{"id":"https://openalex.org/W4417268939","doi":"https://doi.org/10.1109/iccv51701.2025.00175","title":"Region-based Cluster Discrimination for Visual Representation Learning","display_name":"Region-based Cluster Discrimination for Visual Representation Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417268939","doi":"https://doi.org/10.1109/iccv51701.2025.00175"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00175","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.20025","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030459917","display_name":"Yin Xie","orcid":"https://orcid.org/0000-0002-2468-6321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Xie","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107920894","display_name":"Kaicheng Yang","orcid":"https://orcid.org/0009-0008-6073-9014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaicheng Yang","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075570318","display_name":"Xiang An","orcid":"https://orcid.org/0009-0008-4652-8296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang An","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077993462","display_name":"Kun Wu","orcid":"https://orcid.org/0000-0001-6494-8851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100890234","display_name":"Yongle Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongle Zhao","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weimo Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weimo Deng","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099380972","display_name":"Zimin Ran","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zimin Ran","raw_affiliation_strings":["University of Technology Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680203","display_name":"Yumeng Wang","orcid":"https://orcid.org/0000-0002-9273-6239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yumeng Wang","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100531299","display_name":"Ziyong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyong Feng","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085088523","display_name":"Roy Miles","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roy Miles","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079235359","display_name":"Ismail Elezi","orcid":"https://orcid.org/0000-0002-7047-5808"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ismail Elezi","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073110676","display_name":"Jiankang Deng","orcid":"https://orcid.org/0000-0002-3709-6216"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiankang Deng","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.37241654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1793","last_page":"1803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9660999774932861,"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":0.9660999774932861,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012199999764561653,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00279999990016222,"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/feature-learning","display_name":"Feature learning","score":0.5401999950408936},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49000000953674316},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48089998960494995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.435699999332428},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4341999888420105},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4180000126361847},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39719998836517334},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6567000150680542},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4180000126361847},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00175","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:2507.20025","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.20025","pdf_url":"https://arxiv.org/pdf/2507.20025","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.2507.20025","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.20025","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:2507.20025","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.20025","pdf_url":"https://arxiv.org/pdf/2507.20025","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":{"Learning":[0],"visual":[1,65,134],"representations":[2,35],"is":[3],"foundational":[4],"for":[5,39,136],"a":[6,59,72,79,91,105],"broad":[7],"spectrum":[8],"of":[9],"downstream":[10],"tasks.":[11],"Although":[12],"recent":[13],"vision-language":[14,29],"contrastive":[15],"models,":[16],"such":[17,43],"as":[18,44],"CLIP":[19],"and":[20,47,66,77,101,111,133],"SigLIP,":[21],"have":[22,145],"achieved":[23],"impressive":[24],"zero-shot":[25],"performance":[26],"via":[27],"large-scale":[28,116],"alignment,":[30],"their":[31,37],"reliance":[32],"on":[33,115,127],"global":[34],"constrains":[36],"effectiveness":[38],"dense":[40,131],"prediction":[41],"tasks,":[42,128],"grounding,":[45],"OCR,":[46],"segmentation.":[48],"To":[49],"address":[50],"this":[51],"gap,":[52],"we":[53],"introduce":[54],"Region-Aware":[55],"Cluster":[56],"Discrimination":[57],"(RICE),":[58],"novel":[60],"method":[61],"that":[62,97,121],"enhances":[63],"region-level":[64],"OCR":[67,102],"capabilities.":[68],"We":[69,88],"first":[70],"construct":[71],"billion-scale":[73],"candidate":[74],"region":[75,93],"dataset":[76],"propose":[78],"Region":[80],"Transformer":[81],"layer":[82],"to":[83],"extract":[84],"rich":[85],"regional":[86],"semantics.":[87],"further":[89],"design":[90],"unified":[92],"cluster":[94],"discrimination":[95],"loss":[96],"jointly":[98],"supports":[99],"object":[100],"learning":[103],"within":[104],"single":[106],"classification":[107],"framework,":[108],"enabling":[109],"efficient":[110],"scalable":[112],"distributed":[113],"training":[114],"data.":[117],"Extensive":[118],"experiments":[119],"show":[120],"RICE":[122],"consistently":[123],"outperforms":[124],"previous":[125],"methods":[126],"including":[129],"segmentation,":[130],"detection,":[132],"perception":[135],"Multimodal":[137],"Large":[138],"Language":[139],"Models":[140],"(MLLMs).":[141],"The":[142],"pre-trained":[143],"models":[144],"been":[146],"released":[147],"at":[148],"https://github.com/deepglint/MVT.":[149]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}