{"id":"https://openalex.org/W7164840348","doi":"https://doi.org/10.1145/3805622.3810777","title":"Semi-3DETR: Semi-Supervised Detection Transformer for 3D Object Detection","display_name":"Semi-3DETR: Semi-Supervised Detection Transformer for 3D Object Detection","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164840348","doi":"https://doi.org/10.1145/3805622.3810777"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810777","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810777","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104097563","display_name":"Na Dong","orcid":"https://orcid.org/0000-0001-6136-4148"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Na Dong","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-0578-1030","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071967339","display_name":"Gim Hee Lee","orcid":"https://orcid.org/0000-0002-1583-0475"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gim Hee Lee","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1583-0475","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93784402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9674000144004822,"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":0.9674000144004822,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00430000014603138,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0032999999821186066,"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/object-detection","display_name":"Object detection","score":0.5450999736785889},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.41990000009536743},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.3986000120639801},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3788999915122986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37880000472068787},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.37540000677108765},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.3752000033855438},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.32120001316070557},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3151000142097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71670001745224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5450999736785889},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4011000096797943},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810777","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810777","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810777","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.45884960889816284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1923184257","https://openalex.org/W2594519801","https://openalex.org/W2963727135","https://openalex.org/W2988715931","https://openalex.org/W3034428269","https://openalex.org/W3034429258","https://openalex.org/W3034579518","https://openalex.org/W3035057392","https://openalex.org/W3096387236","https://openalex.org/W3096754345","https://openalex.org/W3178218920","https://openalex.org/W3215207332","https://openalex.org/W4210985923","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4226344270","https://openalex.org/W4283588903","https://openalex.org/W4283802212","https://openalex.org/W4382300999","https://openalex.org/W4386076400","https://openalex.org/W4386083048","https://openalex.org/W4386895632","https://openalex.org/W4390871662","https://openalex.org/W4390874476","https://openalex.org/W4402570948","https://openalex.org/W4402778069","https://openalex.org/W4403889749","https://openalex.org/W7133205496","https://openalex.org/W7133215408","https://openalex.org/W7133226318"],"related_works":[],"abstract_inverted_index":{"DETR-based":[0],"3D":[1,36,57,71,122,156],"detectors":[2],"have":[3],"recently":[4],"emerged":[5],"as":[6],"a":[7,125,142],"popular":[8],"alternative":[9],"to":[10,51,55,64,67,101,116,130,145,175],"voting-":[11],"and":[12,83,103,109,124,133,149,162,178],"voxel-based":[13],"methods,":[14],"which":[15],"offer":[16],"end-to-end":[17],"set":[18],"prediction":[19],"without":[20],"handcrafted":[21],"priors":[22],"or":[23],"voxelization.":[24],"However,":[25],"they":[26],"remain":[27],"unexplored":[28],"under":[29,121,136],"semi-supervision,":[30],"where":[31],"the":[32,48,166],"scarcity":[33],"of":[34,76,168],"annotated":[35],"data":[37],"impedes":[38],"their":[39],"widespread":[40],"adoption.":[41],"In":[42],"this":[43],"work,":[44],"we":[45],"present":[46],"Semi-3DETR,":[47],"first":[49],"framework":[50],"systematically":[52],"adapt":[53],"DETR":[54,72],"semi-supervised":[56,70,179],"object":[58],"detection":[59],"by":[60,92],"addressing":[61],"challenges":[62],"unique":[63],"3D.":[65],"Compared":[66],"2D":[68],"Semi-DETR,":[69],"faces":[73],"amplified":[74],"issues":[75,91],"fragile":[77],"volumetric":[78,105],"pseudo-labels,":[79],"unstable":[80],"query":[81,119],"alignment,":[82],"noisy":[84,137],"bipartite":[85],"matching.":[86],"Our":[87],"Semi-3DETR":[88,170],"mitigates":[89],"these":[90],"introducing":[93],"three":[94],"core":[95],"components:":[96],"Robust":[97],"Pseudo-Label":[98],"Denoising":[99],"(RPLD)":[100],"filter":[102],"refine":[104],"pseudo-labels":[106],"against":[107],"orientation":[108],"depth":[110],"errors,":[111],"Query":[112],"Alignment":[113],"Consistency":[114],"(QAC)":[115],"stabilize":[117],"teacher\u2013student":[118],"correspondence":[120],"transformations,":[123],"Hybrid":[126],"Matching":[127],"Strategy":[128],"(HMS)":[129],"balance":[131],"one-to-one":[132],"one-to-many":[134],"assignments":[135],"supervision.":[138],"We":[139],"further":[140],"adopt":[141],"softmax":[143],"classifier":[144],"enforce":[146],"class":[147],"exclusivity":[148],"improve":[150],"pseudo-label":[151],"reliability":[152],"in":[153],"semantically":[154],"ambiguous":[155],"categories.":[157],"Extensive":[158],"experiments":[159],"on":[160],"ScanNet":[161],"SUN":[163],"RGB-D":[164],"demonstrate":[165],"feasibility":[167],"our":[169],"with":[171],"promising":[172],"results":[173],"compared":[174],"fully":[176],"supervised":[177],"baselines.":[180],"The":[181],"source":[182],"code":[183],"will":[184],"be":[185],"released":[186],"upon":[187],"paper":[188],"acceptance.":[189]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}