{"id":"https://openalex.org/W4411276791","doi":"https://doi.org/10.1145/3744247","title":"Multi-Modal 3D Object Detector with Object-Guided Fusion and Hierarchical Sample Selection","display_name":"Multi-Modal 3D Object Detector with Object-Guided Fusion and Hierarchical Sample Selection","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411276791","doi":"https://doi.org/10.1145/3744247"},"language":"en","primary_location":{"id":"doi:10.1145/3744247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744247","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5034926811","display_name":"Jianping Zhong","orcid":"https://orcid.org/0009-0001-1906-734X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianping Zhong","raw_affiliation_strings":["Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044171641","display_name":"Zhaobo Qi","orcid":"https://orcid.org/0000-0001-9196-9818"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaobo Qi","raw_affiliation_strings":["Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017318126","display_name":"Kaiwen Duan","orcid":"https://orcid.org/0000-0002-8663-7429"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Duan","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071230372","display_name":"Yuanrong Xu","orcid":"https://orcid.org/0000-0002-9457-7956"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanrong Xu","raw_affiliation_strings":["Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014774434","display_name":"Weigang Zhang","orcid":"https://orcid.org/0000-0003-0042-7074"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034926811"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.799545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"21","issue":"8","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8596197366714478},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6587923169136047},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6156255006790161},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6034873723983765},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5698694586753845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567737817764282},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5208286046981812},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.481986939907074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42493391036987305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3498613238334656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596197366714478},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6587923169136047},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6156255006790161},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6034873723983765},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5698694586753845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567737817764282},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5208286046981812},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.481986939907074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42493391036987305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3498613238334656},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744247","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1392212626","display_name":null,"funder_award_id":"62441232, 62476068, U21B2038, 62306092, and 62306091","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2555618208","https://openalex.org/W2897529137","https://openalex.org/W2949708697","https://openalex.org/W2962888833","https://openalex.org/W2963400571","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2968296999","https://openalex.org/W2981949127","https://openalex.org/W2982363097","https://openalex.org/W2982770724","https://openalex.org/W3034314779","https://openalex.org/W3035346742","https://openalex.org/W3035574168","https://openalex.org/W3039448353","https://openalex.org/W3107819843","https://openalex.org/W3108426750","https://openalex.org/W3109675406","https://openalex.org/W3113028524","https://openalex.org/W3118341329","https://openalex.org/W3130463448","https://openalex.org/W3166089996","https://openalex.org/W3166470370","https://openalex.org/W3167095230","https://openalex.org/W3177276051","https://openalex.org/W3196024568","https://openalex.org/W3201719054","https://openalex.org/W3207921941","https://openalex.org/W4200632008","https://openalex.org/W4210352603","https://openalex.org/W4214777292","https://openalex.org/W4226098442","https://openalex.org/W4236965008","https://openalex.org/W4283790779","https://openalex.org/W4288705760","https://openalex.org/W4293704629","https://openalex.org/W4294733375","https://openalex.org/W4296118075","https://openalex.org/W4310078553","https://openalex.org/W4312349930","https://openalex.org/W4312934050","https://openalex.org/W4313149358","https://openalex.org/W4320892151","https://openalex.org/W4321770545","https://openalex.org/W4379881908","https://openalex.org/W4382203498","https://openalex.org/W4383066393","https://openalex.org/W4384787373","https://openalex.org/W4385975752","https://openalex.org/W4386072002","https://openalex.org/W4386076096","https://openalex.org/W4386076493","https://openalex.org/W4386083121","https://openalex.org/W4389675241","https://openalex.org/W4389919300","https://openalex.org/W4390479122","https://openalex.org/W4390873604","https://openalex.org/W4409366836","https://openalex.org/W4410992944","https://openalex.org/W6872711877"],"related_works":["https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2000775715","https://openalex.org/W2074467390","https://openalex.org/W2795393339","https://openalex.org/W2626393719","https://openalex.org/W4390618967","https://openalex.org/W2174745845","https://openalex.org/W2063058012"],"abstract_inverted_index":{"Accurately":[0],"detecting":[1],"objects":[2,23,98,116],"in":[3],"3D":[4,68],"scenes":[5],"is":[6,47,169,224],"crucial":[7],"for":[8,114],"autonomous":[9],"driving.":[10],"Although":[11],"existing":[12],"voxel-based":[13],"methods":[14],"have":[15],"achieved":[16],"remarkable":[17],"progress,":[18],"their":[19],"performance":[20],"on":[21,163,193,214,218],"tail":[22,115],"remains":[24],"unsatisfactory.":[25],"We":[26],"identify":[27],"two":[28],"core":[29],"issues":[30],"contributing":[31],"to":[32,93,105,121,132,146],"this":[33],"phenomenon:":[34],"the":[35,51,95,107,124,134,158,174,182,185,194,200,219],"detectors":[36],"frequently":[37],"misidentify":[38],"some":[39],"background":[40],"elements":[41],"as":[42],"foreground":[43],"objects,":[44],"and":[45,54,78,177,188,196,208,216],"there":[46,168],"a":[48,79,128,170],"misalignment":[49,183],"between":[50,173,184],"classification":[52,136,153,175,186],"score":[53,176,187],"detection":[55,189],"quality.":[56,190],"To":[57],"tackle":[58],"these":[59,164],"challenges,":[60],"we":[61],"introduce":[62],"an":[63,72,101],"object-level":[64],"\u2013":[65],"guided":[66],"multi-modal":[67],"object":[69,102],"detector":[70],"with":[71,148],"object-guided":[73],"feature":[74],"fusion":[75],"(OFF)":[76],"module":[77],"hierarchical":[80],"sample":[81],"selection":[82],"(HSS)":[83],"strategy,":[84],"named":[85],"OGMMDet.":[86],"Specifically,":[87],"OFF":[88],"introduces":[89],"rich":[90],"image":[91],"features":[92],"enhance":[94],"representation":[96],"of":[97,139,202],"while":[99,117],"using":[100],"distribution":[103],"heatmap":[104],"suppress":[106],"background.":[108,125],"This":[109,155,179],"approach":[110,131],"provides":[111],"geometry":[112],"clues":[113],"providing":[118],"category":[119],"priors":[120],"filter":[122],"out":[123],"HSS":[126],"uses":[127],"local-to-global":[129],"ranking":[130],"calculate":[133],"relative":[135],"loss":[137],"weights":[138,145],"all":[140],"proposals.":[141,166],"It":[142],"assigns":[143],"higher":[144,149],"proposals":[147],"IoU":[150],"when":[151],"optimizing":[152],"branches.":[154],"ensures":[156],"that":[157],"model":[159],"focuses":[160],"its":[161],"optimization":[162],"higher-quality":[165],"Consequently,":[167],"positive":[171],"correlation":[172],"IoU.":[178],"method":[180],"alleviates":[181],"Extensive":[191],"experiments":[192],"KITTI":[195,220],"nuScenes":[197],"benchmarks":[198],"demonstrate":[199],"effectiveness":[201],"our":[203],"OGMMDet,":[204],"which":[205],"achieves":[206],"45.61%":[207],"68.96%":[209],"mean":[210],"average":[211],"precision":[212],"(mAP)":[213],"pedestrians":[215],"cyclists":[217],"benchmark,":[221],"respectively.":[222],"Code":[223],"available":[225],"at":[226],"https://github.com/ZhongJianPing1/ogmmdet.git":[227],".":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}