{"id":"https://openalex.org/W4382467347","doi":"https://doi.org/10.1609/aaai.v37i2.25252","title":"The Devil Is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-training","display_name":"The Devil Is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-training","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382467347","doi":"https://doi.org/10.1609/aaai.v37i2.25252"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i2.25252","doi":"https://doi.org/10.1609/aaai.v37i2.25252","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i2.25252","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25252/25024","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25252/25024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100458818","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-5248-935X","observed_orcids":["https://orcid.org/0000-0002-5248-935X","https://orcid.org/0000-0003-0954-5405"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102415891","display_name":"Xinghua Jiang","orcid":"https://orcid.org/0000-0002-7791-5159","observed_orcids":["https://orcid.org/0000-0002-7791-5159"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghua Jiang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Shane Li","orcid":"https://orcid.org/0000-0002-0144-9489","observed_orcids":["https://orcid.org/0000-0002-0144-9489","https://orcid.org/0000-0002-1670-1368","https://orcid.org/0009-0004-3423-1517","https://orcid.org/0000-0003-2067-2763"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042200501","display_name":"Antai Guo","orcid":"https://orcid.org/0009-0007-0168-4028","observed_orcids":["https://orcid.org/0009-0007-0168-4028"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Antai Guo","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101541173","display_name":"Yiqing Hu","orcid":"https://orcid.org/0009-0000-0342-0834","observed_orcids":["https://orcid.org/0009-0000-0342-0834"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Hu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016912950","display_name":"Deqiang Jiang","orcid":"https://orcid.org/0000-0003-3987-2431","observed_orcids":["https://orcid.org/0000-0003-3987-2431"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Jiang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073750509","display_name":"Bo Ren","orcid":"https://orcid.org/0000-0002-0619-7188","observed_orcids":["https://orcid.org/0000-0002-0619-7188"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ren","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":3.8665,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95589828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"37","issue":"2","first_page":"1649","last_page":"1656"},"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":0.7031000256538391,"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":0.7031000256538391,"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":0.21529999375343323,"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":0.034699998795986176,"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/masked-image-modeling","display_name":"masked image modeling","score":0.8629999756813049},{"id":"https://openalex.org/keywords/frequency-domain-representation","display_name":"frequency-domain representation","score":0.5649999976158142},{"id":"https://openalex.org/keywords/fourier-domain","display_name":"Fourier domain","score":0.5540000200271606},{"id":"https://openalex.org/keywords/over-smoothing","display_name":"over-smoothing","score":0.7559999823570251},{"id":"https://openalex.org/keywords/visual-representation-learning","display_name":"visual representation learning","score":0.8399999737739563},{"id":"https://openalex.org/keywords/image-reconstruction","display_name":"image reconstruction","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7135158181190491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848713159561157},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5220977067947388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45293739438056946},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3772850036621094},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28703951835632324}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v37i2.25252","doi":"https://doi.org/10.1609/aaai.v37i2.25252","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i2.25252","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25252/25024","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2204.08227","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.08227","pdf_url":"https://arxiv.org/pdf/2204.08227","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":"pmh:oai:ojs.aaai.org:article/25252","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/25252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2204.08227","doi":"https://doi.org/10.48550/arxiv.2204.08227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.08227","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":"doi:10.1609/aaai.v37i2.25252","doi":"https://doi.org/10.1609/aaai.v37i2.25252","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i2.25252","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/25252/25024","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382467347.pdf","grobid_xml":"https://content.openalex.org/works/W4382467347.