{"id":"https://openalex.org/W4387010603","doi":"https://doi.org/10.1109/tmm.2023.3317998","title":"Inter-Modal Masked Autoencoder for Self-Supervised Learning on Point Clouds","display_name":"Inter-Modal Masked Autoencoder for Self-Supervised Learning on Point Clouds","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387010603","doi":"https://doi.org/10.1109/tmm.2023.3317998"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3317998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3317998","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/A5100440985","display_name":"Jiaming Liu","orcid":"https://orcid.org/0009-0003-9699-1987"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Liu","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-9699-1987","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009576623","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0002-3459-5079"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3459-5079","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091227928","display_name":"Maoguo Gong","orcid":"https://orcid.org/0000-0002-0415-8556"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoguo Gong","raw_affiliation_strings":["School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0415-8556","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706710","display_name":"Zhixiao Liu","orcid":"https://orcid.org/0009-0007-3517-9556"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]},{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiao Liu","raw_affiliation_strings":["Yantai Research Institute, Harbin Engineering University, Yantai, China"],"raw_orcid":"https://orcid.org/0009-0007-3517-9556","affiliations":[{"raw_affiliation_string":"Yantai Research Institute, Harbin Engineering University, Yantai, China","institution_ids":["https://openalex.org/I151727225","https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213763","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0001-6766-8310"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-6766-8310","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065027008","display_name":"Wenping Ma","orcid":"https://orcid.org/0000-0001-8872-2195"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenping Ma","raw_affiliation_strings":["School of Artificial Intelligence, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8872-2195","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7036,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.94826579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"3897","last_page":"3908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.9951000213623047,"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/point-cloud","display_name":"Point cloud","score":0.8800913095474243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032945394515991},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.789024829864502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6696155071258545},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4762152135372162},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45431092381477356},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43634432554244995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4221889078617096},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41807591915130615},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3739606738090515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35688018798828125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16478168964385986}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8800913095474243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032945394515991},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.789024829864502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696155071258545},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4762152135372162},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45431092381477356},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43634432554244995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4221889078617096},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41807591915130615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3739606738090515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35688018798828125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16478168964385986},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3317998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3317998","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":[],"awards":[{"id":"https://openalex.org/G1949608614","display_name":null,"funder_award_id":"62036006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G731801172","display_name":null,"funder_award_id":"62276200","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":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W2108598243","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2553307952","https://openalex.org/W2738724892","https://openalex.org/W2945957791","https://openalex.org/W2963158438","https://openalex.org/W2963231572","https://openalex.org/W2979750740","https://openalex.org/W2981440248","https://openalex.org/W2990613095","https://openalex.org/W2998091191","https://openalex.org/W3035524453","https://openalex.org/W3092198590","https://openalex.org/W3094502228","https://openalex.org/W3111535274","https://openalex.org/W3116959466","https://openalex.org/W3119708198","https://openalex.org/W3131096279","https://openalex.org/W3152836822","https://openalex.org/W3153465022","https://openalex.org/W3156072581","https://openalex.org/W3157424380","https://openalex.org/W3158405343","https://openalex.org/W3159746229","https://openalex.org/W3166573884","https://openalex.org/W3167071962","https://openalex.org/W3171007011","https://openalex.org/W3171433839","https://openalex.org/W3176463841","https://openalex.org/W3194137276","https://openalex.org/W3201221410","https://openalex.org/W3202611145","https://openalex.org/W3205586691","https://openalex.org/W4200631318","https://openalex.org/W4214574722","https://openalex.org/W4214644223","https://openalex.org/W4214755140","https://openalex.org/W4287025408","https://openalex.org/W4288089799","https://openalex.org/W4295700816","https://openalex.org/W4302356851","https://openalex.org/W4312270234","https://openalex.org/W4312317653","https://openalex.org/W4312442876","https://openalex.org/W4312788538","https://openalex.org/W4312804044","https://openalex.org/W4312903973","https://openalex.org/W4312980726","https://openalex.org/W4313145913","https://openalex.org/W4313156423","https://openalex.org/W4316660744","https://openalex.org/W4319336452","https://openalex.org/W4366197547","https://openalex.org/W4367663338","https://openalex.org/W4380079737","https://openalex.org/W4382658005","https://openalex.org/W4385245566","https://openalex.org/W4386075863","https://openalex.org/W4390872658","https://openalex.org/W4390874204","https://openalex.org/W4394671432","https://openalex.org/W6687484953","https://openalex.org/W6726945602","https://openalex.org/W6739778489","https://openalex.org/W6747899497","https://openalex.org/W6748208425","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763103765","https://openalex.org/W6763422710","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6779879114","https://openalex.org/W6796918728","https://openalex.org/W6839294089","https://openalex.org/W6839446344","https://openalex.org/W6852340613"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Masked":[0],"autoencoder":[1,112],"(MAE)":[2],"is":[3,38,58,113,193],"a":[4,73,89,109],"recently":[5],"widely":[6],"used":[7],"self-supervised":[8,78,204],"learning":[9,79,156,205],"method":[10,76],"that":[11,169,176],"has":[12],"achieved":[13,194],"great":[14],"success":[15],"in":[16,54,183],"NLP":[17],"and":[18,64,101,118,122,179,197],"computer":[19],"vision.":[20],"However,":[21],"the":[22,46,128,135,158,162,170,212,215],"potential":[23],"advantages":[24],"of":[25,99,104,161,191,217],"masked":[26,105,136,222],"pre-training":[27],"for":[28,60,77,211],"point":[29,43,81,93,106,130,137,149,164,223],"cloud":[30,150],"understanding":[31],"have":[32],"not":[33],"been":[34],"fully":[35],"explored.":[36],"There":[37],"preliminary":[39],"work":[40,209],"on":[41,80,146,195,199],"MAE-based":[42],"clouds":[44,94],"using":[45],"Transformer":[47],"architecture":[48],"to":[49,91,133,152,221],"explore":[50],"low-level":[51],"geometric":[52],"representations":[53],"3D":[55],"space,":[56],"which":[57],"insufficient":[59],"fine-grained":[61],"decoding":[62],"completion":[63],"downstream":[65,185],"tasks.":[66,186],"Inspired":[67],"by":[68,115],"multimodality,":[69],"we":[70,84,141],"propose":[71],"Inter-MAE,":[72],"inter-modal":[74,154],"MAE":[75],"clouds.":[82,224],"Specifically,":[83],"first":[85,213],"use":[86],"Point-MAE":[87],"as":[88],"baseline":[90],"partition":[92],"into":[95],"random":[96],"low":[97],"percentage":[98,103],"visible":[100,129],"high":[102],"patches.":[107,138,165],"Then,":[108],"standard":[110],"Transformer-based":[111],"built":[114],"asymmetric":[116],"design":[117],"shifting":[119],"mask":[120],"operations,":[121],"latent":[123],"features":[124,144,160],"are":[125,177],"learned":[126],"from":[127],"patches":[131],"aiming":[132],"recover":[134],"In":[139],"addition,":[140],"generate":[142],"image":[143,219],"based":[145],"ViT":[147],"after":[148],"rendering":[151],"form":[153],"contrastive":[155],"with":[157],"decoded":[159],"completed":[163],"Extensive":[166],"experiments":[167],"show":[168],"proposed":[171],"Inter-MAE":[172],"generates":[173],"pre-trained":[174],"models":[175],"effective":[178],"exhibit":[180],"superior":[181],"results":[182],"various":[184],"For":[187],"example,":[188],"an":[189],"accuracy":[190],"85.4%":[192],"ScanObjectNN":[196],"86.3%":[198],"ShapeNetPart,":[200],"outperforming":[201],"other":[202],"state-of-the-art":[203],"methods.":[206],"Notably,":[207],"our":[208],"establishes":[210],"time":[214],"feasibility":[216],"applying":[218],"modality":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}