{"id":"https://openalex.org/W4413343999","doi":"https://doi.org/10.1109/tcsvt.2025.3600527","title":"CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection With IoU Joint Prediction","display_name":"CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection With IoU Joint Prediction","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413343999","doi":"https://doi.org/10.1109/tcsvt.2025.3600527"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3600527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3600527","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036952950","display_name":"Zhiwei Ning","orcid":"https://orcid.org/0009-0006-0287-888X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Ning","raw_affiliation_strings":["School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035041169","display_name":"Zhaojiang Liu","orcid":"https://orcid.org/0009-0006-8113-719X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojiang Liu","raw_affiliation_strings":["School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuanang Gao","orcid":"https://orcid.org/0009-0008-6169-7493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanang Gao","raw_affiliation_strings":["School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018613505","display_name":"Yifan Zuo","orcid":"https://orcid.org/0000-0003-4980-7211"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zuo","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063013411","display_name":"Yuming Fang","orcid":"https://orcid.org/0000-0002-6946-3586"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Fang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763568","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-6351-9019"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036952950"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82581936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"2","first_page":"2177","last_page":"2190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9872000217437744,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6607574820518494},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6493654251098633},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6393589973449707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6233181953430176},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5730608701705933},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5074686408042908},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5060359835624695},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4473947584629059},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4334111213684082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41217613220214844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10253378748893738},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10002949833869934}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607574820518494},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6493654251098633},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6393589973449707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233181953430176},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5730608701705933},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5074686408042908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5060359835624695},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4473947584629059},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4334111213684082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41217613220214844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10253378748893738},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10002949833869934},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3600527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3600527","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1583650166","display_name":null,"funder_award_id":"62132006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1965710864","display_name":null,"funder_award_id":"24Z990200676","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2143609571","display_name":null,"funder_award_id":"62271237","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3112143622","display_name":null,"funder_award_id":"20242BAB26014","funder_id":"https://openalex.org/F4320335477","funder_display_name":"Youth Science Foundation of Jiangxi Province"},{"id":"https://openalex.org/G3944859999","display_name":null,"funder_award_id":"62311530101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4129544981","display_name":null,"funder_award_id":"62402318","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5623680443","display_name":null,"funder_award_id":"62376153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G59969715","display_name":null,"funder_award_id":"U24A20220","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/F4320335477","display_name":"Youth Science Foundation of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2237765446","https://openalex.org/W2555618208","https://openalex.org/W2886904239","https://openalex.org/W2901925479","https://openalex.org/W2905272991","https://openalex.org/W2949708697","https://openalex.org/W2962766617","https://openalex.org/W2963727135","https://openalex.org/W2963769056","https://openalex.org/W2968296999","https://openalex.org/W2990763144","https://openalex.org/W3008105217","https://openalex.org/W3034314779","https://openalex.org/W3034407526","https://openalex.org/W3035172746","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3108426750","https://openalex.org/W3109395584","https://openalex.org/W3118268886","https://openalex.org/W3118341329","https://openalex.org/W3167095230","https://openalex.org/W3170984066","https://openalex.org/W3205005447","https://openalex.org/W3206335707","https://openalex.org/W3206528488","https://openalex.org/W3206826736","https://openalex.org/W3217335336","https://openalex.org/W4221167453","https://openalex.org/W4225865900","https://openalex.org/W4226280874","https://openalex.org/W4226439325","https://openalex.org/W4285606661","https://openalex.org/W4293811845","https://openalex.org/W4312307139","https://openalex.org/W4312707458","https://openalex.org/W4312894406","https://openalex.org/W4313149358","https://openalex.org/W4353004817","https://openalex.org/W4367182782","https://openalex.org/W4376607688","https://openalex.org/W4382240183","https://openalex.org/W4383066393","https://openalex.org/W4385975752","https://openalex.org/W4386066365","https://openalex.org/W4386075636","https://openalex.org/W4386076253","https://openalex.org/W4386083035","https://openalex.org/W4386083121","https://openalex.org/W4390872346","https://openalex.org/W4390872444","https://openalex.org/W4390874213","https://openalex.org/W4396680601","https://openalex.org/W4396680691","https://openalex.org/W4402716222"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4396737233","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Multi-modal":[0],"methods":[1],"based":[2],"on":[3,23,227],"camera":[4,92],"and":[5,34,60,91,107,148,171,215,231],"LiDAR":[6,90,105,125,169],"sensors":[7],"have":[8],"garnered":[9],"significant":[10],"attention":[11],"in":[12,177],"the":[13,54,68,81,86,89,121,138,146,165,178,208,221,228],"field":[14],"of":[15,56,88,123,140,224],"3D":[16,46,58,72,99,147],"detection.":[17],"However,":[18],"many":[19],"prevalent":[20],"works":[21],"focus":[22],"single":[24],"or":[25],"partial":[26],"stage":[27],"fusion,":[28],"leading":[29],"to":[30,51,79,103,119,136,206],"insufficient":[31],"feature":[32],"extraction":[33],"suboptimal":[35],"performance.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,65,153],"introduce":[41,154],"a":[42,75,95,199],"multi-stage":[43],"cross-modal":[44],"fusion":[45],"detection":[47],"framework,":[48],"termed":[49],"CMF-IOU,":[50],"effectively":[52],"address":[53],"challenge":[55],"aligning":[57],"spatial":[59,166],"2D":[61,149],"semantic":[62],"information.":[63,93],"Specifically,":[64],"first":[66,111],"project":[67],"pixel":[69],"information":[70,167,173],"into":[71],"space":[73],"via":[74,144],"depth":[76],"completion":[77],"network":[78],"get":[80],"pseudo":[82,108,142,175],"points,":[83],"which":[84,163],"unifies":[85],"representation":[87,122],"Then,":[94],"bilateral":[96],"cross-view":[97],"enhancement":[98],"backbone":[100],"is":[101,134,204,236],"designed":[102,205],"encode":[104],"points":[106,143,170,176],"points.":[109,126],"The":[110,127,234],"sparse-to-distant":[112],"(S2D)":[113],"branch":[114,133,196],"utilizes":[115],"an":[116,155,189],"encoder-decoder":[117],"structure":[118],"reinforce":[120],"sparse":[124],"second":[128],"residual":[129],"view":[130],"consistency":[131],"(ResVC)":[132],"proposed":[135],"mitigate":[137],"influence":[139],"inaccurate":[141],"both":[145,212],"convolution":[150],"processes.":[151],"Subsequently,":[152],"iterative":[156],"voxel-point":[157],"aware":[158],"fine":[159],"grained":[160],"pooling":[161],"module,":[162],"captures":[164],"from":[168,174],"textural":[172],"proposal":[179],"refinement":[180,186],"stage.":[181],"To":[182],"achieve":[183],"more":[184],"precise":[185],"during":[187],"iteration,":[188],"intersection":[190],"over":[191],"union":[192],"(IoU)":[193],"joint":[194],"prediction":[195],"integrated":[197],"with":[198,211],"novel":[200],"proposals":[201],"generation":[202],"technique":[203],"preserve":[207],"bounding":[209],"boxes":[210],"high":[213],"IoU":[214],"classification":[216],"scores.":[217],"Extensive":[218],"experiments":[219],"show":[220],"superior":[222],"performance":[223],"our":[225],"method":[226],"KITTI,":[229],"nuScenes":[230],"Waymo":[232],"datasets.":[233],"code":[235],"available":[237],"at":[238],"https://github.com/pami-zwning/CMF-IOU.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
