{"id":"https://openalex.org/W4386075854","doi":"https://doi.org/10.1109/cvpr52729.2023.02073","title":"MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection","display_name":"MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386075854","doi":"https://doi.org/10.1109/cvpr52729.2023.02073"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.02073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5010965630","display_name":"Yang Jiao","orcid":"https://orcid.org/0000-0002-6390-2517"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Jiao","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","Shanghai Collaborative Innovation Center of Intelligent Visual Computing"],"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499520","display_name":"Shaoxiang Chen","orcid":"https://orcid.org/0000-0002-7627-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoxiang Chen","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","Shanghai Collaborative Innovation Center of Intelligent Visual Computing","Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":[]},{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324184","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-9491-7789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","Shanghai Collaborative Innovation Center of Intelligent Visual Computing","Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"affiliations":[{"raw_affiliation_string":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":[]},{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010965630"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":14.8884,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.99411319,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"21643","last_page":"21652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.8093763589859009},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6871361136436462},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6562702655792236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6465530395507812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5890581011772156},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5486630797386169},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.4734344482421875},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3418654799461365},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.226677805185318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.21309363842010498}],"concepts":[{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.8093763589859009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6871361136436462},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6562702655792236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6465530395507812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5890581011772156},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5486630797386169},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4734344482421875},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3418654799461365},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.226677805185318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.21309363842010498}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.02073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3970387658","display_name":null,"funder_award_id":"62072116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6151995449","display_name":null,"funder_award_id":"21JC1400600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2555618208","https://openalex.org/W2565639579","https://openalex.org/W2897529137","https://openalex.org/W2951517617","https://openalex.org/W2954174912","https://openalex.org/W2963182550","https://openalex.org/W2963400571","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2967324759","https://openalex.org/W2968296999","https://openalex.org/W2969987486","https://openalex.org/W3017930107","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3107819843","https://openalex.org/W3108426750","https://openalex.org/W3117804044","https://openalex.org/W3138006590","https://openalex.org/W3167095230","https://openalex.org/W3170030651","https://openalex.org/W3175382666","https://openalex.org/W3213288297","https://openalex.org/W4281672996","https://openalex.org/W4281773951","https://openalex.org/W4293112749","https://openalex.org/W4312707458","https://openalex.org/W4313142137","https://openalex.org/W4383066393","https://openalex.org/W6754918364","https://openalex.org/W6760782946","https://openalex.org/W6767379092","https://openalex.org/W6781040350","https://openalex.org/W6792148081","https://openalex.org/W6803556390","https://openalex.org/W6838873368","https://openalex.org/W6838956374","https://openalex.org/W6839131839","https://openalex.org/W6842385943"],"related_works":["https://openalex.org/W4319317934","https://openalex.org/W2901265155","https://openalex.org/W2956374172","https://openalex.org/W2351984678","https://openalex.org/W2140032575","https://openalex.org/W2011860471","https://openalex.org/W2012196540","https://openalex.org/W3011451421","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Fusing":[0],"LiDAR":[1,150,221],"and":[2,9,29,62,116,145,151,201,222,243,249],"camera":[3,46,53,195],"information":[4,75,118,144],"is":[5,19,76,104,120,165,187,254],"essential":[6],"for":[7],"accurate":[8],"reliable":[10],"3D":[11,60,85,96,117,240],"object":[12,241],"detection":[13,214,242],"in":[14,51,78,126,197],"autonomous":[15],"driving":[16],"systems.":[17],"This":[18],"challenging":[20],"due":[21],"to":[22,56,122,167,189],"the":[23,42,127,142,169,173,194,213,225],"difficulty":[24],"of":[25,45,141,155,172],"combining":[26],"multi-granularity":[27],"geometric":[28],"semantic":[30,43],"features":[31,47,205,219],"from":[32,220],"two":[33,156],"drastically":[34],"different":[35],"modalities.":[36],"Recent":[37],"approaches":[38,80],"aim":[39],"at":[40,176,256],"exploring":[41],"densities":[44],"through":[48],"lifting":[49,82],"points":[50,83,175],"2D":[52,65,88,115],"images":[54],"(referred":[55],"as":[57,106,233],"\u201cseeds\u201d)":[58],"into":[59,84,206],"space,":[61,86],"then":[63,202],"incorporate":[64],"semantics":[66,89],"via":[67],"cross-modal":[68,147],"interaction":[69,148,178],"or":[70,108,119],"fusion":[71,101],"techniques.":[72,251],"However,":[73],"depth":[74,143,170],"under-investigated":[77],"these":[79],"when":[81],"thus":[87],"can":[90,111],"not":[91,112],"be":[92],"reliably":[93],"fused":[94],"with":[95,138,193,216],"points.":[97],"Moreover,":[98],"their":[99],"multi-modal":[100,204],"strategy,":[102],"which":[103,153],"implemented":[105],"concatenation":[107],"attention,":[109],"either":[110],"effectively":[113],"fuse":[114],"unable":[121],"perform":[123],"fine-grained":[124,146,199],"interactions":[125],"voxel":[128],"space.":[129,209],"To":[130],"this":[131],"end,":[132],"we":[133],"propose":[134],"a":[135,160,181,198,207],"novel":[136],"framework":[137],"better":[139],"utilization":[140],"between":[149],"camera,":[152],"consists":[154],"important":[157],"components.":[158],"First,":[159],"Multi-Depth":[161],"Unprojection":[162],"(MDU)":[163],"method":[164],"used":[166],"enhance":[168],"quality":[171],"lifted":[174],"each":[177],"level.":[179],"Second,":[180],"Gated":[182],"Modality-Aware":[183],"Convolution":[184],"(GMA-Conv)":[185],"block":[186],"applied":[188],"modulate":[190],"voxels":[191],"involved":[192],"modality":[196],"manner":[200],"aggregate":[203],"unified":[208],"Together":[210],"they":[211],"provide":[212],"head":[215],"more":[217],"comprehensive":[218],"camera.":[223],"On":[224],"nuScenes":[226],"test":[227],"benchmark,":[228],"our":[229],"proposed":[230],"method,":[231],"abbreviated":[232],"MSMD-Fusion,":[234],"achieves":[235],"state-of-the-art":[236],"results":[237],"on":[238],"both":[239],"tracking":[244],"tasks":[245],"without":[246],"using":[247],"test-time-augmentation":[248],"ensemble":[250],"The":[252],"code":[253],"available":[255],"https://github.com/SxJyJay/MSMDFusion.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":58},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":16}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}