{"id":"https://openalex.org/W4403791339","doi":"https://doi.org/10.1145/3664647.3680667","title":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","display_name":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791339","doi":"https://doi.org/10.1145/3664647.3680667"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.01781","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108814907","display_name":"Duc Trong Tran","orcid":"https://orcid.org/0009-0002-5028-7807"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Duc Dang Trung Tran","raw_affiliation_strings":["Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032328702","display_name":"Byeongkeun Kang","orcid":"https://orcid.org/0000-0003-2537-7720"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongkeun Kang","raw_affiliation_strings":["Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","Seoul National University of Science and Technology Department of Electrical and Information Engineering Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]},{"raw_affiliation_string":"Seoul National University of Science and Technology Department of Electrical and Information Engineering Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004957625","display_name":"Yeejin Lee","orcid":"https://orcid.org/0000-0002-3439-5042"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeejin Lee","raw_affiliation_strings":["Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","Seoul National University of Science and Technology Department of Electronic Engineering Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]},{"raw_affiliation_string":"Seoul National University of Science and Technology Department of Electronic Engineering Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108814907"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":null,"apc_paid":null,"fwci":1.148,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75491061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1467","last_page":"1475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9933000206947327,"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":0.6386488676071167},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5208954811096191},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4657737910747528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4592234492301941},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09177091717720032},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07967838644981384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6386488676071167},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5208954811096191},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4657737910747528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4592234492301941},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09177091717720032},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07967838644981384}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.01781","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.01781","pdf_url":"https://arxiv.org/pdf/2411.01781","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.01781","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.01781","pdf_url":"https://arxiv.org/pdf/2411.01781","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2546696630","https://openalex.org/W2594519801","https://openalex.org/W2740388794","https://openalex.org/W2904332125","https://openalex.org/W2955058313","https://openalex.org/W2963182550","https://openalex.org/W2963281829","https://openalex.org/W2964044605","https://openalex.org/W2964266557","https://openalex.org/W2990295915","https://openalex.org/W2995182785","https://openalex.org/W3034430142","https://openalex.org/W3034550906","https://openalex.org/W3034949383","https://openalex.org/W3137905681","https://openalex.org/W3172351327","https://openalex.org/W3204034406","https://openalex.org/W4214773923","https://openalex.org/W4221154304","https://openalex.org/W4296550876","https://openalex.org/W4312274934","https://openalex.org/W4312312588","https://openalex.org/W4312327508","https://openalex.org/W4312649925","https://openalex.org/W4313166301","https://openalex.org/W4319300613","https://openalex.org/W4382457953","https://openalex.org/W4383109105","https://openalex.org/W4386076523","https://openalex.org/W4390872957","https://openalex.org/W4390873582","https://openalex.org/W4390873929","https://openalex.org/W4394593003"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"transformer-based":[1],"techniques":[2],"incorporating":[3],"superpoints":[4],"have":[5],"become":[6],"prevalent":[7],"in":[8],"3D":[9,94],"instance":[10,95],"segmentation.":[11],"However,":[12],"they":[13],"often":[14],"encounter":[15],"an":[16],"over-segmentation":[17],"problem,":[18],"especially":[19],"noticeable":[20],"with":[21,68],"large":[22],"objects.":[23],"Additionally,":[24],"unreliable":[25],"mask":[26,31],"predictions":[27],"stemming":[28],"from":[29],"superpoint":[30],"prediction":[32],"further":[33],"compound":[34],"this":[35],"issue.":[36],"To":[37],"address":[38],"these":[39],"challenges,":[40],"we":[41],"propose":[42],"a":[43,55,65,69,73],"novel":[44],"framework":[45],"called":[46],"MSTA3D.":[47],"It":[48],"leverages":[49],"multi-scale":[50],"feature":[51],"representation":[52],"and":[53,85],"introduces":[54],"twin-attention":[56],"mechanism":[57],"to":[58],"effectively":[59],"capture":[60],"them.":[61],"Furthermore,":[62],"MSTA3D":[63],"integrates":[64],"box":[66,70],"query":[67],"regularizer,":[71],"offering":[72],"complementary":[74],"spatial":[75],"constraint":[76],"alongside":[77],"semantic":[78],"queries.":[79],"Experimental":[80],"evaluations":[81],"on":[82],"ScanNetV2,":[83],"ScanNet200":[84],"S3DIS":[86],"datasets":[87],"demonstrate":[88],"that":[89],"our":[90],"approach":[91],"surpasses":[92],"state-of-the-art":[93],"segmentation":[96],"methods.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}