{"id":"https://openalex.org/W4416014098","doi":"https://doi.org/10.1109/iccv51701.2025.00379","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","display_name":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416014098","doi":"https://doi.org/10.1109/iccv51701.2025.00379"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00379","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/2505.04601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030048445","display_name":"Xianhang Li","orcid":"https://orcid.org/0009-0008-1970-4821"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianhang Li","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000416445","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0001-6396-9802"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048179343","display_name":"Haoqin Tu","orcid":"https://orcid.org/0000-0002-5627-249X"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoqin Tu","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015318397","display_name":"Hongru Zhu","orcid":"https://orcid.org/0000-0002-4088-3536"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cihang Xie","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28731649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3977","last_page":"3987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.32679998874664307,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.32679998874664307,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.09960000216960907,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.08969999849796295,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/encoder","display_name":"Encoder","score":0.6725000143051147},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.6488000154495239},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.43140000104904175},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.30079999566078186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801000237464905},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6725000143051147},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44929999113082886},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00379","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:2505.04601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04601","pdf_url":"https://arxiv.org/pdf/2505.04601","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.04601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.04601","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:2505.04601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04601","pdf_url":"https://arxiv.org/pdf/2505.04601","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416014098.pdf","grobid_xml":"https://content.openalex.org/works/W4416014098.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"OpenAI's":[0,73],"CLIP,":[1],"released":[2],"in":[3,104,112,136],"early":[4],"2021,":[5],"have":[6,26],"long":[7],"been":[8],"the":[9,70],"go-to":[10],"choice":[11],"of":[12,63,72],"vision":[13,64,118],"encoder":[14,106],"for":[15,90,95],"building":[16,137],"multimodal":[17,78,114,138,144,152],"foundation":[18],"models.":[19,115],"Although":[20],"recent":[21],"alternatives":[22],"such":[23],"as":[24],"SigLIP":[25],"begun":[27],"to":[28,33,123],"challenge":[29],"this":[30,55],"status":[31],"quo,":[32],"our":[34],"knowledge":[35],"none":[36],"are":[37,49],"fully":[38],"open:":[39],"their":[40,46],"training":[41,47,91,96],"data":[42,97],"remains":[43],"proprietary":[44],"and/or":[45],"recipes":[48],"not":[50],"released.":[51],"This":[52],"paper":[53],"fills":[54],"gap":[56],"with":[57],"OpenVision,":[58],"a":[59,129],"fully-open,":[60],"cost-effective":[61],"family":[62],"encoders":[65,119],"that":[66],"match":[67],"or":[68],"surpass":[69],"performance":[71],"CLIP":[74],"when":[75],"integrated":[76],"into":[77],"frameworks":[79],"like":[80],"LLaVA.":[81],"OpenVision":[82,126],"builds":[83],"on":[84],"existing":[85],"works":[86],"--":[87,98],"e.g.,":[88],"CLIPS":[89],"framework":[92],"and":[93,108,134],"Recap-DataComp-1B":[94],"while":[99,146],"revealing":[100],"multiple":[101],"key":[102],"insights":[103],"enhancing":[105],"quality":[107],"showcasing":[109],"practical":[110],"benefits":[111],"advancing":[113],"By":[116],"releasing":[117],"spanning":[120],"from":[121],"5.9M":[122],"632.1M":[124],"parameters,":[125],"offers":[127],"practitioners":[128],"flexible":[130],"trade-off":[131],"between":[132],"capacity":[133],"efficiency":[135],"models:":[139],"larger":[140],"models":[141],"deliver":[142],"enhanced":[143],"performance,":[145],"smaller":[147],"versions":[148],"enable":[149],"lightweight,":[150],"edge-ready":[151],"deployments.":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}