{"id":"https://openalex.org/W7162015178","doi":"https://doi.org/10.48550/arxiv.2605.20737","title":"Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors","display_name":"Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162015178","doi":"https://doi.org/10.48550/arxiv.2605.20737"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102375313","display_name":"Wei Siqi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136665198","display_name":"Hongbin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hongbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136720039","display_name":"Feng Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136659541","display_name":"Tian Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136671380","display_name":"Chun Kit Calvin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136620675","display_name":"Ming Li","orcid":"https://orcid.org/0000-0001-8415-7010"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064063888","display_name":"Qiuxia Wu","orcid":"https://orcid.org/0000-0002-2284-7806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Qiuxia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9312000274658203,"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":0.9312000274658203,"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":0.016599999740719795,"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":0.004000000189989805,"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/prior-probability","display_name":"Prior probability","score":0.817300021648407},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7042999863624573},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.621399998664856},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6047999858856201},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6004999876022339},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4864000082015991},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/minor","display_name":"Minor (academic)","score":0.4140999913215637}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.817300021648407},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754999756813049},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.621399998664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176000237464905},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5512999892234802},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2779760435","wikidata":"https://www.wikidata.org/wiki/Q5396169","display_name":"Minor (academic)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7731435298919678,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"approaches":[1],"for":[2,93,155],"unsupervised":[3,71],"3D":[4,72,198],"point":[5,199],"cloud":[6],"segmentation":[7],"predominantly":[8],"rely":[9],"on":[10,160],"a":[11,20,27,51,128],"purely":[12,98],"visual":[13,99],"similarity-based":[14],"learning-by-clustering":[15],"paradigm,":[16,28],"which":[17],"suffers":[18],"from":[19,112,145],"fundamental":[21],"limitation:":[22],"long-tail":[23,68],"ambiguity.":[24],"In":[25],"such":[26],"features":[29],"of":[30,97,187,194],"minor":[31,89,143],"classes":[32,144,196],"are":[33,125],"consistently":[34,168],"absorbed":[35,147],"by":[36,148,172],"dominant":[37,102,149],"clusters,":[38,150],"leading":[39],"to":[40,66,78],"severely":[41],"imbalanced":[42],"predictions.":[43],"To":[44],"address":[45],"this":[46],"issue,":[47],"we":[48],"propose":[49],"LangTail,":[50],"language-guided":[52],"hierarchical":[53,129],"learning":[54],"framework":[55,131],"that":[56,166],"leverages":[57],"the":[58,94,185,192],"balanced":[59,116],"world":[60,119],"knowledge":[61,120],"encoded":[62],"in":[63,70,190,197],"language":[64,113,188],"models":[65],"mitigate":[67],"ambiguity":[69],"segmentation.":[73],"The":[74,201],"key":[75],"idea":[76],"is":[77],"establish":[79],"multi-level":[80],"associations":[81],"between":[82],"language-derived":[83],"semantic":[84,110,138],"priors":[85,124,189],"and":[86,117,141,163,178],"visually":[87],"underrepresented":[88,156],"classes,":[90],"thereby":[91],"compensating":[92],"biased":[95],"attention":[96],"clustering":[100,130],"toward":[101],"classes.":[103],"Specifically,":[104],"LangTail":[105,167],"first":[106],"constructs":[107],"an":[108],"entity-level":[109],"prior":[111],"models,":[114],"capturing":[115],"fine-grained":[118],"across":[121],"categories.":[122,157],"These":[123,182],"injected":[126],"into":[127],"via":[132],"contrastive":[133],"alignment.":[134],"This":[135],"guides":[136],"multi-granularity":[137],"structure":[139],"formation":[140],"prevents":[142],"being":[146],"yielding":[151],"more":[152],"discriminative":[153],"representations":[154],"Extensive":[158],"experiments":[159],"ScanNet-v2,":[161],"S3DIS,":[162],"nuScenes":[164],"demonstrate":[165,184],"outperforms":[169],"existing":[170],"methods":[171],"significant":[173],"margins,":[174],"\\ie,":[175],"+13.5,":[176],"+12.9,":[177],"+8.9":[179],"mIoU,":[180],"respectively.":[181],"results":[183],"effectiveness":[186],"improving":[191],"representation":[193],"minority":[195],"clouds.":[200],"code":[202],"will":[203],"be":[204],"released":[205],"at:":[206],"https://github.com/Whisky0129/langtail_official.":[207]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}