{"id":"https://openalex.org/W4415901348","doi":"https://doi.org/10.1109/iccv51701.2025.02029","title":"Refer to Any Segmentation Mask Group with Vision-Language Prompts","display_name":"Refer to Any Segmentation Mask Group with Vision-Language Prompts","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415901348","doi":"https://doi.org/10.1109/iccv51701.2025.02029"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02029","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/2506.05342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050360449","display_name":"Shengcao Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengcao Cao","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zijun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijun Wei","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076366439","display_name":"Jason Kuen","orcid":"https://orcid.org/0000-0001-5099-8145"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Kuen","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034482431","display_name":"Kangning Liu","orcid":"https://orcid.org/0009-0000-0398-9879"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangning Liu","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108240742","display_name":"Lingzhi Zhang","orcid":"https://orcid.org/0009-0005-0557-8789"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingzhi Zhang","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005119482","display_name":"Jiuxiang Gu","orcid":"https://orcid.org/0000-0002-3437-5084"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiuxiang Gu","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027836950","display_name":"HyunJoon Jung","orcid":"https://orcid.org/0000-0001-5892-1089"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HyunJoon Jung","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016962709","display_name":"Liang-Yan Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang-Yan Gui","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049973776","display_name":"Yu-Xiong Wang","orcid":"https://orcid.org/0000-0003-4414-0198"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Xiong Wang","raw_affiliation_strings":["Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21853","last_page":"21863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872999787330627,"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":0.9872999787330627,"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/T10028","display_name":"Topic Modeling","score":0.0017999999690800905,"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/T12031","display_name":"Speech and dialogue systems","score":0.0017999999690800905,"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/segmentation","display_name":"Segmentation","score":0.8550000190734863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5929999947547913},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5321000218391418},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5048999786376953},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4675999879837036},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4507000148296356}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8550000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6628999710083008},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5321000218391418},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5048999786376953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775999903678894}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02029","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:2506.05342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05342","pdf_url":"https://arxiv.org/pdf/2506.05342","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.05342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.05342","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.05342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05342","pdf_url":"https://arxiv.org/pdf/2506.05342","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G539587745","display_name":"RI: Medium: Creating Knowledge with All-Novel-Class Computer Vision","funder_award_id":"2106825","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415901348.pdf","grobid_xml":"https://content.openalex.org/works/W4415901348.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"image":[1],"segmentation":[2,60,106,163,169],"models":[3,107],"have":[4],"advanced":[5],"to":[6,96,98,132],"segment":[7],"images":[8],"into":[9],"high-quality":[10],"masks":[11,71],"for":[12,23],"visual":[13,84],"entities,":[14],"and":[15,30,112,122,130,140,165],"yet":[16],"they":[17],"cannot":[18],"provide":[19],"comprehensive":[20],"semantic":[21],"understanding":[22],"complex":[24,109],"queries":[25],"based":[26,72],"on":[27,73,152],"both":[28],"language":[29],"vision.":[31],"This":[32],"limitation":[33],"reduces":[34],"their":[35],"effectiveness":[36],"in":[37],"applications":[38],"that":[39],"require":[40],"user-friendly":[41],"interactions":[42,111],"driven":[43],"by":[44,77,138],"vision-language":[45],"prompts.":[46],"To":[47,86],"bridge":[48],"this":[49,63,88],"gap,":[50],"we":[51,91,126,146],"introduce":[52],"a":[53,65,68,93,115],"novel":[54,94],"task":[55],"of":[56,70,150],"omnimodal":[57],"referring":[58,161,167],"expression":[59,162,168],"(ORES).":[61],"In":[62],"task,":[64,156],"model":[66],"produces":[67],"group":[69],"arbitrary":[74],"prompts":[75],"specified":[76,137],"text":[78,81,139],"only":[79],"or":[80],"plus":[82],"reference":[83,141],"entities.":[85,142],"address":[87],"new":[89,154],"challenge,":[90],"propose":[92],"framework":[95],"\"Refer":[97],"Any":[99],"Segmentation":[100],"Mask":[101],"Group\"":[102],"(RAS),":[103],"which":[104],"augments":[105],"with":[108],"multimodal":[110,118],"comprehension":[113],"via":[114],"mask-centric":[116],"large":[117],"model.":[119],"For":[120],"training":[121],"benchmarking":[123],"ORES":[124,155],"models,":[125],"create":[127],"datasets":[128],"MaskGroups-2M":[129],"MaskGroups-HQ":[131],"include":[133],"diverse":[134],"mask":[135],"groups":[136],"Through":[143],"extensive":[144],"evaluation,":[145],"demonstrate":[147],"superior":[148],"performance":[149],"RAS":[151],"our":[153],"as":[157,159],"well":[158],"classic":[160],"(RES)":[164],"generalized":[166],"(GRES)":[170],"tasks.":[171],"Project":[172],"page:":[173],"https://Ref2Any.github.io.":[174]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}