{"id":"https://openalex.org/W7137853434","doi":"https://doi.org/10.1609/aaai.v40i13.38026","title":"Point-SRA: Self-Representation Alignment for 3D Representation Learning","display_name":"Point-SRA: Self-Representation Alignment for 3D Representation Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137853434","doi":"https://doi.org/10.1609/aaai.v40i13.38026"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38026","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38026","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38026/41988","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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38026/41988","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122179315","display_name":"Lintong Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lintong Wei","raw_affiliation_strings":["School of Electronics and Information, Xi\u2019an Polytechnic University"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi\u2019an Polytechnic University","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697157","display_name":"Jian Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Lu","raw_affiliation_strings":["School of Electronics and Information, Xi\u2019an Polytechnic University"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi\u2019an Polytechnic University","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102741029","display_name":"Haozhe Cheng","orcid":"https://orcid.org/0000-0002-8723-9924"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Cheng","raw_affiliation_strings":["School of Software, Xi\u2019an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129649813","display_name":"Jihua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["School of Software, Xi\u2019an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"School of Software, Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129710490","display_name":"Kaibing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaibing Zhang","raw_affiliation_strings":["School of Computer Science, Xi\u2019an Polytechnic University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xi\u2019an Polytechnic University","institution_ids":["https://openalex.org/I27599042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5122179315"],"corresponding_institution_ids":["https://openalex.org/I27599042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08283582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10539","last_page":"10547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2651999890804291,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2651999890804291,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.11500000208616257,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09099999815225601,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.7412999868392944},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5928000211715698},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5896999835968018},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5618000030517578},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5472000241279602},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.38440001010894775},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7412999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6639999747276306},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5618000030517578},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.38440001010894775},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38026","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38026","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38026/41988","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,"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38026","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38026","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38026/41988","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137853434.pdf","grobid_xml":"https://content.openalex.org/works/W7137853434.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Masked":[0],"autoencoders":[1],"(MAE)":[2],"have":[3],"become":[4],"a":[5,54,115,132],"dominant":[6],"paradigm":[7],"in":[8,109],"3D":[9,55,169],"representation":[10,56],"learning,":[11],"setting":[12],"new":[13],"performance":[14],"benchmarks":[15],"across":[16],"various":[17],"downstream":[18],"tasks.":[19],"Existing":[20],"methods":[21],"with":[22,42],"fixed":[23],"mask":[24],"ratios":[25,74],"neglect":[26],"multi-level":[27],"representational":[28],"correlations":[29],"and":[30,66,82,126,164],"intrinsic":[31],"geometric":[32,81],"structures,":[33],"while":[34,85],"relying":[35],"on":[36,151],"point-wise":[37],"reconstruction":[38],"assumptions":[39],"that":[40,103],"conflict":[41],"the":[43,76,86,124,139],"diversity":[44],"of":[45],"point":[46,140],"cloud.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52,70,130],"propose":[53],"learning":[57],"method,":[58],"termed":[59],"Point-SRA,":[60],"which":[61],"aligns":[62],"representations":[63,104],"through":[64],"self-distillation":[65],"probabilistic":[67,97],"modeling.":[68],"Specifically,":[69],"assign":[71],"different":[72,106],"masking":[73],"to":[75,78,94,136],"MAE":[77,125],"capture":[79],"complementary":[80],"semantic":[83],"information,":[84],"MeanFlow":[87],"Transformer":[88],"(MFT)":[89],"leverages":[90],"cross-modal":[91],"conditional":[92],"embeddings":[93],"enable":[95],"diverse":[96],"reconstruction.":[98],"Our":[99],"analysis":[100],"further":[101],"reveals":[102],"at":[105,122],"time":[107],"steps":[108],"MFT":[110,127],"also":[111],"exhibit":[112],"complementarity.":[113],"Therefore,":[114],"Dual":[116],"Self-Representation":[117],"Alignment":[118],"mechanism":[119],"is":[120],"proposed":[121],"both":[123],"levels.":[128],"Finally,":[129],"design":[131],"Flow-Conditioned":[133],"Fine-Tuning":[134],"Architecture":[135],"fully":[137],"exploit":[138],"cloud":[141],"distribution":[142],"learned":[143],"via":[144],"MeanFlow.":[145],"Point-SRA":[146,172],"outperforms":[147],"Point-MAE":[148],"by":[149,178],"5.37%":[150],"ScanObjectNN.":[152],"On":[153],"intracranial":[154],"aneurysm":[155],"segmentation,":[156],"it":[157],"reaches":[158],"96.07%":[159],"mean":[160],"IoU":[161],"for":[162,166],"arteries":[163],"86.87%":[165],"aneurysms.":[167],"For":[168],"object":[170],"detection,":[171],"achieves":[173],"47.3%":[174],"AP@50,":[175],"surpassing":[176],"MaskPoint":[177],"5.12%.":[179]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}