{"id":"https://openalex.org/W4386702739","doi":"https://doi.org/10.1109/tmm.2023.3314973","title":"Masked Autoencoders in 3D Point Cloud Representation Learning","display_name":"Masked Autoencoders in 3D Point Cloud Representation Learning","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4386702739","doi":"https://doi.org/10.1109/tmm.2023.3314973"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3314973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3314973","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5057538157","display_name":"Jincen Jiang","orcid":"https://orcid.org/0000-0002-0150-4644"},"institutions":[{"id":"https://openalex.org/I89652312","display_name":"Northwest A&F University","ror":"https://ror.org/0051rme32","country_code":"CN","type":"education","lineage":["https://openalex.org/I89652312"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jincen Jiang","raw_affiliation_strings":["College of Information Engineering, Northwest A&amp;F University, Yangling, China","College of Information Engineering, Northwest A&amp;F University, China"],"raw_orcid":"https://orcid.org/0000-0002-0150-4644","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, Yangling, China","institution_ids":["https://openalex.org/I89652312"]},{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019288783","display_name":"Xuequan Lu","orcid":"https://orcid.org/0000-0003-0959-408X"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuequan Lu","raw_affiliation_strings":["Department of Computer Science and IT, La Trobe University, Melbourne, VIC, Australia","Department of Computer Science and IT, La Trobe University, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0959-408X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and IT, La Trobe University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I196829312"]},{"raw_affiliation_string":"Department of Computer Science and IT, La Trobe University, Australia","institution_ids":["https://openalex.org/I196829312"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lizhi Zhao","orcid":"https://orcid.org/0000-0001-9475-6682"},"institutions":[{"id":"https://openalex.org/I89652312","display_name":"Northwest A&F University","ror":"https://ror.org/0051rme32","country_code":"CN","type":"education","lineage":["https://openalex.org/I89652312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhi Zhao","raw_affiliation_strings":["College of Information Engineering, Northwest A&amp;F University, Yangling, China","College of Information Engineering, Northwest A&amp;F University, China"],"raw_orcid":"https://orcid.org/0000-0001-9475-6682","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, Yangling, China","institution_ids":["https://openalex.org/I89652312"]},{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111039336","display_name":"Richard Dazaley","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Dazeley","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia","School of Information Technology, Deakin University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6199-9685","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032622366","display_name":"Meili Wang","orcid":"https://orcid.org/0000-0001-7901-1789"},"institutions":[{"id":"https://openalex.org/I89652312","display_name":"Northwest A&F University","ror":"https://ror.org/0051rme32","country_code":"CN","type":"education","lineage":["https://openalex.org/I89652312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meili Wang","raw_affiliation_strings":["College of Information Engineering, Northwest A&amp;F University, Yangling, China","College of Information Engineering, Northwest A&amp;F University, China"],"raw_orcid":"https://orcid.org/0000-0001-7901-1789","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, Yangling, China","institution_ids":["https://openalex.org/I89652312"]},{"raw_affiliation_string":"College of Information Engineering, Northwest A&amp;F University, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057538157"],"corresponding_institution_ids":["https://openalex.org/I89652312"],"apc_list":null,"apc_paid":null,"fwci":4.5911,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96135096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"820","last_page":"831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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":0.9878000020980835,"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":0.9847000241279602,"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/computer-science","display_name":"Computer science","score":0.8325036764144897},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.8111505508422852},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6931529641151428},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.646091103553772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.630374550819397},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5545269846916199},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5514968037605286},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5176454186439514},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5020384788513184},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48834583163261414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44307228922843933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3587105870246887