{"id":"https://openalex.org/W4401908525","doi":"https://doi.org/10.1109/tnnls.2024.3443088","title":"Kernel Masked Image Modeling Through the Lens of Theoretical Understanding","display_name":"Kernel Masked Image Modeling Through the Lens of Theoretical Understanding","publication_year":2024,"publication_date":"2024-08-27","ids":{"openalex":"https://openalex.org/W4401908525","doi":"https://doi.org/10.1109/tnnls.2024.3443088","pmid":"https://pubmed.ncbi.nlm.nih.gov/39190525"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3443088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443088","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101680182","display_name":"Yurui Qian","orcid":"https://orcid.org/0000-0002-0010-7508"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yurui Qian","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0010-7508","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445377","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-4219-781X"},"institutions":[{"id":"https://openalex.org/I4210136029","display_name":"Saratoga Hospital","ror":"https://ror.org/048j1wp71","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210136029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["resides in Saratoga, Saratoga, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4219-781X","affiliations":[{"raw_affiliation_string":"resides in Saratoga, Saratoga, CA, USA","institution_ids":["https://openalex.org/I4210136029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039202077","display_name":"Jingjing Zou","orcid":"https://orcid.org/0000-0002-4749-105X"},"institutions":[{"id":"https://openalex.org/I4210128647","display_name":"Human Longevity (United States)","ror":"https://ror.org/03n53gr48","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128647"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Zou","raw_affiliation_strings":["Herbert Wertheim School of Public Health and Human Longevity Science, University of California at San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4749-105X","affiliations":[{"raw_affiliation_string":"Herbert Wertheim School of Public Health and Human Longevity Science, University of California at San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I4210128647"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077401853","display_name":"Jingyang Lin","orcid":"https://orcid.org/0009-0000-3223-3827"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingyang Lin","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0009-0000-3223-3827","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102908901","display_name":"Qibin Sun","orcid":"https://orcid.org/0000-0002-6789-7460"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Sun","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6789-7460","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-7732","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101680182"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.6665,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85275879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"36","issue":"7","first_page":"13512","last_page":"13526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9984999895095825,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"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":0.9929999709129333,"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/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.6463897824287415},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6173254251480103},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5822992324829102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5470125079154968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46591854095458984},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4619157314300537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.411682665348053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37793588638305664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37456434965133667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.26996156573295593},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.2657316029071808},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.21985721588134766}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.6463897824287415},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6173254251480103},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5822992324829102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5470125079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46591854095458984},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4619157314300537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.411682665348053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37793588638305664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37456434965133667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26996156573295593},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.2657316029071808},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.21985721588134766},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3443088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443088","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39190525","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39190525","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":135,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W935362247","https://openalex.org/W1846799578","https://openalex.org/W1861492603","https://openalex.org/W1977295328","https://openalex.org/W1986280275","https://openalex.org/W2007339694","https://openalex.org/W2025768430","https://openalex.org/W2031489346","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2117876524","https://openalex.org/W2138011018","https://openalex.org/W2140095548","https://openalex.org/W2155904486","https://openalex.org/W2167222293","https://openalex.org/W2194775991","https://openalex.org/W2283469138","https://openalex.org/W2321533354","https://openalex.org/W2533598788","https://openalex.org/W2558661413","https://openalex.org/W2592962403","https://openalex.org/W2599837529","https://openalex.org/W2737258237","https://openalex.org/W2757910899","https://openalex.org/W2806857275","https://openalex.org/W2842511635","https://openalex.org/W2884822772","https://openalex.org/W2917551568","https://openalex.org/W2963150697","