{"id":"https://openalex.org/W4402917244","doi":"https://doi.org/10.1109/cvprw63382.2024.00076","title":"MIMIC: Masked Image Modeling with Image Correspondences","display_name":"MIMIC: Masked Image Modeling with Image Correspondences","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4402917244","doi":"https://doi.org/10.1109/cvprw63382.2024.00076"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw63382.2024.00076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw63382.2024.00076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5019820384","display_name":"Kalyani Marathe","orcid":"https://orcid.org/0000-0002-3521-2682"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kalyani Marathe","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030320952","display_name":"Mahtab Bigverdi","orcid":"https://orcid.org/0000-0001-9336-7570"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahtab Bigverdi","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013406069","display_name":"Nishat Anjum Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishat Khan","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025377024","display_name":"Tuhin Kundu","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuhin Kundu","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028548040","display_name":"Patrick Howe","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Howe","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006268025","display_name":"Sharan Ranjit S","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharan Ranjit S","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033616504","display_name":"Anand Bhattad","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Bhattad","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018421415","display_name":"Aniruddha Kembhavi","orcid":"https://orcid.org/0000-0002-7608-7443"},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aniruddha Kembhavi","raw_affiliation_strings":["Allen Institute for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076121553","display_name":"Linda G. Shapiro","orcid":"https://orcid.org/0000-0002-9495-0968"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linda G. Shapiro","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032451496","display_name":"Ranjay Krishna","orcid":"https://orcid.org/0000-0001-8784-2531"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjay Krishna","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5019820384"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54183947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"718","last_page":"727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.7300000190734863,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.7300000190734863,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.6890000104904175,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/image","display_name":"Image (mathematics)","score":0.6530175805091858},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5871756076812744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769335627555847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5723747611045837}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6530175805091858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5871756076812744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769335627555847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5723747611045837}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw63382.2024.00076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw63382.2024.00076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1861492603","https://openalex.org/W2033819227","https://openalex.org/W2085261163","https://openalex.org/W2108598243","https://openalex.org/W2108766544","https://openalex.org/W2151103935","https://openalex.org/W2198618282","https://openalex.org/W2507296351","https://openalex.org/W2520377600","https://openalex.org/W2561074213","https://openalex.org/W2594519801","https://openalex.org/W2942368658","https://openalex.org/W2953127211","https://openalex.org/W2964185501","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3159481202","https://openalex.org/W3180720907","https://openalex.org/W3196466825","https://openalex.org/W4214520160","https://openalex.org/W4232865339","https://openalex.org/W4312443924","https://openalex.org/W4312685069","https://openalex.org/W4313156423","https://openalex.org/W4386075742","https://openalex.org/W4386083144","https://openalex.org/W6636759986","https://openalex.org/W6757817989","https://openalex.org/W6764040762","https://openalex.org/W6765779288","https://openalex.org/W6774314701","https://openalex.org/W6778883912","https://openalex.org/W6796761347","https://openalex.org/W6797065961","https://openalex.org/W6800673378","https://openalex.org/W6802338675","https://openalex.org/W6809664228","https://openalex.org/W6846448456"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Dense":[0],"pixel-specific":[1],"representation":[2],"learning":[3],"at":[4,80],"scale":[5,185],"has":[6],"been":[7],"bottlenecked":[8],"due":[9],"to":[10,69,186,195],"the":[11],"unavailability":[12],"of":[13],"large-scale":[14],"multi-view":[15,71,95],"datasets.":[16,190],"Current":[17],"methods":[18],"for":[19],"building":[20,41],"effective":[21],"pretraining":[22,55],"datasets":[23,42,72,128],"heavily":[24],"rely":[25],"on":[26,117,137,144,151,157,165],"annotated":[27],"3D":[28],"meshes,":[29],"point":[30],"clouds,":[31],"and":[32,77,91,98,130,147,154,160,168,193,198],"camera":[33],"parameters":[34],"from":[35,40,43,73,125,133],"simulated":[36,78],"environments,":[37],"preventing":[38],"them":[39],"real-world":[44,75],"data":[45],"sources":[46],"where":[47],"such":[48],"metadata":[49],"is":[50,177],"lacking.":[51],"We":[52],"introduce":[53],"a":[54],"dataset-curation":[56],"approach":[57],"that":[58],"does":[59],"not":[60],"require":[61],"any":[62],"additional":[63],"annotations.":[64],"Our":[65],"method":[66,182],"allows":[67],"us":[68],"generate":[70],"both":[74],"videos":[76],"environments":[79,135],"scale.":[81],"Specifically,":[82],"we":[83,112],"experiment":[84],"with":[85,89,93,101,163],"two":[86],"scales:":[87],"MIMIC-1M":[88],"1.3M":[90],"MIMIC-3M":[92,121,200],"3.1M":[94],"image":[96,104],"pairs":[97],"train":[99],"models":[100],"different":[102],"masked":[103],"modeling":[105],"objectives.":[106],"Through":[107],"our":[108,118,180],"comprehensive":[109],"experimental":[110],"analysis":[111],"show":[113],"that:":[114],"Representations":[115],"trained":[116],"automatically":[119],"generated":[120],"outperform":[122],"those":[123,131],"learned":[124,132],"expensive":[126],"crowdsourced":[127],"(ImageNet-1K)":[129],"synthetic":[134],"(Multiview-Habitat)":[136],"three":[138],"dense":[139],"geometric":[140],"tasks:":[141],"depth":[142,155],"estimation":[143,150,156],"NYUv2":[145],"(\u21911.7%),":[146],"surface":[148],"normal":[149],"Taskonomy":[152,158,166],"(\u21932.05%),":[153],"(\u21937.5%)":[159],"performs":[161],"on-par":[162],"Multiview-Habitat":[164],"edges":[167],"curvature":[169],"tasks.":[170],"Larger":[171],"dataset":[172],"(MIMIC-3M)":[173],"improves":[174],"performance,":[175],"which":[176],"promising":[178],"since":[179],"curation":[181],"can":[183,201],"arbitrarily":[184],"produce":[187],"even":[188],"larger":[189],"The":[191],"code":[192],"instructions":[194],"download,":[196],"access,":[197],"use":[199],"be":[202],"found":[203],"here.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}