{"id":"https://openalex.org/W7138123808","doi":"https://doi.org/10.1609/aaai.v40i8.37580","title":"Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception","display_name":"Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138123808","doi":"https://doi.org/10.1609/aaai.v40i8.37580"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i8.37580","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37580","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37580","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129682854","display_name":"Xiaoyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007154158","display_name":"Peidong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peidong Li","raw_affiliation_strings":["IROOTECH, Guangzhou, China\nWolf 1069b, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IROOTECH, Guangzhou, China\nWolf 1069b, Guangzhou, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129654276","display_name":"Xian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743704","display_name":"Long Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Shi","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062785978","display_name":"Dedong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dedong Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652086","display_name":"Yitao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitao Wu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121656166","display_name":"Jiajia Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajia Fu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664583","display_name":"Dixiao Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dixiao Cui","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129646117","display_name":"Lijun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129658942","display_name":"Lining Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lining Sun","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129682854"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31746032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6513","last_page":"6520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.3109000027179718,"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":0.3109000027179718,"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/T12290","display_name":"Human Motion and Animation","score":0.12530000507831573,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0714000016450882,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5766000151634216},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/motion-perception","display_name":"Motion perception","score":0.4018000066280365},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.36149999499320984},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656000018119812},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C48575856","wikidata":"https://www.wikidata.org/wiki/Q852504","display_name":"Motion perception","level":3,"score":0.4018000066280365},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i8.37580","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37580","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37580","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37580","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.45668289065361023,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatio-temporal":[0],"alignment":[1,82,92,103,150],"is":[2],"crucial":[3],"for":[4,53,127,152],"temporal":[5,162],"modeling":[6,62,217],"of":[7,59,215],"end-to-end":[8],"(E2E)":[9],"perception":[10,66,195,223],"in":[11,63,70,142,226],"autonomous":[12],"driving":[13],"(AD),":[14],"providing":[15,147],"valuable":[16],"structural":[17],"and":[18,73,78,123,138,164,201,224],"textural":[19],"prior":[20],"information.":[21],"Existing":[22],"methods":[23],"typically":[24],"rely":[25],"on":[26,177],"the":[27,36,57,64,101,148,153,178,184,203,213,227],"attention":[28],"mechanism":[29],"to":[30,98,119],"align":[31],"objects":[32],"across":[33,76,166],"frames,":[34],"simplifying":[35],"motion":[37,61,71,117,139,216],"model":[38,44],"with":[39,174,183],"a":[40,90],"unified":[41],"explicit":[42,60,116],"physical":[43],"(constant":[45],"velocity,":[46],"etc.).":[47],"These":[48],"approaches":[49],"prefer":[50],"semantic":[51,137],"features":[52,75],"implicit":[54],"alignment,":[55],"challenging":[56],"importance":[58],"traditional":[65],"paradigm.":[67],"However,":[68],"variations":[69],"states":[72],"object":[74,97,144],"categories":[77],"frames":[79],"render":[80],"this":[81],"suboptimal.":[83],"To":[84],"address":[85],"this,":[86],"we":[87],"propose":[88],"HAT,":[89],"spatio-temporal":[91],"module":[93],"that":[94],"allows":[95],"each":[96],"adaptively":[99],"decode":[100],"optimal":[102,149],"proposal":[104,151],"from":[105],"multiple":[106,115],"hypotheses":[107],"without":[108],"direct":[109],"supervision.":[110],"Specifically,":[111],"HAT":[112,158,193,219],"first":[113],"utilizes":[114],"models":[118],"generate":[120],"spatial":[121],"anchors":[122],"motion-aware":[124],"feature":[125],"proposals":[126],"historical":[128],"instances.":[129],"It":[130,169],"then":[131],"performs":[132],"multi-hypothesis":[133],"decoding":[134],"by":[135,206,218],"incorporating":[136],"cues":[140],"embedded":[141],"cached":[143],"queries,":[145],"ultimately":[146],"target":[154],"frame.":[155],"On":[156],"nuScenes,":[157],"consistently":[159],"improves":[160],"3D":[161],"detectors":[163],"trackers":[165],"diverse":[167],"baselines.":[168],"achieves":[170],"state-of-the-art":[171],"tracking":[172],"results":[173],"46.0%":[175],"AMOTA":[176],"test":[179],"set":[180],"when":[181],"paired":[182],"DETR3D":[185],"detector.":[186],"In":[187],"an":[188],"object-centric":[189],"E2E":[190,228],"AD":[191],"method,":[192],"enhances":[194],"accuracy":[196],"(+1.3%":[197],"mAP,":[198],"+3.1%":[199],"AMOTA)":[200],"reduces":[202],"collision":[204],"rate":[205],"32%.":[207],"When":[208],"semantics":[209],"are":[210],"corrupted":[211],"(nuScenes-C),":[212],"enhancement":[214],"enables":[220],"more":[221],"robust":[222],"planning":[225],"AD.":[229]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-18T00:00:00"}
