{"id":"https://openalex.org/W4415799137","doi":"https://doi.org/10.52202/079017-0077","title":"Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning","display_name":"Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415799137","doi":"https://doi.org/10.52202/079017-0077"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0077","doi":"https://doi.org/10.52202/079017-0077","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0077","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.19560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042783792","display_name":"Shentong Mo","orcid":"https://orcid.org/0000-0003-3308-9585","observed_orcids":["https://orcid.org/0000-0003-3308-9585"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shentong Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055545928","display_name":"Shengbang Tong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengbang Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3151,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94415132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2348","last_page":"2377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9574999809265137,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9574999809265137,"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":0.0284000001847744,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0031999999191612005,"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/jepa","display_name":"JEPA","score":0.9829999804496765},{"id":"https://openalex.org/keywords/self-supervised-contrastive-learning","display_name":"self-supervised contrastive learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/vicreg","display_name":"VICReg","score":0.9430000185966492},{"id":"https://openalex.org/keywords/exponentially-weighted-moving-average","display_name":"exponential moving average","score":0.6079999804496765},{"id":"https://openalex.org/keywords/image-masking","display_name":"image masking","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2468000054359436},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24220000207424164}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0077","doi":"https://doi.org/10.52202/079017-0077","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0077","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.19560","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.19560","pdf_url":"https://arxiv.org/pdf/2410.19560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2410.19560","doi":"https://doi.org/10.48550/arxiv.2410.19560","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.19560","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.19560","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.19560","pdf_url":"https://arxiv.org/pdf/2410.19560","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415799137.pdf","grobid_xml":"https://content.openalex.org/works/W4415799137.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W3009561768","https://openalex.org/W3135367836","https://openalex.org/W3143083666","https://openalex.org/W3170863103","https://openalex.org/W4221145109","https://openalex.org/W4226002507","https://openalex.org/W4281772236","https://openalex.org/W4386114296","https://openalex.org/W4386221015","https://openalex.org/W4388092911","https://openalex.org/W4389363413","https://openalex.org/W4394861491","https://openalex.org/W4399151798","https://openalex.org/W4410914926","https://openalex.org/W6979267127"],"related_works":["https://openalex.org/W7160439851","https://openalex.org/W4399151798","https://openalex.org/W7220683963","https://openalex.org/W7054840859","https://openalex.org/W4416598848","https://openalex.org/W4386076428","https://openalex.org/W7140108208","https://openalex.org/W7108478410","https://openalex.org/W7167601768","https://openalex.org/W7215041656"],"abstract_inverted_index":{"In":[0],"recent":[1],"advancements":[2],"in":[3,49,59,108,151],"unsupervised":[4],"visual":[5,21,136],"representation":[6,137],"learning,":[7],"the":[8,40,54,62,81,87,99,109,116,131,142],"Joint-Embedding":[9,83],"Predictive":[10,84],"Architecture":[11,85],"(JEPA)":[12],"has":[13],"emerged":[14],"as":[15],"a":[16,73],"significant":[17],"method":[18],"for":[19,101],"extracting":[20],"features":[22],"from":[23,47],"unlabeled":[24],"imagery":[25],"through":[26],"an":[27],"innovative":[28],"masking":[29],"strategy.":[30,91],"Despite":[31],"its":[32],"success,":[33],"two":[34],"primary":[35],"limitations":[36],"have":[37],"been":[38],"identified:":[39],"inefficacy":[41],"of":[42,56,64,111,135],"Exponential":[43],"Moving":[44],"Average":[45],"(EMA)":[46],"I-JEPA":[48,57],"preventing":[50,102],"entire":[51,103],"collapse":[52,104],"and":[53,105,121,133,148,155],"inadequacy":[55],"prediction":[58],"accurately":[60],"learning":[61],"mean":[63,110],"patch":[65],"representations.":[66],"Addressing":[67],"these":[68],"challenges,":[69],"this":[70],"study":[71],"introduces":[72],"novel":[74],"framework,":[75],"namely":[76],"C-JEPA":[77,128,145],"(Contrastive-JEPA),":[78],"which":[79],"integrates":[80],"Image-based":[82],"with":[86],"Variance-Invariance-Covariance":[88],"Regularization":[89],"(VICReg)":[90],"This":[92],"integration":[93],"is":[94],"designed":[95],"to":[96],"effectively":[97],"learn":[98],"variance/covariance":[100],"ensuring":[106],"invariance":[107],"augmented":[112],"views,":[113],"thereby":[114],"overcoming":[115],"identified":[117],"limitations.":[118],"Through":[119],"empirical":[120],"theoretical":[122],"evaluations,":[123],"our":[124],"work":[125],"demonstrates":[126],"that":[127],"significantly":[129],"enhances":[130],"stability":[132],"quality":[134],"learning.":[138],"When":[139],"pre-trained":[140],"on":[141],"ImageNet-1K":[143],"dataset,":[144],"exhibits":[146],"rapid":[147],"improved":[149],"convergence":[150],"both":[152],"linear":[153],"probing":[154],"fine-tuning":[156],"performance":[157],"metrics.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}