{"id":"https://openalex.org/W4415286744","doi":"https://doi.org/10.1109/wacv61042.2026.00301","title":"GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving","display_name":"GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415286744","doi":"https://doi.org/10.1109/wacv61042.2026.00301"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.15672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053797102","display_name":"William Ljungbergh","orcid":"https://orcid.org/0000-0002-0194-6346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Ljungbergh","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010159086","display_name":"Adam Lilja","orcid":"https://orcid.org/0000-0001-5733-4472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Lilja","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Adam Tonderski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Tonderski","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arvid Laveno Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arvid Laveno Ling","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003312930","display_name":"Carl Lindstr\u00f6m","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carl Lindstr\u00f6m","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244596","display_name":"Willem Verbeke","orcid":"https://orcid.org/0000-0002-6860-210X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Willem Verbeke","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113096054","display_name":"Junsheng Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junsheng Fu","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013054127","display_name":"Christoffer Petersson","orcid":"https://orcid.org/0000-0002-9203-558X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoffer Petersson","raw_affiliation_strings":["Zenseact"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zenseact","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lars Hammarstrand","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lars Hammarstrand","raw_affiliation_strings":["Chalmers University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"last","author":{"id":null,"display_name":"Michael Felsberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Felsberg","raw_affiliation_strings":["Linköping University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linköping University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"3077","last_page":"3087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.8762999773025513,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.8762999773025513,"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.8639000058174133,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8234000205993652,"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/representation","display_name":"Representation (politics)","score":0.6097999811172485},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6007999777793884},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5121999979019165},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4717999994754791},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4684000015258789},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.42739999294281006},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/occupancy-grid-mapping","display_name":"Occupancy grid mapping","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601000070571899},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6097999811172485},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953999757766724},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C57077369","wikidata":"https://www.wikidata.org/wiki/Q7075747","display_name":"Occupancy grid mapping","level":4,"score":0.39399999380111694},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3346000015735626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2685999870300293}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv61042.2026.00301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.15672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15672","pdf_url":"https://arxiv.org/pdf/2503.15672","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:DiVA.org:liu-218890","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-218890","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.15672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.15672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.15672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15672","pdf_url":"https://arxiv.org/pdf/2503.15672","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Self-supervised":[0],"pre-training":[1,76,190],"based":[2],"on":[3,24,156],"next-token":[4],"prediction":[5,184],"has":[6,19],"enabled":[7],"large":[8,26],"language":[9],"models":[10],"to":[11,21,44,50],"capture":[12],"the":[13,45,52,59,97,101,108,113,138,146],"underlying":[14,53],"structure":[15,57,99],"of":[16,28,40,47,58,100,134,145],"text,":[17],"and":[18,55,61,73,115,128,148,170,181,188,197],"led":[20],"unprecedented":[22],"performance":[23],"a":[25,71,81,121,141,186],"array":[27],"tasks":[29],"when":[30],"applied":[31],"at":[32,86],"scale.":[33],"Similarly,":[34],"autonomous":[35,158,193],"driving":[36,159],"generates":[37],"vast":[38],"amounts":[39],"spatiotemporal":[41],"data,":[42],"alluding":[43],"possibility":[46],"harnessing":[48],"scale":[49],"learn":[51],"geometric":[54,72,127,180],"semantic":[56,74,129,165,182],"environment":[60,147],"its":[62,149],"evolution":[63,150],"over":[64],"time.":[65,152],"In":[66],"this":[67],"direction,":[68],"we":[69],"propose":[70],"self-supervised":[75],"method,":[77],"GASP,":[78],"that":[79,177],"learns":[80,140],"unified":[82],"representation":[83,144],"by":[84],"predicting,":[85],"any":[87],"queried":[88],"future":[89],"point":[90],"in":[91,164],"spacetime,":[92],"(1)":[93],"general":[94],"occupancy,":[95,106],"capturing":[96],"evolving":[98],"3D":[102],"scene;":[103],"(2)":[104],"ego":[105,109,171],"modeling":[107,126],"vehicle":[110],"path":[111],"through":[112,151],"environment;":[114],"(3)":[116],"distilled":[117],"high-level":[118],"features":[119],"from":[120],"vision":[122],"foundation":[123],"model.":[124],"By":[125],"4D":[130,179],"occupancy":[131,166,183],"fields":[132],"instead":[133],"raw":[135],"sensor":[136],"measurements,":[137],"model":[139],"structured,":[142],"generalizable":[143],"We":[153],"validate":[154],"GASP":[155],"multiple":[157],"benchmarks,":[160],"demonstrating":[161],"significant":[162],"improvements":[163],"forecasting,":[167],"online":[168],"mapping,":[169],"trajectory":[172],"prediction.":[173],"Our":[174],"results":[175],"demonstrate":[176],"continuous":[178],"provides":[185],"scalable":[187],"effective":[189],"paradigm":[191],"for":[192],"driving.":[194],"For":[195],"code":[196],"additional":[198],"visualizations,":[199],"see":[200],"our":[201],"project":[202],"page.":[203]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-17T00:00:00"}