{"id":"https://openalex.org/W7117243533","doi":"https://doi.org/10.48550/arxiv.2512.19934","title":"Vehicle-centric Perception via Multimodal Structured Pre-training","display_name":"Vehicle-centric Perception via Multimodal Structured Pre-training","publication_year":2025,"publication_date":"2025-12-22","ids":{"openalex":"https://openalex.org/W7117243533","doi":"https://doi.org/10.48550/arxiv.2512.19934"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.19934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19934","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.19934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121266605","display_name":"Wentao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Wentao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121287752","display_name":"Xiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121269267","display_name":"Chenglong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenglong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121273437","display_name":"Jin Y Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103220986","display_name":"Bin Luo","orcid":"https://orcid.org/0000-0003-0419-6058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Bin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121266605"],"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":0.527899980545044,"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":0.527899980545044,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11100000143051147,"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":0.06530000269412994,"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/feature","display_name":"Feature (linguistics)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5893999934196472},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.580299973487854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5461000204086304},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5367000102996826},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4544999897480011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6608999967575073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.580299973487854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5602999925613403},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.19934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19934","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.19934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19934","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vehicle-centric":[0],"perception":[1,37],"plays":[2],"a":[3,46,195],"crucial":[4],"role":[5],"in":[6,30],"many":[7],"intelligent":[8,14],"systems,":[9,13],"including":[10,109],"large-scale":[11,196],"surveillance":[12],"transportation,":[15],"and":[16,54,94,112,128,136,149,152,170,204],"autonomous":[17],"driving.":[18],"Existing":[19],"approaches":[20],"lack":[21],"effective":[22],"learning":[23,169],"of":[24,103,114,190,218],"vehicle-related":[25,56],"knowledge":[26],"during":[27,160,183],"pre-training,":[28],"resulting":[29],"poor":[31],"capability":[32,74],"for":[33,79],"modeling":[34],"general":[35],"vehicle":[36,120,157,202],"representations.":[38],"To":[39,186],"handle":[40],"this":[41],"problem,":[42],"we":[43,83,192],"propose":[44],"VehicleMAE-V2,":[45,191],"novel":[47],"vehicle-centric":[48,80],"pre-trained":[49],"large":[50],"model.":[51],"By":[52],"exploring":[53],"exploiting":[55],"multimodal":[57],"structured":[58,104],"priors":[59,105],"to":[60,75,99,123,173],"guide":[61],"the":[62,72,85,119,142,175,188,215],"masked":[63,133,184],"token":[64,107],"reconstruction":[65,108],"process,":[66],"our":[67],"approach":[68],"can":[69,129,153],"significantly":[70],"enhance":[71],"model's":[73],"learn":[76],"generalizable":[77],"representations":[78],"perception.":[81],"Specifically,":[82],"design":[84],"Symmetry-guided":[86],"Mask":[87],"Module":[88,92,97],"(SMM),":[89],"Contour-guided":[90],"Representation":[91,96],"(CRM)":[93],"Semantics-guided":[95],"(SRM)":[98],"incorporate":[100],"three":[101],"kinds":[102],"into":[106],"symmetry,":[110],"contour":[111,147],"semantics":[113],"vehicles":[115],"respectively.":[116],"SMM":[117],"utilizes":[118],"symmetry":[121],"constraints":[122],"avoid":[124],"retaining":[125],"symmetric":[126],"patches":[127,135],"thus":[130,154],"select":[131],"high-quality":[132],"image":[134],"reduce":[137],"information":[138,159],"redundancy.":[139],"CRM":[140],"minimizes":[141],"probability":[143],"distribution":[144],"divergence":[145],"between":[146],"features":[148,151,166],"reconstructed":[150],"preserve":[155],"holistic":[156],"structure":[158],"pixel-level":[161],"reconstruction.":[162,185],"SRM":[163],"aligns":[164],"image-text":[165],"through":[167],"contrastive":[168],"cross-modal":[171],"distillation":[172],"address":[174],"feature":[176],"confusion":[177],"caused":[178],"by":[179],"insufficient":[180],"semantic":[181],"understanding":[182],"support":[187],"pre-training":[189],"construct":[193],"Autobot4M,":[194],"dataset":[197],"comprising":[198],"approximately":[199],"4":[200],"million":[201],"images":[203],"12,693":[205],"text":[206],"descriptions.":[207],"Extensive":[208],"experiments":[209],"on":[210],"five":[211],"downstream":[212],"tasks":[213],"demonstrate":[214],"superior":[216],"performance":[217],"VehicleMAE-V2.":[219]},"counts_by_year":[],"updated_date":"2025-12-25T23:15:44.422516","created_date":"2025-12-25T00:00:00"}