{"id":"https://openalex.org/W4387969559","doi":"https://doi.org/10.1145/3581783.3612107","title":"Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation","display_name":"Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969559","doi":"https://doi.org/10.1145/3581783.3612107"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101477578","display_name":"Yuanbin Wang","orcid":"https://orcid.org/0000-0003-1077-8142"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanbin Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024226895","display_name":"Shaofei Huang","orcid":"https://orcid.org/0000-0001-8996-9907"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Huang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056297901","display_name":"Yulu Gao","orcid":"https://orcid.org/0000-0002-3895-1288"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulu Gao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779509","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-5702-1254"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084236468","display_name":"Rui Wang","orcid":"https://orcid.org/0009-0001-8423-6170"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016509766","display_name":"Kehua Sheng","orcid":"https://orcid.org/0009-0008-3370-7711"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehua Sheng","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102736982","display_name":"Bo Zhang","orcid":"https://orcid.org/0009-0005-3354-8018"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101477578"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.8981,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88243584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3745","last_page":"3754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9973999857902527,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7539045214653015},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7219000458717346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6660785675048828},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6597725749015808},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6566139459609985},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6188539862632751},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5226659178733826},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4320133328437805},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4258941411972046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42139673233032227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37907710671424866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12332695722579956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539045214653015},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7219000458717346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660785675048828},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6597725749015808},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6566139459609985},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6188539862632751},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5226659178733826},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4320133328437805},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4258941411972046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42139673233032227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37907710671424866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12332695722579956},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5696407354","display_name":null,"funder_award_id":"62122010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2924485953","https://openalex.org/W2927958594","https://openalex.org/W2981856165","https://openalex.org/W2982166103","https://openalex.org/W2997006708","https://openalex.org/W3092946149","https://openalex.org/W3092960051","https://openalex.org/W3109154950","https://openalex.org/W3177330511","https://openalex.org/W3212887756","https://openalex.org/W4205189682","https://openalex.org/W4310557340","https://openalex.org/W4312414163","https://openalex.org/W4312912313","https://openalex.org/W4313128851","https://openalex.org/W4386065742","https://openalex.org/W4386075580","https://openalex.org/W6600212061","https://openalex.org/W6600708310"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W3016928466","https://openalex.org/W4389574804","https://openalex.org/W4390516098","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W2936725271","https://openalex.org/W4399442168","https://openalex.org/W2114282491","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Traditional":[0],"3D":[1,58,108,128,161],"segmentation":[2,60,72,162,215],"methods":[3,191],"can":[4],"only":[5],"recognize":[6],"a":[7,75,115],"fixed":[8],"range":[9],"of":[10,29,147,168,181],"classes":[11,149],"that":[12],"appear":[13],"in":[14,22,44,86,209],"the":[15,27,45,82,141,153,160,166,169,210],"training":[16],"set,":[17],"which":[18],"limits":[19],"their":[20,41],"application":[21],"real-world":[23],"scenarios":[24],"due":[25],"to":[26,54,57,80,88,124,164],"lack":[28],"generalization":[30,42],"ability.":[31],"Large-scale":[32],"visual-language":[33],"pre-trained":[34,154],"models,":[35],"such":[36],"as":[37,157],"CLIP,":[38],"have":[39],"shown":[40],"ability":[43],"zero-shot":[46,68,193],"2D":[47,106,126],"vision":[48],"tasks,":[49],"but":[50],"are":[51,103,150,175],"still":[52],"unable":[53],"be":[55],"applied":[56],"semantic":[59,71,132,214],"directly.":[61],"In":[62],"this":[63],"work,":[64],"we":[65],"focus":[66],"on":[67,177,197,202],"point":[69,89,182,212],"cloud":[70,90,183,213],"and":[73,95,100,107,127,133,199,204],"propose":[74],"simple":[76],"yet":[77],"effective":[78,111],"baseline":[79],"transfer":[81],"visual-linguistic":[83],"knowledge":[84,112],"implied":[85],"CLIP":[87,155,170],"encoder":[91],"at":[92],"both":[93],"feature":[94],"output":[96,142],"levels.":[97],"Both":[98],"feature-level":[99,138],"output-level":[101],"alignments":[102],"conducted":[104,176],"between":[105],"encoders":[109],"for":[110,137,159,221],"transfer.":[113],"Concretely,":[114],"Multi-granularity":[116],"Cross-modal":[117],"Feature":[118],"Alignment":[119],"(MCFA)":[120],"module":[121],"is":[122],"proposed":[123],"align":[125],"features":[129],"from":[130],"global":[131],"local":[134],"position":[135],"perspectives":[136],"alignment.":[139],"For":[140],"level,":[143],"per-pixel":[144],"pseudo":[145],"labels":[146],"unseen":[148],"extracted":[151],"using":[152],"model":[156,163],"supervision":[158],"mimic":[165],"behavior":[167],"image":[171],"encoder.":[172],"Extensive":[173],"experiments":[174],"two":[178],"popular":[179],"benchmarks":[180],"segmentation.":[184],"Our":[185],"method":[186],"outperforms":[187],"significantly":[188],"previous":[189],"state-of-the-art":[190],"under":[192],"setting":[194],"(+29.2%":[195],"mIoU":[196,201],"SemanticKITTI":[198],"31.8%":[200],"nuScenes),":[203],"further":[205],"achieves":[206],"promising":[207],"results":[208],"annotation-free":[211],"setting,":[216],"showing":[217],"its":[218],"great":[219],"potential":[220],"label-efficient":[222],"learning.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}