{"id":"https://openalex.org/W4402765050","doi":"https://doi.org/10.3390/s24196166","title":"TAMC: Textual Alignment and Masked Consistency for Open-Vocabulary 3D Scene Understanding","display_name":"TAMC: Textual Alignment and Masked Consistency for Open-Vocabulary 3D Scene Understanding","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4402765050","doi":"https://doi.org/10.3390/s24196166","pmid":"https://pubmed.ncbi.nlm.nih.gov/39409206"},"language":"en","primary_location":{"id":"doi:10.3390/s24196166","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/s24196166","pdf_url":"https://www.mdpi.com/1424-8220/24/19/6166/pdf?version=1727168847","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/19/6166/pdf?version=1727168847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107916241","display_name":"Juan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Juan Wang","raw_affiliation_strings":["Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002859625","display_name":"Zhijie Wang","orcid":"https://orcid.org/0000-0003-4420-848X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhijie Wang","raw_affiliation_strings":["RIKEN AIP, Tokyo 1030027, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4420-848X","affiliations":[{"raw_affiliation_string":"RIKEN AIP, Tokyo 1030027, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009192524","display_name":"Tomo Miyazaki","orcid":"https://orcid.org/0000-0001-5205-0542"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomo Miyazaki","raw_affiliation_strings":["Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5205-0542","affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050710691","display_name":"Yaohou Fan","orcid":"https://orcid.org/0009-0006-0558-9733"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yaohou Fan","raw_affiliation_strings":["Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan"],"raw_orcid":"https://orcid.org/0009-0006-0558-9733","affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020830042","display_name":"Shinichiro Omachi","orcid":"https://orcid.org/0000-0001-7706-9995"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shinichiro Omachi","raw_affiliation_strings":["Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7706-9995","affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Graduate School of Engineering, Tohoku University, Sendai 9808579, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020830042"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.3399,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.554545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"19","first_page":"6166","last_page":"6166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9991999864578247,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7923455238342285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7771762013435364},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7153602838516235},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6836363077163696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6735769510269165},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6523208022117615},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6138662695884705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5945277810096741},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5663774013519287},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5165873765945435},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4520256519317627},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4055154323577881},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34386420249938965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3362342119216919},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3262142241001129}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7923455238342285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771762013435364},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7153602838516235},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6836363077163696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6735769510269165},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6523208022117615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6138662695884705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5945277810096741},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5663774013519287},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5165873765945435},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4520256519317627},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4055154323577881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34386420249938965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3362342119216919},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3262142241001129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s24196166","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/s24196166","pdf_url":"https://www.mdpi.com/1424-8220/24/19/6166/pdf?version=1727168847","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:39409206","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39409206","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11478597","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11478597","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11478597/pdf/sensors-24-06166.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:65d8d837a3874ec4b4e9705a1c24ff92","is_oa":true,"landing_page_url":"https://doaj.org/article/65d8d837a3874ec4b4e9705a1c24ff92","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 24, Iss 19, p 6166 (2024)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/24/19/6166/","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24196166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s24196166","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/s24196166","pdf_url":"https://www.mdpi.com/1424-8220/24/19/6166/pdf?version=1727168847","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G4365181739","display_name":null,"funder_award_id":"JPMJSP2114","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402765050.pdf","grobid_xml":"https://content.openalex.org/works/W4402765050.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2594519801","https://openalex.org/W2797997528","https://openalex.org/W2903179262","https://openalex.org/W2938428612","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2963231572","https://openalex.org/W2963640720","https://openalex.org/W3034999214","https://openalex.org/W3035086574","https://openalex.org/W3035472394","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3171433839","https://openalex.org/W3193423746","https://openalex.org/W3204832889","https://openalex.org/W4206398307","https://openalex.org/W4284961860","https://openalex.org/W4312274934","https://openalex.org/W4312458986","https://openalex.org/W4312559104","https://openalex.org/W4312747482","https://openalex.org/W4312960937","https://openalex.org/W4313145913","https://openalex.org/W4313156423","https://openalex.org/W4376275089","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4390874324","https://openalex.org/W4402716083","https://openalex.org/W6811433417"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W3134559341","https://openalex.org/W4385570385"],"abstract_inverted_index":{"Three-dimensional":[0],"(3D)":[1],"Scene":[2],"Understanding":[3],"achieves":[4],"environmental":[5],"perception":[6],"by":[7],"extracting":[8],"and":[9,34,76,112,142,170,192],"analyzing":[10],"point":[11,37,70],"cloud":[12,38,71],"data":[13,72],"with":[14,90,145],"wide":[15],"applications":[16],"including":[17],"virtual":[18],"reality,":[19],"robotics,":[20],"etc.":[21],"Previous":[22],"methods":[23,51],"align":[24,143,189],"the":[25,35,41,53,58,64,80,91,96,108,122,126,135,146,150,166,185,201],"2D":[26,113,162],"image":[27,163],"feature":[28,39,60],"from":[29],"a":[30,101,158,173,181],"pre-trained":[31],"CLIP":[32],"model":[33,123,175],"3D":[36,59,111,118,132,147,168],"for":[40,160],"open":[42],"vocabulary":[43],"scene":[44,128,169],"understanding":[45],"ability.":[46],"We":[47],"believe":[48],"that":[49],"existing":[50],"have":[52],"following":[54],"two":[55],"deficiencies:":[56],"(1)":[57],"extraction":[61],"process":[62],"ignores":[63],"challenges":[65],"of":[66,110,184,203],"real":[67],"scenarios,":[68],"i.e.,":[69],"are":[73],"very":[74],"sparse":[75],"even":[77],"incomplete;":[78],"(2)":[79],"training":[81,104,151],"stage":[82],"lacks":[83],"direct":[84],"text":[85],"supervision,":[86],"leading":[87],"to":[88,120,124,165,176],"inconsistency":[89],"inference":[92],"stage.":[93],"To":[94],"address":[95],"first":[97,156],"issue,":[98,137],"we":[99,115,138,155,188],"employ":[100],"Masked":[102],"Consistency":[103],"policy.":[105],"Specifically,":[106],"during":[107,149,196],"alignment":[109],"features,":[114],"mask":[116],"some":[117],"features":[119,148,191,194],"force":[121],"understand":[125],"entire":[127],"using":[129],"only":[130],"partial":[131],"features.":[133],"For":[134],"second":[136],"generate":[139,157],"pseudo-text":[140],"labels":[141],"them":[144],"process.":[152],"In":[153],"particular,":[154],"description":[159,183],"each":[161],"belonging":[164],"same":[167],"then":[171],"use":[172],"summarization":[174],"fuse":[177],"these":[178],"descriptions":[179],"into":[180],"single":[182],"scene.":[186],"Subsequently,":[187],"2D-3D":[190],"3D-text":[193],"simultaneously":[195],"training.":[197],"Massive":[198],"experiments":[199],"demonstrate":[200],"effectiveness":[202],"our":[204],"method,":[205],"outperforming":[206],"state-of-the-art":[207],"approaches.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}