{"id":"https://openalex.org/W4387436633","doi":"https://doi.org/10.1145/3581783.3612106","title":"Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning","display_name":"Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387436633","doi":"https://doi.org/10.1145/3581783.3612106"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612106","doi":"https://doi.org/10.1145/3581783.3612106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612106","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612106","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612106","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101810463","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-5159-5954","observed_orcids":["https://orcid.org/0000-0001-5159-5954"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5159-5954","affiliations":[{"raw_affiliation_string":"Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061","observed_orcids":["https://orcid.org/0000-0003-3957-7061"]},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3957-7061","affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325720","display_name":"Can Wang","orcid":"https://orcid.org/0009-0008-7317-6791","observed_orcids":["https://orcid.org/0009-0008-7317-6791"]},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Kiel University, Kiel, Germany"],"raw_orcid":"https://orcid.org/0009-0008-7317-6791","affiliations":[{"raw_affiliation_string":"Kiel University, Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093024319","display_name":"Xulin King","orcid":"https://orcid.org/0009-0002-9715-5799","observed_orcids":["https://orcid.org/0009-0002-9715-5799"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xulin King","raw_affiliation_strings":["Hangzhou GOTHEN Technology Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-9715-5799","affiliations":[{"raw_affiliation_string":"Hangzhou GOTHEN Technology Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316","observed_orcids":["https://orcid.org/0000-0002-6332-8316"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6332-8316","affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9728,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80356394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1738","last_page":"1749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9843999743461609,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9843999743461609,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.013000000268220901,"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":0.0013000000035390258,"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-autoencoder","display_name":"masked autoencoder","score":0.9079999923706055},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6769999861717224},{"id":"https://openalex.org/keywords/alignment-constraints","display_name":"alignment constraints","score":0.781000018119812},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5680000185966492},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6930000185966492},{"id":"https://openalex.org/keywords/3d-shape-classification","display_name":"3D shape classification","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9236048460006714},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.8515766263008118},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6402866840362549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6299964785575867},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6063894033432007},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.565167248249054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5104650259017944},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.340962290763855},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3052837550640106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13249370455741882},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06339097023010254},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3581783.3612106","doi":"https://doi.org/10.1145/3581783.3612106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612106","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612106","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.03670","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03670","pdf_url":"https://arxiv.org/pdf/2310.03670","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.2310.03670","doi":"https://doi.org/10.48550/arxiv.2310.03670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.03670","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":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612106","doi":"https://doi.org/10.1145/3581783.3612106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612106","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612106","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8283459870","display_name":null,"funder_award_id":"62203476","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387436633.pdf","grobid_xml":"https://content.openalex.org/works/W4387436633.