{"id":"https://openalex.org/W7221786441","doi":"https://doi.org/10.66977/xsci.2610.0039","title":"Mining Cross-Modal Perception Gaps in Autonomous Driving: When Camera and LiDAR Disagree","display_name":"Mining Cross-Modal Perception Gaps in Autonomous Driving: When Camera and LiDAR Disagree","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7221786441","doi":"https://doi.org/10.66977/xsci.2610.0039"},"language":"en","primary_location":{"id":"doi:10.66977/xsci.2610.0039","doi":"https://doi.org/10.66977/xsci.2610.0039","is_oa":false,"landing_page_url":"https://doi.org/10.66977/xsci.2610.0039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.16906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143911003","display_name":"\u66f9\u7ea2\u68ee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongsen Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020391366","display_name":"Mona Jaber","orcid":"https://orcid.org/0000-0002-0908-3207","observed_orcids":["https://orcid.org/0000-0002-0908-3207"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mona Jaber","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158746429","display_name":"Shanxin Yuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanxin Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146963655","display_name":"Ahmed Sayed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Sayed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10036","display_name":"Advanced Neural Network Applications","score":0.06780000030994415,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.003800000064074993,"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/camera-lidar-fusion","display_name":"LiDAR-camera fusion","score":0.8640000224113464},{"id":"https://openalex.org/keywords/3d-object-detection","display_name":"3D object detection","score":0.9620000123977661},{"id":"https://openalex.org/keywords/autonomous-driving-perception","display_name":"autonomous driving perception","score":0.7540000081062317},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.9129999876022339},{"id":"https://openalex.org/keywords/modality-dominance","display_name":"modality dominance","score":0.6039999723434448},{"id":"https://openalex.org/keywords/attention-based-fusion","display_name":"attention fusion","score":0.5099999904632568},{"id":"https://openalex.org/keywords/nuscenes","display_name":"nuScenes","score":0.8209999799728394},{"id":"https://openalex.org/keywords/kitti","display_name":"KITTI","score":0.8309999704360962},{"id":"https://openalex.org/keywords/waymo","display_name":"Waymo","score":0.8050000071525574},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.7275999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6363999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5831000208854675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4700999855995178},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C141898687","wikidata":"https://www.wikidata.org/wiki/Q1501997","display_name":"Hausdorff distance","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.26649999618530273},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.66977/xsci.2610.0039","doi":"https://doi.org/10.66977/xsci.2610.0039","is_oa":false,"landing_page_url":"https://doi.org/10.66977/xsci.2610.0039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:arXiv.org:2610.16906","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.16906","pdf_url":"https://arxiv.org/pdf/2610.16906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.16906","doi":"https://doi.org/10.48550/arxiv.2610.16906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.16906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.16906","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.16906","pdf_url":"https://arxiv.org/pdf/2610.16906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221786441.pdf","grobid_xml":"https://content.openalex.org/works/W7221786441.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214279911","https://openalex.org/W4385076301","https://openalex.org/W4313024246","https://openalex.org/W4225986494","https://openalex.org/W4412626884","https://openalex.org/W7128505576","https://openalex.org/W4414333799","https://openalex.org/W7165749771","https://openalex.org/W7155581473","https://openalex.org/W4407794184"],"abstract_inverted_index":{"Multi-modal":[0],"fusion":[1,100,214],"for":[2,268],"3D":[3],"object":[4,41,110],"detection":[5],"assumes":[6],"that":[7,31,89,179,256],"cameras":[8],"and":[9,56,86,150,208,250],"LiDAR":[10],"are":[11,32,160],"broadly":[12],"complementary.":[13],"In":[14],"practice,":[15],"how":[16],"much":[17],"each":[18],"modality":[19,180],"is":[20,26,115,182,263],"trusted":[21],"at":[22,140],"a":[23,112,122,204,217,254,265],"given":[24],"location":[25],"decided":[27],"by":[28,42,127,224],"learned":[29],"weights":[30,249],"neither":[33],"characterized":[34],"nor":[35],"auditable.":[36],"We":[37,176,198],"label":[38],"every":[39],"ground-truth":[40],"which":[43,79],"modalities":[44],"detected":[45],"it,":[46],"then":[47],"mine":[48],"the":[49,59,65,70,98,109,128,144,164,169,188,200,248],"resulting":[50],"0.4M-object":[51],"database":[52],"across":[53],"nuScenes,":[54],"KITTI,":[55],"Waymo.":[57],"Because":[58],"patterns":[60],"shift":[61],"with":[62,185],"distance":[63,84],"from":[64],"ego":[66],"vehicle,":[67],"we":[68],"read":[69],"mined":[71,201],"model":[72],"through":[73,216],"Spatially":[74],"Stratified":[75],"Feature":[76],"Attribution":[77],"(SSFA),":[78],"conditions":[80],"Shapley":[81],"attribution":[82,91],"on":[83,153],"zones":[85],"exposes":[87],"structure":[88,202],"global":[90],"averages":[92],"away.":[93],"Three":[94],"assumptions":[95],"built":[96],"into":[97,203,211],"current":[99],"design":[101],"do":[102],"not":[103,161],"hold.":[104],"The":[105,156],"modality-preference":[106],"boundary":[107],"tracks":[108],"itself:":[111],"traffic":[113],"cone":[114],"nearly":[116],"six":[117],"times":[118],"as":[119,121,253],"likely":[120],"truck":[123],"to":[124,148,226],"be":[125,258],"seen":[126],"camera":[129],"alone":[130,167],"(16.8%":[131],"vs.":[132],"2.9%),":[133],"regardless":[134],"of":[135,158,173,236,247],"range.":[136],"Camera-only":[137],"detections":[138],"peak":[139],"10\u201330":[141],"m,":[142],"inside":[143],"band":[145],"usually":[146],"ceded":[147],"LiDAR,":[149],"fall":[151],"away":[152],"either":[154],"side.":[155],"drivers":[157],"failure":[159],"additive":[162],"either:":[163],"distance\u00d7density":[165],"interaction":[166],"outweighs":[168],"entire":[170],"main":[171],"effect":[172],"viewing":[174],"direction.":[175],"further":[177],"find":[178],"dominance":[181],"directionally":[183],"nonstationary,":[184],"objects":[186],"behind":[187],"vehicle":[189],"being":[190],"markedly":[191],"more":[192],"LiDAR-dominant":[193],"than":[194],"those":[195],"in":[196,239],"front.":[197],"compile":[199],"Modality":[205],"Reliability":[206],"Map":[207],"inject":[209],"it":[210,252],"four":[212],"pretrained":[213],"detectors":[215],"lightweight":[218],"attention":[219],"layer.":[220],"This":[221],"improves":[222],"performance":[223],"up":[225],"1.3":[227],"mean":[228],"Average":[229],"Precision":[230],"(mAP)":[231],"while":[232],"fine-tuning":[233],"under":[234],"4%":[235],"their":[237],"parameters":[238],"2\u20133":[240],"GPU-hours.":[241],"Our":[242],"work":[243],"lifts":[244],"reliability":[245],"out":[246],"treats":[251],"quantity":[255],"can":[257],"examined":[259],"before":[260],"deployment.":[261],"That":[262],"what":[264],"safety":[266],"measure":[267],"multimodal":[269],"perception":[270],"must":[271],"rest":[272],"on.":[273]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-15T00:00:00"}