{"id":"https://openalex.org/W4416748833","doi":"https://doi.org/10.1109/iros60139.2025.11246316","title":"Efficient Multimodal 3D Object Detector via Instance-Level Contrastive Distillation","display_name":"Efficient Multimodal 3D Object Detector via Instance-Level Contrastive Distillation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748833","doi":"https://doi.org/10.1109/iros60139.2025.11246316"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5019048720","display_name":"Zhonghuan Su","orcid":"https://orcid.org/0000-0001-8161-8846"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuoqun Su","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019035804","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0001-9794-3221"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109691048","display_name":"Shuaifeng Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaifeng Jiao","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721758","display_name":"Junhao Xiao","orcid":"https://orcid.org/0000-0002-4751-539X"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junhao Xiao","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005551827","display_name":"Y. H. Wang","orcid":"https://orcid.org/0000-0001-7984-0448"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["Hunan University,College of Electrical and Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Electrical and Information Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032262344","display_name":"Xieyuanli Chen","orcid":"https://orcid.org/0000-0003-0955-6681"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xieyuanli Chen","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology, and the National Key Laboratory of Equipment State Sensing and Smart Support","institution_ids":["https://openalex.org/I4210145386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019048720"],"corresponding_institution_ids":["https://openalex.org/I4210145386"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85400311,"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":"9878","last_page":"9885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9728000164031982,"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":0.9728000164031982,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/object-detection","display_name":"Object detection","score":0.6464999914169312},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.6025000214576721},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5442000031471252},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5013999938964844},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48170000314712524},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44110000133514404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7243000268936157},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6464999914169312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6359999775886536},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2555618208","https://openalex.org/W2963438049","https://openalex.org/W2992308087","https://openalex.org/W3034486798","https://openalex.org/W3035574168","https://openalex.org/W3108426750","https://openalex.org/W3109395584","https://openalex.org/W3118341329","https://openalex.org/W4200629389","https://openalex.org/W4205146836","https://openalex.org/W4214755140","https://openalex.org/W4312941264","https://openalex.org/W4382240183","https://openalex.org/W4383066393","https://openalex.org/W4385245566","https://openalex.org/W4386075636","https://openalex.org/W4386075892","https://openalex.org/W4386076253","https://openalex.org/W4386083121","https://openalex.org/W4388979610","https://openalex.org/W4390874155","https://openalex.org/W4402703030","https://openalex.org/W4405219754"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"3D":[1,57,70,130,142],"object":[2,71,131,143],"detectors":[3],"leverage":[4],"the":[5,23,39,43,56,126,135],"strengths":[6],"of":[7,42,137,155],"both":[8],"geometry-aware":[9],"LiDAR":[10,94],"point":[11],"clouds":[12],"and":[13,32,81,109,128],"semantically":[14],"rich":[15],"RGB":[16],"images":[17],"to":[18,51],"enhance":[19],"detection":[20,58,132],"performance.":[21],"However,":[22],"inherent":[24],"heterogeneity":[25],"between":[26],"these":[27],"modalities,":[28],"including":[29],"unbalanced":[30],"convergence":[31],"modal":[33],"misalignment,":[34],"poses":[35],"significant":[36],"challenges.":[37],"Meanwhile,":[38,104],"large":[40],"size":[41],"detection-oriented":[44],"feature":[45],"also":[46],"constrains":[47],"existing":[48],"fusion":[49,111],"strategies":[50],"capture":[52],"long-range":[53],"dependencies":[54],"for":[55],"tasks.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"introduce":[64],"a":[65],"fast":[66],"yet":[67],"effective":[68],"multimodal":[69,120],"detector,":[72],"incorporating":[73],"our":[74,138,141,156],"proposed":[75],"Instance-level":[76],"Contrastive":[77],"Distillation":[78],"(ICD)":[79],"framework":[80],"Cross":[82],"Linear":[83],"Attention":[84],"Fusion":[85],"Module":[86],"(CLFM).":[87],"ICD":[88],"aligns":[89],"instance-level":[90],"image":[91],"features":[92],"with":[93],"representations":[95],"through":[96],"object-aware":[97],"contrastive":[98],"distillation,":[99],"ensuring":[100],"fine-grained":[101],"cross-modal":[102,115],"consistency.":[103],"CLFM":[105],"presents":[106],"an":[107],"efficient":[108],"scalable":[110],"strategy":[112],"that":[113],"enhances":[114],"global":[116],"interactions":[117],"within":[118],"sizable":[119],"BEV":[121],"features.":[122],"Extensive":[123],"experiments":[124],"on":[125],"KITTI":[127],"nuScenes":[129],"benchmarks":[133],"demonstrate":[134],"effectiveness":[136],"methods.":[139],"Notably,":[140],"detector":[144],"outperforms":[145],"state-of-the-art":[146],"(SOTA)":[147],"methods":[148],"while":[149],"achieving":[150],"superior":[151],"efficiency.":[152],"The":[153],"implementation":[154],"method":[157],"has":[158],"been":[159],"released":[160],"as":[161],"open-source":[162],"at:":[163],"https://github.com/nubot-nudt/ICD-Fusion.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}