{"id":"https://openalex.org/W4401416652","doi":"https://doi.org/10.1109/icra57147.2024.10610905","title":"Multimodal Object Query Initialization for 3D Object Detection","display_name":"Multimodal Object Query Initialization for 3D Object Detection","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416652","doi":"https://doi.org/10.1109/icra57147.2024.10610905"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5093081419","display_name":"Mathijs R. van Geerenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mathijs R. Van Geerenstein","raw_affiliation_strings":["Corporate Research,Robert Bosch GmbH,Renningen,Germany,71272"],"affiliations":[{"raw_affiliation_string":"Corporate Research,Robert Bosch GmbH,Renningen,Germany,71272","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078398825","display_name":"Felicia Ruppel","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felicia Ruppel","raw_affiliation_strings":["Corporate Research,Robert Bosch GmbH,Renningen,Germany,71272"],"affiliations":[{"raw_affiliation_string":"Corporate Research,Robert Bosch GmbH,Renningen,Germany,71272","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085054529","display_name":"Klaus Dietmayer","orcid":"https://orcid.org/0000-0002-1651-014X"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Dietmayer","raw_affiliation_strings":["Ulm University,Institute of Measurement, Control and Microtechnology,Germany"],"affiliations":[{"raw_affiliation_string":"Ulm University,Institute of Measurement, Control and Microtechnology,Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085298812","display_name":"Dariu M. Gavrila","orcid":"https://orcid.org/0000-0002-1810-4196"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dariu M. Gavrila","raw_affiliation_strings":["Delft University of Technology,Intelligent Vehicles Group,the Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Intelligent Vehicles Group,the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093081419"],"corresponding_institution_ids":["https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":3.0245,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90775833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12484","last_page":"12491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9987999796867371,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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":0.8047518730163574},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7289280891418457},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6231240034103394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956453084945679},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5636019706726074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43563586473464966},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4153587222099304},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34979408979415894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22615814208984375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0872156023979187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047518730163574},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7289280891418457},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6231240034103394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956453084945679},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5636019706726074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43563586473464966},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4153587222099304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34979408979415894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22615814208984375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0872156023979187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2222512263","https://openalex.org/W2555618208","https://openalex.org/W2560609797","https://openalex.org/W2612690371","https://openalex.org/W2798405286","https://openalex.org/W2897529137","https://openalex.org/W2963351448","https://openalex.org/W2963400571","https://openalex.org/W2963727135","https://openalex.org/W2964054038","https://openalex.org/W2968296999","https://openalex.org/W2969987486","https://openalex.org/W2970987838","https://openalex.org/W3017930107","https://openalex.org/W3035172746","https://openalex.org/W3035346742","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3107819843","https://openalex.org/W3108426750","https://openalex.org/W3117804044","https://openalex.org/W3118341329","https://openalex.org/W3136022415","https://openalex.org/W3146455718","https://openalex.org/W3167095230","https://openalex.org/W3167539120","https://openalex.org/W3167732492","https://openalex.org/W3170030651","https://openalex.org/W3175563878","https://openalex.org/W3209639308","https://openalex.org/W3213288297","https://openalex.org/W4214624153","https://openalex.org/W4281672996","https://openalex.org/W4281773951","https://openalex.org/W4285812971","https://openalex.org/W4293112749","https://openalex.org/W4308080199","https://openalex.org/W4310273780","https://openalex.org/W4312501532","https://openalex.org/W4312562010","https://openalex.org/W4312707458","https://openalex.org/W4313121901","https://openalex.org/W4361274151","https://openalex.org/W4367182782","https://openalex.org/W4383066393","https://openalex.org/W4383097697","https://openalex.org/W4385245566","https://openalex.org/W4385804883","https://openalex.org/W4390873750","https://openalex.org/W6739778489","https://openalex.org/W6767379092","https://openalex.org/W6784094891","https://openalex.org/W6793267612","https://openalex.org/W6803556390","https://openalex.org/W6838873368","https://openalex.org/W6838956374","https://openalex.org/W6842385943","https://openalex.org/W6846908210"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"3D":[0,94],"object":[1,34,42,89,95,132],"detection":[2,96,133],"models":[3],"that":[4],"exploit":[5,67],"both":[6],"LiDAR":[7,60,131],"and":[8,63,85,139],"camera":[9],"sensor":[10,47,115,169],"features":[11],"are":[12],"top":[13],"performers":[14],"in":[15,31,129],"large-scale":[16],"autonomous":[17],"driving":[18],"benchmarks.":[19],"A":[20],"transformer":[21,107],"is":[22,49,102],"a":[23,50,105],"popular":[24],"network":[25],"architecture":[26],"used":[27],"for":[28,88,92,156],"this":[29],"task,":[30],"which":[32],"so-called":[33],"queries":[35,43,111],"act":[36],"as":[37,171],"candidate":[38],"objects.":[39],"Initializing":[40],"these":[41,77],"based":[44],"on":[45,59,134],"current":[46],"inputs":[48],"common":[51],"practice.":[52],"For":[53],"this,":[54],"existing":[55],"methods":[56],"strongly":[57],"rely":[58],"data":[61],"however,":[62],"do":[64],"not":[65],"fully":[66],"image":[68],"features.":[69],"Besides,":[70],"they":[71],"introduce":[72],"significant":[73],"latency.":[74],"To":[75],"overcome":[76],"limitations":[78],"we":[79,122],"propose":[80],"EfficientQ3M,":[81],"an":[82],"efficient,":[83],"modular,":[84],"multimodal":[86,145],"solution":[87],"query":[90,146],"initialization":[91,100],"transformer-based":[93,130],"models.":[97],"The":[98,159],"proposed":[99,160],"method":[101,161],"combined":[103],"with":[104,165],"\"modality-balanced\"":[106],"decoder":[108],"where":[109],"the":[110,118,124,127,135,141,153],"can":[112,162],"access":[113],"all":[114],"modalities":[116,170],"throughout":[117],"decoder.":[119],"In":[120],"experiments,":[121],"outperform":[123],"state":[125],"of":[126,143,168],"art":[128],"competitive":[136],"nuScenes":[137],"benchmark":[138],"showcase":[140],"benefits":[142],"input-dependent":[144],"initialization,":[147],"while":[148],"being":[149],"more":[150],"efficient":[151],"than":[152],"available":[154],"alternatives":[155],"LiDAR-camera":[157],"initialization.":[158],"be":[163],"applied":[164],"any":[166],"combination":[167],"input,":[172],"demonstrating":[173],"its":[174],"modularity.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}