https://openalex.org/W2963420272","https://openalex.org/W2964194231","https://openalex.org/W2965373594","https://openalex.org/W3035524453","https://openalex.org/W3042609801","https://openalex.org/W3118608800","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3160566314","https://openalex.org/W3169827396","https://openalex.org/W3171007011","https://openalex.org/W3183430956","https://openalex.org/W3189347889","https://openalex.org/W4220899212","https://openalex.org/W4224246420","https://openalex.org/W4225512839","https://openalex.org/W4225624178","https://openalex.org/W4226213156","https://openalex.org/W4280557312","https://openalex.org/W4281709991","https://openalex.org/W4281729085","https://openalex.org/W4283022354","https://openalex.org/W4283449034","https://openalex.org/W4297808394","https://openalex.org/W4298186587","https://openalex.org/W4301914798","https://openalex.org/W4309161945","https://openalex.org/W4312262772","https://openalex.org/W4312309398","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4313021454","https://openalex.org/W4313156423","https://openalex.org/W4319300504","https://openalex.org/W4320458322","https://openalex.org/W4361193944","https://openalex.org/W4366352791","https://openalex.org/W4366567824","https://openalex.org/W4367663188","https://openalex.org/W4379117118","https://openalex.org/W4379534806","https://openalex.org/W4382240135","https://openalex.org/W4382465386","https://openalex.org/W4382469100","https://openalex.org/W4386066407","https://openalex.org/W4386076203","https://openalex.org/W4386076493","https://openalex.org/W4386076509","https://openalex.org/W4386221015","https://openalex.org/W4387415072","https://openalex.org/W4389104669","https://openalex.org/W4390874319","https://openalex.org/W4391147937","https://openalex.org/W4392617711","https://openalex.org/W4393147340","https://openalex.org/W4395056497","https://openalex.org/W4399527506","https://openalex.org/W4402715775","https://openalex.org/W4402727760","https://openalex.org/W4402754277","https://openalex.org/W6638677478","https://openalex.org/W6676014314","https://openalex.org/W6744513255","https://openalex.org/W6746052068","https://openalex.org/W6747899497","https://openalex.org/W6755207826","https://openalex.org/W6771917389","https://openalex.org/W6774314701","https://openalex.org/W6776929863","https://openalex.org/W6783757617","https://openalex.org/W6787972765","https://openalex.org/W6788135285","https://openalex.org/W6790850890","https://openalex.org/W6791353385","https://openalex.org/W6791742336","https://openalex.org/W6794295097","https://openalex.org/W6795754764","https://openalex.org/W6796422976","https://openalex.org/W6796530276","https://openalex.org/W6796761347","https://openalex.org/W6802387851","https://openalex.org/W6803702653","https://openalex.org/W6804160461","https://openalex.org/W6810039040","https://openalex.org/W6810265253","https://openalex.org/W6810613308","https://openalex.org/W6810737369","https://openalex.org/W6810744310","https://openalex.org/W6837948907","https://openalex.org/W6838638105","https://openalex.org/W6838657836","https://openalex.org/W6839005623","https://openalex.org/W6843801771","https://openalex.org/W6844138932","https://openalex.org/W6845452229","https://openalex.org/W6845983704","https://openalex.org/W6847389933","https://openalex.org/W6849575128","https://openalex.org/W6849925848","https://openalex.org/W6850882814","https://openalex.org/W6850930123","https://openalex.org/W6852003021","https://openalex.org/W6856303245","https://openalex.org/W6862816224"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2065805792","https://openalex.org/W4285290579","https://openalex.org/W3125885229","https://openalex.org/W2896570485","https://openalex.org/W1527525543","https://openalex.org/W2370512383","https://openalex.org/W2962818398","https://openalex.org/W2111121652"],"abstract_inverted_index":{"Masked":[0],"image":[1],"modeling":[2],"(MIM)":[3],"has":[4],"been":[5],"considered":[6],"as":[7,175],"the":[8,28,31,45,54,63,76,96,102,118,123,128,146,192,196,200],"state-of-the-art":[9],"(SOTA)":[10],"self-supervised":[11],"learning":[12],"(SSL)":[13],"technique":[14],"in":[15,53,168,190],"terms":[16],"of":[17,24,34,49,79,104,117,122,195],"visual":[18],"pretraining.":[19],"The":[20,206],"impressive":[21],"generalization":[22,99,194],"ability":[23,100],"MIM":[25,51,68,172],"also":[26],"paves":[27],"way":[29],"for":[30,73],"remarkable":[32],"success":[33],"large-scale":[35],"vision":[36],"foundation":[37],"models.":[38],"In":[39],"this":[40],"article,":[41],"we":[42,61,89,111],"further":[43],"discuss":[44],"validity":[46],"and":[47,60,83,101,127,179,188,199],"advantages":[48],"implementing":[50],"techniques":[52],"reproducing":[55],"kernel":[56,105,147,204],"Hilbert":[57],"spaces":[58],"(RKHSs)":[59],"associate":[62],"analysis":[64,189],"with":[65],"a":[66,91,113,135,162],"novel":[67],"method":[69,157],"named":[70],"R-MIM":[71,125,156,198],"(short":[72],"RKHS-MIM).":[74],"Through":[75],"careful":[77],"construction":[78],"an":[80],"augmentation":[81],"graph":[82],"by":[84],"using":[85],"spectral":[86],"decomposition":[87],"techniques,":[88,173],"establish":[90],"systematic":[92],"theoretical":[93,186,201],"understanding":[94],"between":[95],"proposed":[97,197],"R-MIM's":[98],"choice":[103],"function":[106],"used":[107],"during":[108],"training.":[109],"Specifically,":[110],"reach":[112],"conclusion":[114],"that":[115,151],"both":[116],"local":[119],"Lipschitz":[120],"constant":[121],"resultant":[124],"model":[126],"corresponding":[129],"expected":[130],"pretraining":[131],"error":[132],"can":[133],"have":[134],"strong":[136],"composite":[137],"effect":[138],"on":[139,145,165],"bounding":[140],"downstream":[141,166],"task":[142],"error,":[143],"depending":[144],"options.":[148],"We":[149],"demonstrate":[150],"under":[152],"mild":[153],"mathematical":[154],"assumptions,":[155],"is":[158,208],"guaranteed":[159],"to":[160,170,203],"return":[161],"lower":[163],"bound":[164],"tasks":[167],"comparison":[169],"vanilla":[171],"such":[174],"masked":[176],"autoencoder":[177],"(MAE)":[178],"SimMIM.":[180],"Empirical":[181],"justification":[182],"well":[183],"corroborates":[184],"our":[185],"hypothesis":[187],"showing":[191],"superior":[193],"link":[202],"choices.":[205],"code":[207],"available":[209],"at:":[210],"https://github.com/yurui-q/R-MIM.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}