{"id":"https://openalex.org/W7129037241","doi":"https://doi.org/10.1109/tcsvt.2026.3664837","title":"LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation","display_name":"LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129037241","doi":"https://doi.org/10.1109/tcsvt.2026.3664837"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3664837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3664837","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Lei Yao","orcid":"https://orcid.org/0009-0007-0304-3056"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Yao","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0007-0304-3056","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Wang","orcid":"https://orcid.org/0000-0001-8659-4724"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8659-4724","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040232431","display_name":"Yawen Cui","orcid":"https://orcid.org/0000-0002-9337-687X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yawen Cui","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9337-687X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Moyun Liu","orcid":"https://orcid.org/0000-0002-4530-2606"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moyun Liu","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4530-2606","affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044722301","display_name":"Lap\u2010Pui Chau","orcid":"https://orcid.org/0000-0003-4932-0593"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lap-Pui Chau","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-4932-0593","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6284,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96809129,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"36","issue":"6","first_page":"7513","last_page":"7525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8119000196456909,"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":0.8119000196456909,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.11060000211000443,"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"}},{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.011599999852478504,"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/initialization","display_name":"Initialization","score":0.6625000238418579},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5065000057220459},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.46389999985694885},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45210000872612},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011000156402588},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.46389999985694885},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4189999997615814},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C13670688","wikidata":"https://www.wikidata.org/wiki/Q3500548","display_name":"Space partitioning","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.26840001344680786},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2669000029563904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3664837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3664837","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Query-based":[0],"3D":[1],"scene":[2,78,180],"instance":[3,138,181],"segmentation":[4],"from":[5,16,66],"point":[6,27],"clouds":[7,28],"has":[8],"attained":[9],"notable":[10],"performance.":[11,52],"However,":[12],"existing":[13],"methods":[14],"suffer":[15],"the":[17,23,63,107,126,141,157,163,208],"query":[18,37,59,64,127],"initialization":[19],"dilemma":[20],"due":[21],"to":[22,61,109,121],"sparse":[24],"nature":[25],"of":[26,143,210],"and":[29,47,73,80,115,146,193,204,215],"rely":[30],"on":[31,111,156,188],"computationally":[32],"intensive":[33],"attention":[34],"mechanisms":[35],"in":[36,177],"decoders.":[38],"We":[39,83],"accordingly":[40],"introduce":[41],"<italic":[42,152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LaSSM</i>,":[44],"prioritizing":[45],"simplicity":[46],"efficiency":[48],"while":[49],"maintaining":[50],"competitive":[51,186],"Specifically,":[53],"we":[54],"propose":[55],"a":[56,86,101,116],"hierarchical":[57],"semantic-spatial":[58],"initializer":[60],"derive":[62],"set":[65,128],"superpoints":[67],"by":[68,129,167],"considering":[69],"both":[70],"semantic":[71],"cues":[72],"spatial":[74,117],"distribution,":[75],"achieving":[76],"comprehensive":[77],"coverage":[79],"accelerated":[81],"convergence.":[82],"further":[84],"present":[85],"coordinate-guided":[87],"state":[88],"space":[89],"model":[90,108],"(SSM)":[91],"decoder":[92,99],"that":[93,105],"progressively":[94],"refines":[95],"queries.":[96],"The":[97,213],"novel":[98],"features":[100],"local":[102],"aggregation":[103],"scheme":[104],"restricts":[106],"focus":[110],"geometrically":[112],"coherent":[113],"regions":[114],"dual-path":[118],"SSM":[119],"block":[120],"capture":[122],"underlying":[123],"dependencies":[124],"within":[125],"integrating":[130],"associated":[131],"coordinates":[132],"information.":[133],"Our":[134],"design":[135],"enables":[136],"efficient":[137],"prediction,":[139],"avoiding":[140],"incorporation":[142],"noisy":[144],"information":[145],"reducing":[147],"redundant":[148],"computation.":[149],"LaSSM":[150,183],"ranks":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">first":[154],"place</i>":[155],"latest":[158],"ScanNet++":[159,194],"V2":[160],"leaderboard,":[161],"outperforming":[162],"previous":[164],"best":[165],"method":[166],"2.5%":[168],"mAP":[169],"with":[170,197],"only":[171],"1/3":[172],"FLOPs,":[173],"demonstrating":[174],"its":[175],"superiority":[176],"challenging":[178],"large-scale":[179],"segmentation.":[182],"also":[184],"achieves":[185],"performance":[187],"ScanNet":[189],"V2,":[190],"ScanNet200,":[191],"S3DIS":[192],"V1":[195],"benchmarks":[196],"less":[198],"computational":[199],"cost.":[200],"Extensive":[201],"ablation":[202],"studies":[203],"qualitative":[205],"results":[206],"validate":[207],"effectiveness":[209],"our":[211],"design.":[212],"code":[214],"weights":[216],"are":[217],"available":[218],"at":[219],"https://github.com/RayYoh/LaSSM.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-14T00:00:00"}