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325036764144897},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8111505508422852},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6931529641151428},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.646091103553772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630374550819397},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5545269846916199},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5514968037605286},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5176454186439514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5020384788513184},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48834583163261414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44307228922843933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587105870246887},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3314973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3314973","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W2553307952","https://openalex.org/W2737234477","https://openalex.org/W2796426482","https://openalex.org/W2810240468","https://openalex.org/W2886499109","https://openalex.org/W2962928871","https://openalex.org/W2963053547","https://openalex.org/W2963123724","https://openalex.org/W2963158438","https://openalex.org/W2963231572","https://openalex.org/W2963443993","https://openalex.org/W2963509914","https://openalex.org/W2963719584","https://openalex.org/W2964228567","https://openalex.org/W2964935548","https://openalex.org/W2979750740","https://openalex.org/W2981440248","https://openalex.org/W2991485494","https://openalex.org/W3009750677","https://openalex.org/W3023371261","https://openalex.org/W3034459762","https://openalex.org/W3035398346","https://openalex.org/W3035524453","https://openalex.org/W3043238202","https://openalex.org/W3094502228","https://openalex.org/W3111535274","https://openalex.org/W3157424380","https://openalex.org/W3203089644","https://openalex.org/W4312270234","https://openalex.org/W4312788538","https://openalex.org/W4312980726","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4385415959","https://openalex.org/W6687484953","https://openalex.org/W6739778489","https://openalex.org/W6748208425","https://openalex.org/W6755207826","https://openalex.org/W6763103765","https://openalex.org/W6763422710","https://openalex.org/W6783272290","https://openalex.org/W6790978476","https://openalex.org/W6796761347","https://openalex.org/W6839294089"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W10861731","https://openalex.org/W2072565696","https://openalex.org/W2050451745"],"abstract_inverted_index":{"Transformer-based":[0],"Self-supervised":[1],"Representation":[2],"Learning":[3],"methods":[4,21,209],"learn":[5,118],"generic":[6],"features":[7,107,121,191],"from":[8,196],"unlabeled":[9],"datasets":[10],"for":[11,17,80,202],"providing":[12],"useful":[13],"network":[14],"initialization":[15],"parameters":[16],"downstream":[18,203],"tasks.":[19],"Recently,":[20],"based":[22],"upon":[23],"masking":[24],"Autoencoders":[25,66],"have":[26],"been":[27],"explored":[28],"in":[29,67],"the":[30,49,86,106,134,152,166,174,182,189],"fields.":[31],"The":[32],"input":[33,87],"can":[34],"be":[35],"intuitively":[36],"masked":[37,65,138],"due":[38,57],"to":[39,51,58,104,117,150],"regular":[40],"content,":[41],"like":[42],"sequence":[43],"words":[44],"and":[45,92,126,172,179,211],"2D":[46],"pixels.":[47],"However,":[48],"extension":[50],"3D":[52,68],"point":[53,69,88,123,154,167,197],"cloud":[54,70,89,124,155,168,198],"is":[55],"challenging":[56],"irregularity.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,112],"propose":[64],"representation":[71],"learning":[72],"(abbreviated":[73],"as":[74,156],"MAE3D),":[75],"a":[76,94,157],"novel":[77],"autoencoding":[78],"paradigm":[79],"self-supervised":[81,161],"learning.":[82],"We":[83,140,159],"first":[84],"split":[85],"into":[90],"patches":[91,125,199],"mask":[93],"portion":[95],"of":[96,108,122,137],"them,":[97],"then":[98,132],"use":[99,141],"our":[100,142,194],"Patch":[101],"Embedding":[102],"Module":[103,146],"extract":[105],"unmasked":[109],"patches.":[110,139],"Secondly,":[111],"employ":[113],"patch-wise":[114],"MAE3D":[115,195],"Transformers":[116],"both":[119],"local":[120,190],"high-level":[127],"contextual":[128],"relationships":[129],"between":[130],"patches,":[131],"complete":[133,151],"latent":[135],"representations":[136],"Point":[143],"Cloud":[144],"Reconstruction":[145],"with":[147,165],"multi-task":[148],"loss":[149],"incomplete":[153],"result.":[158],"conduct":[160],"pre-training":[162],"on":[163,177],"ShapeNet55":[164],"completion":[169],"pre-text":[170],"task":[171],"fine-tune":[173],"pre-trained":[175],"model":[176],"ModelNet40":[178],"ScanObjectNN":[180],"(PB_T50_RS,":[181],"hardest":[183],"variant).":[184],"Comprehensive":[185],"experiments":[186],"demonstrate":[187],"that":[188],"extracted":[192],"by":[193],"are":[200,221],"beneficial":[201],"classification":[204,213],"tasks,":[205],"soundly":[206],"outperforming":[207],"state-of-the-art":[208],"(93.4%":[210],"86.2%":[212],"accuracy,":[214],"respectively).":[215],"<italic":[216],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Our":[218],"source":[219],"codes":[220],"available":[222],"at:":[223],"<uri>https://github.com/Jinec98/MAE3D</uri>.</i>":[224]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}