{"id":"https://openalex.org/W7127647385","doi":"https://doi.org/10.1109/tmm.2026.3654421","title":"Multi-Granularity Superpoint Graph Learning for Weakly Supervised 3D Semantic Segmentation","display_name":"Multi-Granularity Superpoint Graph Learning for Weakly Supervised 3D Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127647385","doi":"https://doi.org/10.1109/tmm.2026.3654421"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3654421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654421","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/A5125047374","display_name":"Yan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Fan","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-5877-8523","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125095435","display_name":"Yu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-4788-8655","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124981521","display_name":"Pengfei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Zhu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030769176","display_name":"Le Hui","orcid":"https://orcid.org/0000-0003-0851-6805"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Hui","raw_affiliation_strings":["Shaanxi Key Laboratory of Information Acquisition and Processing, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0851-6805","affiliations":[{"raw_affiliation_string":"Shaanxi Key Laboratory of Information Acquisition and Processing, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079434039","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0002-9157-838X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9157-838X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072082954","display_name":"Bin Xiao","orcid":"https://orcid.org/0000-0002-2108-152X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xiao","raw_affiliation_strings":["Department of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-8469-5302","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121896344","display_name":"Qinghua Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Hu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7765-8095","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15849543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"4245","last_page":"4258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9315999746322632,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9315999746322632,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.004399999976158142,"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/segmentation","display_name":"Segmentation","score":0.5878000259399414},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5730999708175659},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5253000259399414},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5238999724388123},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48899999260902405},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44449999928474426},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.3978999853134155},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.39579999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6111999750137329},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3654421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654421","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/G1585402135","display_name":null,"funder_award_id":"62222608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3286624083","display_name":null,"funder_award_id":"62476195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4898710334","display_name":null,"funder_award_id":"24JCYBJC00950","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G5070492027","display_name":null,"funder_award_id":"U23B2049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G549457566","display_name":null,"funder_award_id":"2022ZD0116500","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5651682600","display_name":null,"funder_award_id":"24YDTPJC00150","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G7077580569","display_name":null,"funder_award_id":"62436002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7168322241","display_name":null,"funder_award_id":"62306238","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1,193,224],"3D":[2],"semantic":[3,36],"segmentation":[4],"has":[5],"proven":[6],"effective":[7],"in":[8,53,155],"alleviating":[9],"the":[10,23,29,34,74,83,98,103,114,122,136,139,165,187,202],"heavy":[11],"dependence":[12],"on":[13,97,182],"dense":[14],"annotations":[15],"by":[16,204],"generating":[17],"high-quality":[18,130],"pseudo-labels.":[19],"However,":[20],"due":[21],"to":[22,81,101,120,171,221],"scene":[24,170],"complexity":[25],"and":[26,47,175,200],"disorder":[27],"of":[28,78,85,107,125,138,164,207],"point":[30,79,229],"cloud,":[31],"merely":[32],"applying":[33],"model":[35],"prediction":[37],"or":[38,146],"hand-crafted":[39],"feature":[40],"similarity":[41],"for":[42,231],"pseudo":[43,55,86,131],"labeling":[44],"is":[45,118,159],"inefficient":[46],"biased.":[48],"This":[49,157],"limitation":[50],"inevitably":[51],"results":[52],"incorrect":[54],"labels.":[56,87,132],"To":[57,133],"tackle":[58],"this":[59],"challenge,":[60],"we":[61,149],"propose":[62],"a":[63,91,151,173],"new":[64],"method":[65,189],"called":[66],"Multi-granularity":[67],"Superpoint":[68],"Graph":[69],"Learning":[70],"(MSGL)":[71],"that":[72,186],"leverages":[73],"multi-scale":[75],"local":[76,93],"features":[77],"clouds":[80],"improve":[82],"quality":[84],"We":[88],"first":[89],"design":[90],"multi-granularity":[92,152],"representation":[94,141],"learning":[95,177],"module":[96,142],"superpoint":[99,109,166],"graph":[100,167],"capture":[102],"neighboring":[104],"structure":[105],"information":[106],"each":[108,169,232],"within":[110,168],"complex":[111],"scenes.":[112],"Subsequently,":[113],"generated":[115],"structural":[116,140],"embedding":[117],"utilized":[119],"enhance":[121],"affinity":[123],"matrix":[124],"label":[126,198],"propagation,":[127],"thereby":[128],"yielding":[129],"further":[134],"enforce":[135],"generalization":[137],"under":[143,195],"scenario":[144],"changes":[145],"data":[147],"fluctuations,":[148],"present":[150],"consistency":[153],"loss":[154,158],"MSGL.":[156],"applied":[160],"across":[161],"different":[162],"views":[163],"ensure":[172],"robust":[174],"consistent":[176],"process.":[178],"Our":[179],"experiments":[180],"conducted":[181],"three":[183],"benchmarks":[184],"show":[185],"proposed":[188],"outperforms":[190],"existing":[191],"weakly":[192],"methods":[194,225],"several":[196],"sparse":[197],"settings,":[199],"improves":[201],"baseline":[203],"an":[205],"average":[206],"7.7%":[208],"with":[209,226],"only":[210,227],"1%":[211],"extra":[212],"computation":[213],"cost.":[214],"Moreover,":[215],"our":[216],"approach":[217],"even":[218],"compares":[219],"favorably":[220],"some":[222],"fully":[223],"one":[228],"labeled":[230],"thing.":[233]},"counts_by_year":[],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2026-02-06T00:00:00"}