{"id":"https://openalex.org/W3188283811","doi":"https://doi.org/10.1109/tcsvt.2021.3102025","title":"Transformer3D-Det: Improving 3D Object Detection by Vote Refinement","display_name":"Transformer3D-Det: Improving 3D Object Detection by Vote Refinement","publication_year":2021,"publication_date":"2021-08-03","ids":{"openalex":"https://openalex.org/W3188283811","doi":"https://doi.org/10.1109/tcsvt.2021.3102025","mag":"3188283811"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3102025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3102025","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":"https://openalex.org/A5016042658","display_name":"Lichen Zhao","orcid":"https://orcid.org/0000-0002-5805-3194"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lichen Zhao","raw_affiliation_strings":["College of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039703932","display_name":"Jinyang Guo","orcid":"https://orcid.org/0000-0003-1956-3367"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinyang Guo","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082181536","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0003-2775-9730"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035443556","display_name":"Lu Sheng","orcid":"https://orcid.org/0000-0002-8525-9163"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Sheng","raw_affiliation_strings":["College of Software, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016042658"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":5.5161,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96947023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":"12","first_page":"4735","last_page":"4746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9897000193595886,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164889812469482},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.7133840322494507},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6566516160964966},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6204293966293335},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5587864518165588},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.52684086561203},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.48829221725463867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4670730233192444},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4591403007507324},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.415530800819397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.391740620136261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2822197675704956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25683292746543884},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07219928503036499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164889812469482},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.7133840322494507},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6566516160964966},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6204293966293335},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5587864518165588},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.52684086561203},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.48829221725463867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4670730233192444},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4591403007507324},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.415530800819397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.391740620136261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2822197675704956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25683292746543884},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07219928503036499},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3102025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3102025","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":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G522138796","display_name":null,"funder_award_id":"61906012","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1923184257","https://openalex.org/W2229637417","https://openalex.org/W2293349265","https://openalex.org/W2463032559","https://openalex.org/W2555618208","https://openalex.org/W2558294288","https://openalex.org/W2560609797","https://openalex.org/W2594519801","https://openalex.org/W2768282280","https://openalex.org/W2780829839","https://openalex.org/W2897529137","https://openalex.org/W2904332125","https://openalex.org/W2949708697","https://openalex.org/W2951517617","https://openalex.org/W2954258401","https://openalex.org/W2962759414","https://openalex.org/W2963057320","https://openalex.org/W2963182550","https://openalex.org/W2963400571","https://openalex.org/W2963721253","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2964080601","https://openalex.org/W2968296999","https://openalex.org/W2981949127","https://openalex.org/W2988715931","https://openalex.org/W3003618643","https://openalex.org/W3034239841","https://openalex.org/W3034314779","https://openalex.org/W3034428269","https://openalex.org/W3034429258","https://openalex.org/W3034430142","https://openalex.org/W3034579518","https://openalex.org/W3034602892","https://openalex.org/W3035265375","https://openalex.org/W3035346742","https://openalex.org/W3035748168","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3096754345","https://openalex.org/W4303579812","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6746052068","https://openalex.org/W6760424586","https://openalex.org/W6763422710","https://openalex.org/W6765299845","https://openalex.org/W6778791504","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W3130645678","https://openalex.org/W2804574147","https://openalex.org/W4285742308","https://openalex.org/W2921865287","https://openalex.org/W3213290865","https://openalex.org/W4297824084","https://openalex.org/W2974375613","https://openalex.org/W2935837427","https://openalex.org/W2593809839","https://openalex.org/W2801801420"],"abstract_inverted_index":{"Voting-based":[0],"methods":[1],"(e.g.,":[2],"VoteNet)":[3],"have":[4],"achieved":[5],"promising":[6],"results":[7,25,66],"for":[8,162,216],"3D":[9,44,75,195,217],"object":[10,33,45,76,196,218],"detection.":[11,219],"However,":[12],"the":[13,31,64,74,109,120,143,149,154,158,163,169,210],"simple":[14,41],"voting":[15,24,65],"operation":[16],"in":[17,51],"VoteNet":[18,68],"may":[19],"lead":[20],"to":[21,62,113,135,182],"less":[22],"accurate":[23,138],"that":[26],"are":[27],"far":[28],"away":[29],"from":[30],"true":[32],"centers.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,53,106,174],"propose":[39,176],"a":[40,56,87,91,96,177,187],"but":[42],"effective":[43],"detection":[46,77,160,197],"method":[47],"called":[48],"Transformer3D-Det":[49],"(T3D),":[50],"which":[52],"additionally":[54],"introduce":[55],"transformer":[57,130],"based":[58,131],"vote":[59,88,92,110,117,132,151],"refinement":[60,93,133],"module":[61,112,134,147],"refine":[63],"of":[67,84,171,212],"and":[69,95,139,156,206],"can":[70,192],"thus":[71],"significantly":[72],"improve":[73],"performance.":[78,198],"Specifically,":[79],"our":[80,129,184,189,213],"T3D":[81,190,214],"framework":[82,191,215],"consists":[83],"three":[85],"modules:":[86],"generation":[89,99,111,146],"module,":[90,94],"bounding":[97,144],"box":[98,145],"module.":[100],"Given":[101],"an":[102],"input":[103,155,164],"point":[104,165],"cloud,":[105],"first":[107],"utilize":[108],"generate":[114],"multiple":[115],"coarse":[116,122],"clusters.":[118],"Then,":[119],"clustered":[121],"votes":[123],"will":[124],"be":[125],"refined":[126,150],"by":[127],"using":[128],"produce":[136],"more":[137],"meaningful":[140],"votes.":[141],"Finally,":[142],"takes":[148],"clusters":[152],"as":[153],"generates":[157],"final":[159],"result":[161],"cloud.":[166],"To":[167],"alleviate":[168],"impact":[170],"inaccurate":[172],"votes,":[173],"also":[175],"new":[178],"non-vote":[179],"loss":[180],"function":[181],"train":[183],"T3D.":[185],"As":[186],"result,":[188],"achieve":[193],"better":[194],"Comprehensive":[199],"experiments":[200],"on":[201],"two":[202],"benchmark":[203],"datasets":[204],"ScanNetV2":[205],"SUN":[207],"RGB-D":[208],"demonstrate":[209],"effectiveness":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}