{"id":"https://openalex.org/W4394866526","doi":"https://doi.org/10.1109/iccv51701.2025.00369","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","display_name":"RankCLIP: Ranking-Consistent Language-Image Pretraining","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4394866526","doi":"https://doi.org/10.1109/iccv51701.2025.00369"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00369","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.09387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100395351","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0001-6450-8485"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776767","display_name":"Zhuokai Zhao","orcid":"https://orcid.org/0000-0001-8201-2977"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuokai Zhao","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032213685","display_name":"Zhaorun Chen","orcid":"https://orcid.org/0000-0002-2668-6587"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaorun Chen","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056189990","display_name":"Zhili Feng","orcid":"https://orcid.org/0000-0001-6573-7933"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhili Feng","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112102159","display_name":"Zenghui Ding","orcid":"https://orcid.org/0000-0002-6787-9318"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenghui Ding","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101515037","display_name":"Yining Sun","orcid":"https://orcid.org/0000-0001-9851-7611"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yining Sun","raw_affiliation_strings":["HFIPS, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100395351"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00038776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3874","last_page":"3884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.957099974155426,"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":0.7792671918869019},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7289825677871704},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.643620491027832},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6118221282958984},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5961381196975708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.581721305847168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5778601765632629},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5775370001792908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5321988463401794},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4921840727329254},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4658316969871521},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4218199849128723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.362470805644989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1087183952331543},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06654444336891174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792671918869019},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7289825677871704},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.643620491027832},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6118221282958984},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5961381196975708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581721305847168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5778601765632629},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5775370001792908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5321988463401794},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4921840727329254},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4658316969871521},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4218199849128723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.362470805644989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1087183952331543},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06654444336891174},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00369","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:2404.09387","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.09387","pdf_url":"https://arxiv.org/pdf/2404.09387","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.2404.09387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.09387","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.09387","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.09387","pdf_url":"https://arxiv.org/pdf/2404.09387","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":[{"id":"https://openalex.org/G425254596","display_name":null,"funder_award_id":"2024YFF0507603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2067317451","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2188500270","https://openalex.org/W1546381263","https://openalex.org/W627697492"],"abstract_inverted_index":{"Self-supervised":[0],"contrastive":[1],"learning":[2,124],"models,":[3],"such":[4],"as":[5],"CLIP,":[6],"have":[7],"set":[8],"new":[9],"benchmarks":[10],"for":[11],"vision-language":[12],"models":[13],"in":[14,104,112],"many":[15],"downstream":[16,106],"tasks.":[17],"However,":[18],"their":[19],"dependency":[20],"on":[21],"rigid":[22,52],"one-to-one":[23,53],"mappings":[24],"overlooks":[25],"the":[26,51,63,79,86,100,119],"complex":[27],"and":[28,33,36,58,69,73,91],"often":[29],"multifaceted":[30],"relationships":[31,89],"between":[32,90],"within":[34,92],"texts":[35],"images.":[37],"To":[38],"this":[39,122],"end,":[40],"we":[41,98],"introduce":[42],"RankCLIP,":[43],"a":[44],"novel":[45],"pre-training":[46],"method":[47],"that":[48],"extends":[49],"beyond":[50],"matching":[54],"framework":[55],"of":[56,102,121],"CLIP":[57],"its":[59],"variants.":[60],"By":[61],"extending":[62],"traditional":[64],"pair-wise":[65],"loss":[66],"to":[67,84],"list-wise,":[68],"leveraging":[70],"both":[71],"in-modal":[72],"cross-modal":[74],"ranking":[75],"consistency,":[76],"RankCLIP":[77,103],"improves":[78],"alignment":[80],"process,":[81],"enabling":[82],"it":[83],"capture":[85],"nuanced":[87],"many-to-many":[88],"each":[93],"modality.":[94],"Through":[95],"comprehensive":[96],"experiments,":[97],"demonstrate":[99],"effectiveness":[101],"various":[105],"tasks,":[107],"notably":[108],"achieving":[109],"significant":[110],"gains":[111],"zero-shot":[113],"classifications":[114],"over":[115],"state-of-the-art":[116],"methods,":[117],"underscoring":[118],"importance":[120],"enhanced":[123],"process.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}