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W2518108298","https://openalex.org/W2553307952","https://openalex.org/W2560609797","https://openalex.org/W2560722161","https://openalex.org/W2624503621","https://openalex.org/W2626778328","https://openalex.org/W2796426482","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2947713925","https://openalex.org/W2963509914","https://openalex.org/W2965373594","https://openalex.org/W2968609420","https://openalex.org/W2979750740","https://openalex.org/W2997337685","https://openalex.org/W2999905431","https://openalex.org/W3005680577","https://openalex.org/W3030163527","https://openalex.org/W3030520226","https://openalex.org/W3034459762","https://openalex.org/W3035524453","https://openalex.org/W3046762217","https://openalex.org/W3094502228","https://openalex.org/W3106566829","https://openalex.org/W3111535274","https://openalex.org/W3116959466","https://openalex.org/W3119708198","https://openalex.org/W3126337491","https://openalex.org/W3126656152","https://openalex.org/W3129873671","https://openalex.org/W3135367836","https://openalex.org/W3155390614","https://openalex.org/W3157424380","https://openalex.org/W3168649818","https://openalex.org/W3170863103","https://openalex.org/W3171007011","https://openalex.org/W3175937066","https://openalex.org/W3197097949","https://openalex.org/W3201095453","https://openalex.org/W3202611145","https://openalex.org/W3211450877","https://openalex.org/W4214755140","https://openalex.org/W4221146303","https://openalex.org/W4221160819","https://openalex.org/W4226002507","https://openalex.org/W4226253852","https://openalex.org/W4234552385","https://openalex.org/W4281732104","https://openalex.org/W4284966156","https://openalex.org/W4287572671","https://openalex.org/W4287592659","https://openalex.org/W4311992366","https://openalex.org/W4312270234","https://openalex.org/W4312317653","https://openalex.org/W4312367717","https://openalex.org/W4312788538","https://openalex.org/W4312804044","https://openalex.org/W4312980726","https://openalex.org/W4319452690","https://openalex.org/W4386075705","https://openalex.org/W4386221015","https://openalex.org/W4390874324","https://openalex.org/W4394671432","https://openalex.org/W7133191943","https://openalex.org/W7133230951"],"related_works":["https://openalex.org/W4312788538","https://openalex.org/W4390991753","https://openalex.org/W4402979570","https://openalex.org/W4386702739","https://openalex.org/W4387010603","https://openalex.org/W4408354699","https://openalex.org/W4391350246","https://openalex.org/W4385380820","https://openalex.org/W4398787741","https://openalex.org/W7125919208"],"abstract_inverted_index":{"Masked":[0],"Autoencoders":[1],"(MAE)":[2],"have":[3,22],"demonstrated":[4],"promising":[5],"performance":[6],"in":[7,61,186],"self-supervised":[8,83,241],"learning":[9,41,242],"for":[10,77,80,156,196],"both":[11],"2D":[12],"and":[13,32,93,116,210,232,246],"3D":[14],"computer":[15],"vision.":[16],"Nevertheless,":[17],"existing":[18],"MAE-based":[19],"methods":[20],"still":[21],"certain":[23],"drawbacks.":[24],"Firstly,":[25],"the":[26,30,38,48,54,58,62,91,94,103,108,114,117,120,123,133,139,143,154,161,170,176,183,187,197,228,239],"functional":[27],"decoupling":[28],"between":[29,90],"encoder":[31,95,115],"decoder":[33,92,118,136],"is":[34,206],"incomplete,":[35],"which":[36,101],"limits":[37],"encoder's":[39],"representation":[40,106,111,140],"ability.":[42],"Secondly,":[43],"downstream":[44,215],"tasks":[45],"solely":[46],"utilize":[47],"encoder,":[49],"failing":[50],"to":[51,151],"fully":[52],"leverage":[53],"knowledge":[55,184],"acquired":[56],"through":[57],"encoder-decoder":[59],"architecture":[60],"pre-text":[63],"task.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,131,146,190],"propose":[69],"Point":[70],"Regress":[71],"AutoEncoder":[72],"(Point-RAE),":[73],"a":[74,98,192,222],"new":[75,193],"scheme":[76],"regressive":[78],"autoencoders":[79],"point":[81],"cloud":[82],"learning.":[84],"The":[85],"proposed":[86,198],"method":[87],"decouples":[88],"functions":[89],"by":[96,113],"introducing":[97],"mask":[99],"regressor,":[100],"predicts":[102],"masked":[104,125,157,171],"patch":[105,110,126,172],"from":[107,122,160,175],"visible":[109,165],"encoded":[112,162],"reconstructs":[119],"target":[121],"predicted":[124,159],"representation.":[127],"By":[128],"doing":[129],"so,":[130],"minimize":[132],"impact":[134],"of":[135,142,164,182,225],"updates":[137],"on":[138,213,227,235],"space":[141],"encoder.":[144,177],"Moreover,":[145],"introduce":[147],"an":[148],"alignment":[149],"constraint":[150],"ensure":[152],"that":[153,203],"representations":[155,163],"patches,":[158,166],"are":[167,249],"aligned":[168],"with":[169],"presentations":[173],"computed":[174],"To":[178],"make":[179],"full":[180],"use":[181],"learned":[185],"pre-training":[188,209],"stage,":[189],"design":[191],"finetune":[194],"mode":[195],"Point-RAE.":[199],"Extensive":[200],"experiments":[201],"demonstrate":[202],"our":[204,218],"approach":[205],"efficient":[207],"during":[208],"generalizes":[211],"well":[212],"various":[214],"tasks.":[216],"Specifically,":[217],"pre-trained":[219],"models":[220],"achieve":[221],"high":[223],"accuracy":[224,234],"90.28%":[226],"ScanObjectNN":[229],"hardest":[230],"split":[231],"94.1%":[233],"ModelNet40,":[236],"surpassing":[237],"all":[238],"other":[240],"methods.":[243],"Our":[244],"code":[245],"pretrained":[247],"model":[248],"public":[250],"available":[251],"at:":[252],"https://github.com/liuyyy111/Point-RAE.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-09T00:00:00"}