":[70],"multiple":[72,158],"resolutions,":[73],"are":[75],"constructed":[76],"by":[77,95],"nesting":[78],"set":[80],"random":[82],"views":[83,105],"around":[84],"region.":[87],"inference,":[89],"performs":[91],"selectively":[92],"sampling":[96],"proper":[97],"region":[98,147],"representations":[99],"for":[100,117],"from":[102],"nested":[104],"based":[106],"on":[107,157],"and":[109,149],"priors.":[111],"This":[112],"allows":[113],"information":[116],"better":[120],"match":[121],"preferences,":[123],"thereby":[124],"improving":[125],"representational":[127],"models.":[132],"Experiments":[133],"show":[134],"that":[135],"brings":[137],"mutual":[138],"improvement":[139],"upon":[140],"broad":[141],"including":[143],"captioning,":[145],"open-vocabulary":[146],"recognition":[148],"attribute":[150],"detection.":[151],"Furthermore,":[152],"achieves":[154],"state-of-the-art":[155],"results":[156],"using":[162],"single":[164],"model.":[165],"Code":[166],"available":[168],"at":[169],"https://github.com/callsys/DynRefer.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}