{"id":"https://openalex.org/W7124138844","doi":"https://doi.org/10.1109/tcsvt.2026.3654118","title":"Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection","display_name":"Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection","publication_year":2026,"publication_date":"2026-01-14","ids":{"openalex":"https://openalex.org/W7124138844","doi":"https://doi.org/10.1109/tcsvt.2026.3654118"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3654118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3654118","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":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123031924","display_name":"Rui Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ding","raw_affiliation_strings":["State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009875443","display_name":"Zhaonian Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaonian Kuang","raw_affiliation_strings":["State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123022082","display_name":"Yuzhe Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yuzhe Ji","raw_affiliation_strings":["Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0525-5059"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-0525-5059","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123022628","display_name":"Xinhu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xinhu Zheng","raw_affiliation_strings":["Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9898-5543","affiliations":[{"raw_affiliation_string":"Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123016479","display_name":"Gang Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Hua","raw_affiliation_strings":["Multimodal Experiences Research Laboratory, Dolby Laboratories, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9522-6157","affiliations":[{"raw_affiliation_string":"Multimodal Experiences Research Laboratory, Dolby Laboratories, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I4210093996"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.05780321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"5815","last_page":"5827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8486999869346619,"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":0.8486999869346619,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.02280000038444996,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.01720000058412552,"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/bottleneck","display_name":"Bottleneck","score":0.6344000101089478},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6003000140190125},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4528999924659729},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.42899999022483826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4271000027656555},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575000286102295},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6344000101089478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6067000031471252},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6003000140190125},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4374000132083893},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2026.3654118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3654118","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"},{"id":"pmh:doi:10.48550/arxiv.2603.07486","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.07486","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7998775839805603}],"awards":[{"id":"https://openalex.org/G3187807108","display_name":null,"funder_award_id":"62373298","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G405689140","display_name":null,"funder_award_id":"2023ZD006","funder_id":"https://openalex.org/F4320336753","funder_display_name":"Changsha Science and Technology Project"},{"id":"https://openalex.org/G4870418371","display_name":null,"funder_award_id":"JYB2025XDXM504","funder_id":"https://openalex.org/F4320336751","funder_display_name":"Science Foundation of Ministry of Education of China"},{"id":"https://openalex.org/G8008072069","display_name":null,"funder_award_id":"U24A20252","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/F4320336751","display_name":"Science Foundation of Ministry of Education of China","ror":null},{"id":"https://openalex.org/F4320336753","display_name":"Changsha Science and Technology Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"3D":[1,83,220],"object":[2,84,221],"detection":[3,85],"with":[4,229],"bird\u2019s":[5],"eye":[6],"view":[7],"(BEV)":[8],"has":[9],"achieved":[10],"desired":[11],"advances":[12],"on":[13,167,242,248,253,266],"benchmarks.":[14],"Nonetheless,":[15],"the":[16,22,48,60,160,168,212,263],"accuracy":[17,265],"may":[18,58],"drop":[19],"significantly":[20],"in":[21,47,119],"real":[23],"world":[24],"due":[25],"to":[26,154,178,215,273],"data":[27,87,114,134,183,234,257,271],"corruption":[28,115,235],"such":[29],"as":[30,198,205],"sensor":[31],"configurations":[32],"for":[33,38,81,130,219,236],"LiDAR":[34],"and":[35,78,147,189,239,251,269],"scene":[36],"conditions":[37],"camera.":[39],"One":[40],"design":[41],"bottleneck":[42],"of":[43,51,113,163,182,233,256],"previous":[44],"models":[45],"resides":[46],"tightly":[49],"coupling":[50],"multi-modal":[52],"BEV":[53,143],"features":[54,102,124,144,153,174,197,203,218],"during":[55],"fusion,":[56],"which":[57],"degrade":[59],"overall":[61],"system":[62],"performance":[63],"if":[64],"one":[65],"modality":[66,118,166],"or":[67],"both":[68,240,267],"is":[69,246],"corrupted.":[70],"To":[71,136],"mitigate,":[72],"we":[73,139,194,209,225],"propose":[74],"a":[75,164,206,227,230],"Multi-Modal":[76],"Decouple":[77],"Recouple":[79],"Network":[80],"robust":[82,131,199,217],"under":[86,133],"corruption.":[88,135,258],"Different":[89],"modalities":[90,104,129],"commonly":[91],"share":[92],"some":[93],"high-level":[94],"invariant":[95,101,123,152],"features.":[96],"We":[97,170],"observe":[98],"that":[99],"these":[100,173],"across":[103,128],"do":[105],"not":[106],"always":[107],"fail":[108],"simultaneously,":[109],"because":[110],"different":[111,180],"types":[112,181,255],"affect":[116],"each":[117,156,192],"distinct":[120],"ways.":[121],"These":[122],"can":[125],"be":[126],"recovered":[127],"fusion":[132],"this":[137],"end,":[138],"explicitly":[140],"decouple":[141],"Camera/LiDAR":[142],"into":[145,175],"modality-invariant":[146,196],"modality-specific":[148,202],"parts.":[149],"It":[150],"allows":[151],"compensate":[155],"other":[157],"while":[158,201],"mitigates":[159],"negative":[161],"impact":[162],"corrupted":[165,268],"other.":[169],"then":[171],"recouple":[172],"three":[176,213],"experts":[177,214],"handle":[179],"corruption,":[184],"respectively,":[185],"i.e.,":[186],"LiDAR,":[187,237],"camera,":[188,238],"both.":[190],"For":[191,223],"expert,":[193],"use":[195],"information,":[200],"serve":[204],"complement.":[207],"Finally,":[208],"adaptively":[210],"fuse":[211],"exact":[216],"detection.":[222],"validation,":[224],"collect":[226],"benchmark":[228],"large":[231],"quantity":[232],"based":[241],"nuScenes.":[243],"Our":[244,259],"model":[245,260],"trained":[247],"clean":[249,270],"nuScenes":[250],"tested":[252],"all":[254],"consistently":[261],"achieves":[262],"best":[264],"compared":[272],"recent":[274],"models.":[275]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-01-15T00:00:00"}