{"id":"https://openalex.org/W7137054008","doi":"https://doi.org/10.1109/itsc60802.2025.11423488","title":"SMAE-DIM: Vehicle-Centric Semantic Masked AutoEncoders Pre-Training by Distilling Multimodal Foundational Models","display_name":"SMAE-DIM: Vehicle-Centric Semantic Masked AutoEncoders Pre-Training by Distilling Multimodal Foundational Models","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7137054008","doi":"https://doi.org/10.1109/itsc60802.2025.11423488"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073053332","display_name":"Alexandre Carriconde Marques","orcid":"https://orcid.org/0000-0002-1866-4169"},"institutions":[{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Alexandre Marques","raw_affiliation_strings":["University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125997105","display_name":"Pedro Ferreira","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro Ferreira","raw_affiliation_strings":["University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126031427","display_name":"Bruno Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bruno Silva","raw_affiliation_strings":["University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra,Institute of Systems and Robotics,Coimbra,Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126030684","display_name":"Jorge Batista","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jorge Batista","raw_affiliation_strings":["University of Coimbra,Institute of Systems and Robotics,Dept. of Electrical and Computer Engineering,Coimbra,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Coimbra,Institute of Systems and Robotics,Dept. of Electrical and Computer Engineering,Coimbra,Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69505507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3843","last_page":"3850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5005999803543091,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5005999803543091,"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/T10028","display_name":"Topic Modeling","score":0.06030000001192093,"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/T12031","display_name":"Speech and dialogue systems","score":0.0406000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3772999942302704},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36340001225471497},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.2858999967575073},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2685000002384186},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.25049999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.22699999809265137},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.22699999809265137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2519904008","https://openalex.org/W2789546350","https://openalex.org/W3043149731","https://openalex.org/W3092740872","https://openalex.org/W3139434170","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3170841864","https://openalex.org/W4214736485","https://openalex.org/W4285207098","https://openalex.org/W4312442470","https://openalex.org/W4312629998","https://openalex.org/W4312956471","https://openalex.org/W4313136445","https://openalex.org/W4313156423","https://openalex.org/W4382465386","https://openalex.org/W4385801120","https://openalex.org/W4388976122","https://openalex.org/W4389104669","https://openalex.org/W4390873744","https://openalex.org/W4393148742","https://openalex.org/W4393159256","https://openalex.org/W4400721967","https://openalex.org/W4402951563","https://openalex.org/W4403081406","https://openalex.org/W4409263152"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"SMAE-DIM,":[5],"a":[6,30,37,63,90,151],"vehiclecentric":[7],"semantic":[8,60,122,148],"Masked":[9,22],"Autoencoder":[10],"(MAE)":[11],"pre-training":[12],"by":[13,112],"distilling":[14],"multimodal":[15],"foundational":[16],"models.":[17],"Our":[18],"approach":[19],"integrates":[20],"MAE-based":[21],"Image":[23],"Modeling":[24],"(MIM)":[25],"with":[26,89],"CLIPstyle":[27],"distillation,":[28],"leveraging":[29,113],"curated,":[31],"large-scale":[32,54],"vehicle":[33],"dataset":[34,82],"(Automobile1M)":[35],"and":[36,126,143,147],"visually":[38,97],"grounded,":[39],"unpaired":[40],"text":[41,93],"corpus.":[42],"Unlike":[43],"traditional":[44],"vision-language":[45,110],"models":[46],"that":[47,131],"require":[48],"carefully":[49],"curated":[50,84],"image-caption":[51],"pairs":[52],"or":[53],"aligned":[55],"datasets,":[56],"our":[57],"method":[58],"distills":[59],"knowledge":[61],"from":[62],"pre-trained":[64],"CLIP":[65],"model":[66],"without":[67],"the":[68],"need":[69],"for":[70,85],"direct":[71],"image-text":[72],"alignment":[73,123],"during":[74,109],"training.":[75],"We":[76],"also":[77],"introduce":[78],"Automobile1M-a":[79],"largescale,":[80],"in-domain":[81],"specifically":[83],"vehicle-centric":[86],"pre-training,":[87],"alongside":[88],"dedicated":[91],"distillation":[92,101,111],"corpus":[94],"focused":[95],"on":[96],"grounded":[98],"language.":[99],"Specialized":[100],"losses":[102],"were":[103],"employed":[104],"to":[105,135],"enhance":[106],"open-vocabulary":[107],"logits":[108],"image":[114],"embeddings":[115],"as":[116],"auxiliary":[117],"pseudo-text":[118],"embeddings,":[119],"thereby":[120],"strengthening":[121],"between":[124],"visual":[125],"textual":[127],"modalities.":[128],"Experiments":[129],"demonstrate":[130],"SMAE-DIM":[132],"effectively":[133],"transfers":[134],"vehiclespecific":[136],"downstream":[137],"tasks":[138],"via":[139],"both":[140],"linear":[141],"probing":[142],"fine-tuning,":[144],"unifying":[145],"structural":[146],"understanding":[149],"within":[150],"single":[152],"pretraining":[153],"framework.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-17T00:00:00"}