{"id":"https://openalex.org/W4399410938","doi":"https://doi.org/10.1109/tpami.2024.3410324","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","display_name":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399410938","doi":"https://doi.org/10.1109/tpami.2024.3410324","pmid":"https://pubmed.ncbi.nlm.nih.gov/38843054"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3410324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3410324","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hub.hku.hk/handle/10722/351086","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032013734","display_name":"Runyu Ding","orcid":"https://orcid.org/0009-0009-1582-5092"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Runyu Ding","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075014670","display_name":"Jihan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jihan Yang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068548252","display_name":"Chuhui Xue","orcid":"https://orcid.org/0000-0002-3562-3094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuhui Xue","raw_affiliation_strings":["ByteDance Inc, Singapore"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340238","display_name":"Wenqing Zhang","orcid":"https://orcid.org/0000-0003-3479-282X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqing Zhang","raw_affiliation_strings":["ByteDance Inc, Singapore"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562162","display_name":"Song Bai","orcid":"https://orcid.org/0000-0002-2570-9118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Bai","raw_affiliation_strings":["ByteDance Inc, Singapore"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102498323","display_name":"Xiaojuan Qi","orcid":"https://orcid.org/0000-0002-4285-1626"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaojuan Qi","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032013734"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":5.4596,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96781831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"46","issue":"12","first_page":"8517","last_page":"8533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9933000206947327,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9911999702453613,"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":0.6905843019485474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6488414406776428},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39281779527664185},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3748682737350464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905843019485474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488414406776428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39281779527664185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3748682737350464}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3410324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3410324","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38843054","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38843054","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:hub.hku.hk:10722/351086","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/351086","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:hub.hku.hk:10722/351086","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/351086","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W2336961836","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2886641317","https://openalex.org/W2896348597","https://openalex.org/W2924485953","https://openalex.org/W2962759414","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2963517242","https://openalex.org/W2990613095","https://openalex.org/W3009201938","https://openalex.org/W3034949383","https://openalex.org/W3034999214","https://openalex.org/W3035318263","https://openalex.org/W3049293589","https://openalex.org/W3129377622","https://openalex.org/W3171433839","https://openalex.org/W3173859428","https://openalex.org/W3174527233","https://openalex.org/W3176368002","https://openalex.org/W3198790326","https://openalex.org/W3202473909","https://openalex.org/W4200150166","https://openalex.org/W4205189682","https://openalex.org/W4214624153","https://openalex.org/W4312274934","https://openalex.org/W4312424618","https://openalex.org/W4312458986","https://openalex.org/W4312818263","https://openalex.org/W4312912313","https://openalex.org/W4312960937","https://openalex.org/W4313145913","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386075580","https://openalex.org/W4386075819","https://openalex.org/W4386075898","https://openalex.org/W4386076668","https://openalex.org/W4390190234","https://openalex.org/W4390872570","https://openalex.org/W4390872744","https://openalex.org/W4402667898","https://openalex.org/W4402716083","https://openalex.org/W6637242042","https://openalex.org/W6739651123","https://openalex.org/W6739663239","https://openalex.org/W6739778489","https://openalex.org/W6747827861","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763229141","https://openalex.org/W6763578275","https://openalex.org/W6776047415","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802517928","https://openalex.org/W6803567076","https://openalex.org/W6803872405","https://openalex.org/W6811433417","https://openalex.org/W6839015040","https://openalex.org/W6839701648","https://openalex.org/W6849177959","https://openalex.org/W6854061876","https://openalex.org/W6854222408"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Open-world":[0],"instance-level":[1,190],"scene":[2],"understanding":[3],"aims":[4],"to":[5,28,73,79,91,105,117,128,146,163,206],"locate":[6,208],"and":[7,34,124,158,219,225,253],"recognize":[8],"unseen":[9],"object":[10,183],"categories":[11],"that":[12,98,150],"are":[13],"not":[14],"present":[15],"in":[16,46,75,171,240],"the":[17,25,43,51,58,80,130,152,165,172,196,204],"annotated":[18],"dataset.":[19],"This":[20,114,193],"task":[21],"is":[22,50,71],"challenging":[23],"because":[24],"model":[26],"needs":[27],"both":[29],"localize":[30],"novel":[31,169,209],"3D":[32,76,112,122,153,156,216],"objects":[33],"infer":[35],"their":[36],"semantic":[37,241],"categories.":[38],"A":[39],"key":[40],"factor":[41],"for":[42,108,137,168],"recent":[44],"progress":[45],"2D":[47],"open-world":[48,173],"perception":[49],"availability":[52],"of":[53,65,82,111,199],"large-scale":[54],"image-text":[55,103],"pairs":[56,104],"from":[57,102,135],"Internet,":[59],"which":[60,180],"cover":[61],"a":[62,237],"wide":[63],"range":[64],"vocabulary":[66],"concepts.":[67],"However,":[68],"this":[69,87],"success":[70],"hard":[72],"replicate":[74],"scenarios":[77],"due":[78],"scarcity":[81],"3D-text":[83],"pairs.":[84],"To":[85],"address":[86],"challenge,":[88],"we":[89,140,175],"propose":[90],"harness":[92],"pre-trained":[93],"vision-language":[94],"(VL)":[95],"foundation":[96],"models":[97],"encode":[99],"extensive":[100,213],"knowledge":[101],"generate":[106],"captions":[107,136],"multi-view":[109,159],"images":[110],"scenes.":[113],"allows":[115],"us":[116],"establish":[118],"explicit":[119],"associations":[120],"between":[121,155],"shapes":[123],"semantic-rich":[125],"captions.":[126],"Moreover,":[127],"enhance":[129],"fine-grained":[131],"visual-semantic":[132],"representation":[133],"learning":[134],"object-level":[138],"categorization,":[139],"design":[141],"hierarchical":[142],"point-caption":[143],"association":[144],"methods":[145,235],"learn":[147],"semantic-aware":[148],"embeddings":[149],"exploit":[151],"geometry":[154],"points":[157],"images.":[160],"In":[161],"addition,":[162],"tackle":[164],"localization":[166],"challenge":[167],"classes":[170],"setting,":[174],"develop":[176],"debiased":[177],"instance":[178,200,247],"localization,":[179],"involves":[181],"training":[182],"grouping":[184,201],"modules":[185],"on":[186,215],"unlabeled":[187],"data":[188],"using":[189],"pseudo":[191],"supervision.":[192],"significantly":[194],"improves":[195],"generalization":[197],"capabilities":[198],"and,":[202],"thus,":[203],"ability":[205],"accurately":[207],"objects.":[210],"We":[211],"conduct":[212],"experiments":[214],"semantic,":[217],"instance,":[218],"panoptic":[220,254],"segmentation":[221,242,248,255],"tasks,":[222],"covering":[223],"indoor":[224],"outdoor":[226],"scenes":[227],"across":[228],"three":[229],"datasets.":[230],"Our":[231],"method":[232],"outperforms":[233],"baseline":[234],"by":[236],"significant":[238],"margin":[239],"(e.g.":[243,249,256],"34.5%":[244],"\u223c":[245,251,258],"65.3%),":[246],"21.8%":[250],"54.0%),":[252],"14.7%":[257],"43.3%).":[259],"Code":[260],"will":[261],"be":[262],"available.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}