{"id":"https://openalex.org/W4386597050","doi":"https://doi.org/10.1109/icip49359.2023.10222769","title":"3M3D: Multi-View, Multi-Path, Multi-Representation for 3D Object Detection","display_name":"3M3D: Multi-View, Multi-Path, Multi-Representation for 3D Object Detection","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597050","doi":"https://doi.org/10.1109/icip49359.2023.10222769"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222769","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222769","pdf_url":"https://ieeexplore.ieee.org/ielx7/10221937/10221892/10222769.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/10221937/10221892/10222769.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101938959","display_name":"Jongwoo Park","orcid":"https://orcid.org/0009-0006-7558-3804"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jongwoo Park","raw_affiliation_strings":["Motional","Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]},{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041345752","display_name":"Apoorv Singh","orcid":"https://orcid.org/0000-0001-5365-5543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apoorv Singh","raw_affiliation_strings":["Motional"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076852104","display_name":"Varun Bankiti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varun Bankiti","raw_affiliation_strings":["Motional"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motional","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8497,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81959076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1930","last_page":"1934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.8469405770301819},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6908227205276489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6728115677833557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6544344425201416},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5631088614463806},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5142157077789307},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5129618048667908},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4733441174030304},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4593944549560547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.28158771991729736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469405770301819},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6908227205276489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6728115677833557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6544344425201416},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5631088614463806},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5142157077789307},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5129618048667908},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4733441174030304},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4593944549560547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28158771991729736},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222769","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222769","pdf_url":"https://ieeexplore.ieee.org/ielx7/10221937/10221892/10222769.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/icip49359.2023.10222769","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222769","pdf_url":"https://ieeexplore.ieee.org/ielx7/10221937/10221892/10222769.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386597050.pdf","grobid_xml":"https://content.openalex.org/works/W4386597050.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2102605133","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3109395584","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3159695738","https://openalex.org/W3215100485","https://openalex.org/W4225793049","https://openalex.org/W4312894406","https://openalex.org/W4313007769","https://openalex.org/W4383066393","https://openalex.org/W4385301252","https://openalex.org/W4390189588","https://openalex.org/W6620707391","https://openalex.org/W6802311648"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W4390721878","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"3D":[0,21,76],"visual":[1],"perception":[2],"tasks":[3],"based":[4],"on":[5,215,221],"multi-camera":[6],"images":[7,27],"are":[8,46,203],"essential":[9],"for":[10,75],"autonomous":[11],"driving":[12],"systems.":[13],"The":[14],"latest":[15],"work":[16],"in":[17,95,118,148,181],"this":[18],"field":[19],"performs":[20],"object":[22,34],"detection":[23],"by":[24,38,109,134],"leveraging":[25],"multi-view":[26,40,50,83,107,110,120,132,161],"as":[28,55],"an":[29],"input":[30],"and":[31,52,85,100,122],"iteratively":[32],"enhancing":[33],"queries":[35,179,193],"(object":[36],"proposals)":[37],"cross-attending":[39],"features.":[41,150],"However,":[42],"individual":[43],"backbone":[44,65],"features":[45,84,87,108,121,133],"not":[47,157],"updated":[48],"with":[49,195],"features,":[51],"it":[53],"stays":[54],"a":[56],"mere":[57],"collection":[58],"of":[59,62,92,125,136,139,175,178,223],"the":[60,63,90,93,119,126,137,149,155,160,166,173,176,216],"output":[61],"single-image":[64],"network.":[66],"Therefore":[67],"we":[68,80,105,130,171,189,211],"propose":[69],"3M3D:":[70],"A":[71],"Multi-view,":[72],"Multi-path,":[73],"Multi-representation":[74],"Object":[77],"Detection":[78],"where":[79],"update":[81,106,131],"both":[82,96],"query":[86],"to":[88,184,206],"enhance":[89,123],"representation":[91],"scene":[94],"fine":[97],"panoramic":[98,116],"view":[99],"coarse":[101],"global":[102,127],"view.":[103],"Firstly,":[104],"axis":[111,162],"self-attention.":[112],"It":[113,151],"will":[114,152],"incorporate":[115],"information":[117,156],"understanding":[124],"scene.":[128],"Secondly,":[129],"self-attention":[135],"Region":[138],"Interest":[140],"(ROI)":[141],"windows":[142],"which":[143,202],"encodes":[144],"local":[145],"finer":[146],"details":[147],"help":[153],"exchange":[154],"only":[158],"along":[159,165,194],"but":[163],"also":[164],"other":[167],"spatial":[168],"dimension.":[169],"Lastly,":[170],"leverage":[172],"fact":[174],"multi-representation":[177],"(MRQ)":[180],"different":[182],"domains":[183],"further":[185],"boost":[186],"performance.":[187],"Here":[188],"use":[190],"sparse":[191],"floating":[192],"dense":[196],"Bird\u2019s":[197],"Eye":[198],"View":[199],"(BEV)":[200],"queries,":[201],"later":[204],"post-processed":[205],"filter":[207],"duplicate":[208],"detections.":[209],"Moreover,":[210],"show":[212],"performance":[213],"improvements":[214],"nuScenes":[217],"benchmark":[218],"dataset":[219],"[1]":[220],"top":[222],"our":[224],"baselines.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}