{"id":"https://openalex.org/W4405778881","doi":"https://doi.org/10.1109/tmm.2024.3521664","title":"Category-Level Multi-Object 9D State Tracking Using Object-Centric Multi-Scale Transformer in Point Cloud Stream","display_name":"Category-Level Multi-Object 9D State Tracking Using Object-Centric Multi-Scale Transformer in Point Cloud Stream","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778881","doi":"https://doi.org/10.1109/tmm.2024.3521664"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521664","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":"https://openalex.org/A5055922003","display_name":"Jingtao Sun","orcid":"https://orcid.org/0000-0001-5087-1304"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingtao Sun","raw_affiliation_strings":["College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025640070","display_name":"Yaonan Wang","orcid":"https://orcid.org/0000-0002-0519-6458"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022848316","display_name":"Mingtao Feng","orcid":"https://orcid.org/0000-0003-0384-3743"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004388046","display_name":"Xiaofeng Guo","orcid":"https://orcid.org/0000-0002-7258-3060"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Guo","raw_affiliation_strings":["College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and National Engineering Research Center for Robot Visual Perception and Control, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control (NERC-RVC), Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036075088","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0002-6375-581X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032262344","display_name":"Xieyuanli Chen","orcid":"https://orcid.org/0000-0003-0955-6681"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xieyuanli Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055922003"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19403469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1072","last_page":"1085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9259999990463257,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9110999703407288,"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":0.7958624362945557},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5250099301338196},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5053501725196838},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4990570545196533},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48027729988098145},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46811336278915405},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.46517300605773926},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4477368891239166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4243716895580292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38254931569099426},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07027280330657959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958624362945557},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5250099301338196},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5053501725196838},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4990570545196533},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48027729988098145},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46811336278915405},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.46517300605773926},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4477368891239166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4243716895580292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38254931569099426},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07027280330657959},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521664","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3703054089","display_name":null,"funder_award_id":"2021JC0004","funder_id":"https://openalex.org/F4320322866","funder_display_name":"Natural Science Foundation of Hainan Province"},{"id":"https://openalex.org/G8190209641","display_name":null,"funder_award_id":"62133005","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"},{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1994380564","https://openalex.org/W2001054718","https://openalex.org/W2105934661","https://openalex.org/W2798270772","https://openalex.org/W2888752296","https://openalex.org/W2903788651","https://openalex.org/W2947689748","https://openalex.org/W2962941647","https://openalex.org/W2963892972","https://openalex.org/W3012271043","https://openalex.org/W3034534268","https://openalex.org/W3034597466","https://openalex.org/W3034739212","https://openalex.org/W3035131925","https://openalex.org/W3091357794","https://openalex.org/W3107372911","https://openalex.org/W3107992529","https://openalex.org/W3109520136","https://openalex.org/W3119686997","https://openalex.org/W3129380256","https://openalex.org/W3132607695","https://openalex.org/W3151772196","https://openalex.org/W3163945288","https://openalex.org/W3167949052","https://openalex.org/W3170294192","https://openalex.org/W3174635123","https://openalex.org/W3180107049","https://openalex.org/W3193686508","https://openalex.org/W3196204376","https://openalex.org/W3196328566","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W3203676240","https://openalex.org/W3205986419","https://openalex.org/W3206934897","https://openalex.org/W3214466318","https://openalex.org/W3217365746","https://openalex.org/W4205105995","https://openalex.org/W4205268584","https://openalex.org/W4206522166","https://openalex.org/W4210344621","https://openalex.org/W4210786150","https://openalex.org/W4213019189","https://openalex.org/W4214526701","https://openalex.org/W4214614183","https://openalex.org/W4226166791","https://openalex.org/W4226321491","https://openalex.org/W4226322645","https://openalex.org/W4226409831","https://openalex.org/W4281482294","https://openalex.org/W4285147600","https://openalex.org/W4291653107","https://openalex.org/W4292692470","https://openalex.org/W4312270234","https://openalex.org/W4312473433","https://openalex.org/W4312630861","https://openalex.org/W4312877043","https://openalex.org/W4313068503","https://openalex.org/W4385245566","https://openalex.org/W4386075656","https://openalex.org/W4386075917","https://openalex.org/W4386076180","https://openalex.org/W4390872672","https://openalex.org/W4399419060","https://openalex.org/W6739778489","https://openalex.org/W6766978945","https://openalex.org/W6767716835","https://openalex.org/W6784333009","https://openalex.org/W6788023325","https://openalex.org/W6837634608"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W3150465815","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W1997222214","https://openalex.org/W2560439919","https://openalex.org/W4389340727","https://openalex.org/W2802581102","https://openalex.org/W4205786897"],"abstract_inverted_index":{"Category-level":[0],"object":[1,22,101],"pose":[2,33,67,150,186],"estimation":[3,61,111,148],"and":[4,15,68,84,124,149,184],"tracking":[5,49,151,187],"has":[6],"achieved":[7],"impressive":[8],"progress":[9],"in":[10,74,102],"computer":[11],"vision,":[12],"augmented":[13],"reality,":[14],"robotics.":[16],"Existing":[17],"methods":[18],"either":[19],"estimate":[20,64,95],"the":[21,31,51,65,75,96,103,121,157],"states":[23,119],"from":[24,50],"a":[25,35,57,113],"single":[26,36],"observation":[27],"or":[28],"only":[29],"track":[30],"6-DoF":[32,66],"of":[34,71,99,160],"object.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,154],"focus":[42],"on":[43,132,143,173],"category-level":[44,145],"multi-object":[45,126,146],"9-Dimensional":[46],"(9D)":[47],"state":[48,60,98,128,147],"point":[52],"cloud":[53],"stream.":[54],"We":[55,106],"propose":[56],"novel":[58],"9D":[59,97,127],"network":[62,110],"to":[63,89,94,116,163],"3D":[69],"size":[70],"each":[72,100],"instance":[73],"scene.":[76],"It":[77],"uses":[78],"our":[79,109,138,161,164,174,179],"devised":[80],"multi-scale":[81],"global":[82],"attention":[83,87],"object-level":[85],"local":[86],"modules":[88],"obtain":[90],"representative":[91],"latent":[92],"features":[93],"current":[104,122],"observation.":[105],"then":[107],"integrate":[108],"into":[112],"Kalman":[114],"filter":[115],"combine":[117],"previous":[118],"with":[120,168],"estimates":[123],"achieve":[125],"tracking.":[129],"Experiment":[130],"results":[131],"two":[133],"public":[134],"datasets":[135],"show":[136,178],"that":[137],"method":[139,162],"achieves":[140],"state-of-the-art":[141],"performance":[142],"both":[144],"tasks.":[152],"Furthermore,":[153],"directly":[155],"apply":[156],"pre-trained":[158],"model":[159],"air-ground":[165],"robot":[166],"system":[167],"multiple":[169],"moving":[170],"objects.":[171],"Experiments":[172],"collected":[175],"real-world":[176],"dataset":[177],"method's":[180],"strong":[181],"generalization":[182],"ability":[183],"real-time":[185],"performance.":[188]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}