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W264456315","https://openalex.org/W1861492603","https://openalex.org/W2010581936","https://openalex.org/W2108598243","https://openalex.org/W2144884820","https://openalex.org/W2160103646","https://openalex.org/W2518108298","https://openalex.org/W2565639579","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2757910899","https://openalex.org/W2765407302","https://openalex.org/W2896457183","https://openalex.org/W2897097528","https://openalex.org/W2908510526","https://openalex.org/W2914483840","https://openalex.org/W2942810103","https://openalex.org/W2954124637","https://openalex.org/W2970971581","https://openalex.org/W2996035354","https://openalex.org/W3034175346","https://openalex.org/W3094502228","https://openalex.org/W3099422760","https://openalex.org/W3112516115","https://openalex.org/W3135058862","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3170863103","https://openalex.org/W3177183540","https://openalex.org/W3188427387","https://openalex.org/W3203605797","https://openalex.org/W3203606893","https://openalex.org/W3204076343","https://openalex.org/W3213836217","https://openalex.org/W4221144677","https://openalex.org/W4226002507","https://openalex.org/W4226379819","https://openalex.org/W4226483978","https://openalex.org/W4239072543","https://openalex.org/W4250640407","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4382465386","https://openalex.org/W4386221015","https://openalex.org/W4402234085","https://openalex.org/W6600565697","https://openalex.org/W6683798357","https://openalex.org/W6735463952","https://openalex.org/W6784818933"],"related_works":["https://openalex.org/W4283022354","https://openalex.org/W4413055791","https://openalex.org/W4386221015","https://openalex.org/W4406902947","https://openalex.org/W4403889191","https://openalex.org/W4409366765","https://openalex.org/W4399375780","https://openalex.org/W4382469100","https://openalex.org/W4403049035","https://openalex.org/W4412382425"],"abstract_inverted_index":{"The":[0],"self-supervised":[1],"Masked":[2,97],"Image":[3,98],"Modeling":[4,99],"(MIM)":[5],"schema,":[6],"following":[7],"\"mask-and-reconstruct\"":[8],"pipeline":[9],"of":[10,30,47,119,156,184,205],"recovering":[11],"contents":[12,122],"from":[13,34,61,78,123],"masked":[14],"image,":[15],"has":[16,90],"recently":[17],"captured":[18],"the":[19,23,27,82,85,136,140,153,158,163,181,193,199,203],"increasing":[20],"interest":[21],"in":[22,71,117,152],"community,":[24],"owing":[25],"to":[26,50,84,179,197],"excellent":[28],"ability":[29],"learning":[31,39,182],"visual":[32,107,200],"representation":[33],"unlabeled":[35],"data.":[36,76],"Aiming":[37],"at":[38],"representations":[40,148],"with":[41,54,114],"high":[42],"semantics":[43,68],"abstracted,":[44],"a":[45,95],"group":[46],"works":[48],"attempts":[49],"reconstruct":[51],"non-semantic":[52],"pixels":[53],"large-ratio":[55],"masking":[56],"strategy,":[57],"which":[58,88,157],"may":[59],"suffer":[60],"\"over-smoothing\"":[62],"problem,":[63],"while":[64],"others":[65],"directly":[66],"infuse":[67],"into":[69],"targets":[70],"off-line":[72],"way":[73],"requiring":[74],"extra":[75],"Different":[77],"them,":[79],"we":[80,110],"shift":[81],"perspective":[83,92],"Fourier":[86],"domain":[87],"naturally":[89],"global":[91],"and":[93,126,176],"present":[94],"new":[96],"(MIM),":[100],"termed":[101],"Geminated":[102],"Gestalt":[103],"Autoencoder":[104],"(Ge^2-AE)":[105],"for":[106],"pre-training.":[108],"Specifically,":[109],"equip":[111],"our":[112,185,188],"model":[113],"geminated":[115],"decoders":[116],"charge":[118],"reconstructing":[120],"image":[121],"both":[124],"pixel":[125],"frequency":[127,206],"space,":[128],"where":[129],"each":[130],"other":[131],"serves":[132],"as":[133],"not":[134],"only":[135],"complementation":[137],"but":[138],"also":[139,172],"reciprocal":[141],"constraints.":[142],"Through":[143],"this":[144,191],"way,":[145],"more":[146],"robust":[147],"can":[149],"be":[150],"learned":[151],"pre-trained":[154],"encoders,":[155],"effectiveness":[159],"is":[160,192],"confirmed":[161],"by":[162],"juxtaposing":[164],"experimental":[165],"results":[166],"on":[167],"downstream":[168],"recognition":[169],"tasks.":[170],"We":[171],"conduct":[173],"several":[174],"quantitative":[175],"qualitative":[177],"experiments":[178],"investigate":[180],"behavior":[183],"method.":[186],"To":[187],"best":[189],"knowledge,":[190],"first":[194],"MIM":[195],"work":[196],"solve":[198],"pre-training":[201],"through":[202],"lens":[204],"domain.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-06-29T00:00:00"}