{"id":"https://openalex.org/W4392903246","doi":"https://doi.org/10.1109/icassp48485.2024.10448295","title":"Language-Driven Open-Vocabulary 3D Semantic Segmentation with Knowledge Distillation","display_name":"Language-Driven Open-Vocabulary 3D Semantic Segmentation with Knowledge Distillation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903246","doi":"https://doi.org/10.1109/icassp48485.2024.10448295"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100651962","display_name":"Yuting Wu","orcid":"https://orcid.org/0000-0003-3196-5916"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Wu","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016645126","display_name":"Xian-Feng Han","orcid":"https://orcid.org/0000-0002-4869-4537"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Feng Han","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047341940","display_name":"Guoqiang Xiao","orcid":"https://orcid.org/0000-0003-2165-476X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Xiao","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3320","last_page":"3324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8509924411773682},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6880882382392883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6835587024688721},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6803542971611023},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.671150267124176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6348825097084045},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5756946802139282},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5534510612487793},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5279613733291626},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5151054263114929},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4613044857978821},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11224636435508728},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07506415247917175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509924411773682},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6880882382392883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6835587024688721},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6803542971611023},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.671150267124176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6348825097084045},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5756946802139282},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5534510612487793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5279613733291626},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5151054263114929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4613044857978821},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11224636435508728},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07506415247917175},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8297516908","display_name":null,"funder_award_id":"62002299","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":31,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1665214252","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2963182550","https://openalex.org/W3009201938","https://openalex.org/W3137210930","https://openalex.org/W3177330511","https://openalex.org/W3215626407","https://openalex.org/W4205189682","https://openalex.org/W4312274934","https://openalex.org/W4312818263","https://openalex.org/W4313145913","https://openalex.org/W4366197620","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386076097","https://openalex.org/W4390189960","https://openalex.org/W4390190234","https://openalex.org/W4402716083","https://openalex.org/W6637242042","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6638667902","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6811433417","https://openalex.org/W6851696756","https://openalex.org/W6851768568"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2395910192","https://openalex.org/W2112752961","https://openalex.org/W2113687551"],"abstract_inverted_index":{"3D":[0,11,48],"open-vocabulary":[1],"semantic":[2,58],"segmentation":[3],"is":[4],"a":[5,38,46],"challenge":[6],"in":[7,70,79],"the":[8,53,71,95],"task":[9],"of":[10,75],"scene":[12],"understanding,":[13],"as":[14],"most":[15],"current":[16],"models":[17],"trained":[18],"on":[19,102],"closed-set":[20],"datasets":[21],"struggle":[22],"to":[23,66,81],"effectively":[24],"identify":[25],"categories":[26],"that":[27,110],"were":[28],"not":[29],"seen":[30],"during":[31],"training.":[32],"To":[33],"address":[34],"this,":[35],"we":[36,61],"introduce":[37],"framework":[39],"called":[40],"LSWKD.":[41],"It":[42],"distills":[43],"knowledge":[44],"from":[45],"pre-trained":[47],"open-world":[49],"model,":[50],"thereby":[51],"enhancing":[52],"alignment":[54],"between":[55],"visual":[56],"and":[57,104],"features.":[59],"Furthermore,":[60],"employ":[62],"Point-discriminative":[63],"Contrastive":[64,77],"Learning":[65],"compute":[67],"caption":[68],"loss":[69],"teacher":[72,96],"model":[73],"instead":[74],"CLIP-style":[76],"Loss":[78],"order":[80],"let":[82],"each":[83],"point":[84],"be":[85,122],"supervised":[86],"with":[87,117],"its":[88],"all":[89],"related":[90],"language":[91],"captions,":[92],"which":[93],"improves":[94],"model\u2019s":[97],"performance.":[98],"We":[99],"conducted":[100],"experiments":[101],"ScanNet":[103],"S3DIS":[105],"datasets.":[106],"The":[107],"results":[108],"demonstrate":[109],"our":[111],"approach":[112],"achieves":[113],"better":[114],"hIoU":[115],"compared":[116],"state-of-the-art":[118],"models.":[119],"Code":[120],"will":[121],"released":[123],"at":[124],"https://github.com/wu39848/LSWKD.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}