{"id":"https://openalex.org/W7128612321","doi":"https://doi.org/10.48550/arxiv.2602.09425","title":"Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification","display_name":"Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128612321","doi":"https://doi.org/10.48550/arxiv.2602.09425"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.09425","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125657719","display_name":"Yiqiao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yiqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125641487","display_name":"Bo Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125642139","display_name":"Jie Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jie","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":false,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9337999820709229,"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":0.9337999820709229,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.012000000104308128,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.008999999612569809,"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/bridging","display_name":"Bridging (networking)","score":0.7695000171661377},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.618399977684021},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48829999566078186},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4645000100135803},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44909998774528503},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.4244000017642975},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7695000171661377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6342999935150146},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.618399977684021},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44909998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43700000643730164},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C52121051","wikidata":"https://www.wikidata.org/wiki/Q43193","display_name":"Truck","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.09425","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.09425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.09425","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.09425","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5782677531242371}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"truck":[1,71],"classification":[2,72,120,194],"is":[3,42],"critical":[4],"for":[5,69,199],"intelligent":[6],"transportation":[7],"systems":[8],"(ITS),":[9],"yet":[10],"current":[11],"LiDAR-based":[12],"methods":[13],"face":[14],"scalability":[15],"challenges":[16],"due":[17,161],"to":[18,39,96,134,162,181],"their":[19,37],"reliance":[20],"on":[21,108],"supervised":[22,136,184],"deep":[23],"learning":[24],"and":[25,53,86,93,205],"labor-intensive":[26],"manual":[27,222],"annotation.":[28],"Vision-Language":[29],"Models":[30],"(VLMs)":[31],"offer":[32],"promising":[33],"few-shot":[34,188],"generalization,":[35],"but":[36,155],"application":[38],"roadside":[40],"LiDAR":[41,100],"limited":[43],"by":[44,65],"a":[45,59,109,131,141,174,226],"modality":[46],"gap":[47,64],"between":[48],"sparse":[49],"3D":[50],"point":[51],"clouds":[52],"dense":[54],"2D":[55,104],"imagery.":[56],"We":[57,138],"propose":[58],"framework":[60,172],"that":[61],"bridges":[62],"this":[63,171],"adapting":[66],"off-the-shelf":[67],"VLMs":[68],"fine-grained":[70],"without":[73,209],"parameter":[74],"fine-tuning.":[75],"Our":[76],"new":[77],"depth-aware":[78],"image":[79],"generation":[80],"pipeline":[81],"applies":[82],"noise":[83],"removal,":[84],"spatial":[85],"temporal":[87],"registration,":[88],"orientation":[89],"rectification,":[90],"morphological":[91],"operations,":[92],"anisotropic":[94],"smoothing":[95],"transform":[97],"sparse,":[98],"occluded":[99],"scans":[101],"into":[102],"depth-encoded":[103],"visual":[105],"proxies.":[106],"Validated":[107],"real-world":[110],"dataset":[111],"of":[112,170,196,220,228],"20":[113],"vehicle":[114],"classes,":[115],"our":[116],"approach":[117],"achieves":[118,191],"competitive":[119],"accuracy":[121,157],"with":[122],"as":[123,125,173],"few":[124],"16-30":[126],"examples":[127],"per":[128],"class,":[129],"offering":[130],"scalable":[132],"alternative":[133],"data-intensive":[135],"baselines.":[137],"further":[139],"observe":[140],"\"Semantic":[142],"Anchor\"":[143],"effect:":[144],"text-based":[145],"guidance":[146],"regularizes":[147],"performance":[148],"in":[149,158,231],"ultra-low-shot":[150],"regimes":[151],"$k":[152],"<":[153],"4$,":[154],"degrades":[156],"more-shot":[159],"settings":[160],"semantic":[163],"mismatch.":[164],"Furthermore,":[165],"we":[166],"demonstrate":[167],"the":[168,187,210,217],"efficacy":[169],"Cold":[175],"Start":[176],"strategy,":[177],"using":[178],"VLM-generated":[179],"labels":[180],"bootstrap":[182],"lightweight":[183],"models.":[185],"Notably,":[186],"VLM-based":[189],"model":[190],"over":[192],"correct":[193],"rate":[195],"75":[197],"percent":[198],"specific":[200],"drayage":[201],"categories":[202],"(20ft,":[203],"40ft,":[204],"53ft":[206],"containers)":[207],"entirely":[208],"costly":[211],"training":[212],"or":[213],"fine-tuning,":[214],"significantly":[215],"reducing":[216],"intensive":[218],"demands":[219],"initial":[221],"labeling,":[223],"thus":[224],"achieving":[225],"method":[227],"practical":[229],"use":[230],"ITS":[232],"applications.":[233]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-12T00:00:00"}