{"id":"https://openalex.org/W4400649796","doi":"https://doi.org/10.1109/iv55156.2024.10588635","title":"TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction","display_name":"TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400649796","doi":"https://doi.org/10.1109/iv55156.2024.10588635"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","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/A5040592157","display_name":"Junrui Zhang","orcid":"https://orcid.org/0009-0005-8244-2770"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Junrui Zhang","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032684585","display_name":"Mozhgan Pourkeshavarz","orcid":"https://orcid.org/0000-0001-9657-0793"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mozhgan Pourkeshavarz","raw_affiliation_strings":["Huawei Technologies Canada,Noah’s Ark Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada,Noah’s Ark Laboratory","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012752787","display_name":"Amir Rasouli","orcid":"https://orcid.org/0000-0002-0106-2225"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir Rasouli","raw_affiliation_strings":["Huawei Technologies Canada,Noah’s Ark Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada,Noah’s Ark Laboratory","institution_ids":["https://openalex.org/I4210115038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4017,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79442702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3282","last_page":"3288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9945999979972839,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/trajectory","display_name":"Trajectory","score":0.7645554542541504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7192719578742981},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.621520459651947},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5270745158195496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029544234275818},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494367003440857},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1144726574420929}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7645554542541504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192719578742981},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.621520459651947},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5270745158195496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029544234275818},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494367003440857},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1144726574420929},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2020209171","https://openalex.org/W2118978333","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2339172597","https://openalex.org/W2532516272","https://openalex.org/W2799059904","https://openalex.org/W2955189650","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963816519","https://openalex.org/W2970941190","https://openalex.org/W3022061250","https://openalex.org/W3035096461","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3090783937","https://openalex.org/W3090789587","https://openalex.org/W3103649165","https://openalex.org/W3108486966","https://openalex.org/W3116651890","https://openalex.org/W3122855191","https://openalex.org/W3132250316","https://openalex.org/W3136608531","https://openalex.org/W3139491754","https://openalex.org/W3180491419","https://openalex.org/W3191907322","https://openalex.org/W3196864007","https://openalex.org/W4225918570","https://openalex.org/W4312366598","https://openalex.org/W4313054679","https://openalex.org/W4383066546","https://openalex.org/W4383097400","https://openalex.org/W4383109107","https://openalex.org/W4385221361","https://openalex.org/W4386065605","https://openalex.org/W4386072089","https://openalex.org/W4386076060","https://openalex.org/W4386076407","https://openalex.org/W4390872109","https://openalex.org/W4390874244","https://openalex.org/W4401414548","https://openalex.org/W4401415859","https://openalex.org/W4401417197","https://openalex.org/W6764733053","https://openalex.org/W6784071224","https://openalex.org/W6790920653"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"a":[1,31,52,132,141,151,173,189,228],"safety":[2],"critical":[3],"task,":[4],"autonomous":[5],"driving":[6],"requires":[7],"accurate":[8],"predictions":[9],"of":[10,116,197,230,238],"road":[11],"users\u2019":[12],"future":[13],"trajectories":[14],"for":[15,74],"safe":[16],"motion":[17,85],"planning,":[18],"particularly":[19],"under":[20],"challenging":[21,36,58],"conditions.":[22],"Yet,":[23],"many":[24],"recent":[25],"deep":[26],"learning":[27,135,191],"methods":[28,56],"suffer":[29],"from":[30],"degraded":[32],"performance":[33,212],"on":[34,83,162,219,227],"the":[35,46,63,84,117,163,168,183,186,220,231,235],"scenarios,":[37,89],"mainly":[38],"because":[39],"these":[40],"scenarios":[41,59],"appear":[42],"less":[43],"frequently":[44],"in":[45,62,188,241],"training":[47,67,128,169,243],"data.":[48],"To":[49],"address":[50],"such":[51,95,105],"long-tail":[53,221],"issue,":[54],"existing":[55],"force":[57],"closer":[60],"together":[61],"feature":[64],"space":[65],"during":[66],"to":[68,87,125,233],"trigger":[69],"information":[70,106,130],"sharing":[71],"among":[72],"them":[73],"more":[75,91],"robust":[76],"learning.":[77],"These":[78,155],"methods,":[79],"however,":[80],"primarily":[81],"rely":[82],"patterns":[86],"characterize":[88],"omitting":[90],"informative":[92],"contextual":[93,148],"information,":[94,171],"as":[96],"interactions":[97],"and":[98,172,205,216],"scene":[99,114,217],"layout.":[100],"We":[101,193],"argue":[102],"that":[103,207],"exploiting":[104],"not":[107],"only":[108],"improves":[109],"prediction":[110],"accuracy":[111,215],"but":[112],"also":[113],"compliance":[115,218],"generated":[118],"trajectories.":[119],"In":[120],"this":[121],"paper,":[122],"we":[123,139,145,181,224],"propose":[124,140],"incorporate":[126],"richer":[127],"dynamics":[129,170],"into":[131,159],"prototypical":[133],"contrastive":[134,190],"framework.":[136,154,192],"More":[137],"specifically,":[138],"two-stage":[142],"process.":[143],"First,":[144],"generate":[146],"rich":[147],"features":[149,156],"using":[150,167,185,200],"baseline":[152],"encoder-decoder":[153],"are":[157],"split":[158],"clusters":[160,232],"based":[161],"model\u2019s":[164],"output":[165],"errors,":[166],"prototype":[174],"is":[175],"computed":[176],"within":[177],"each":[178],"cluster.":[179],"Second,":[180],"retrain":[182],"model":[184],"prototypes":[187],"conduct":[194],"empirical":[195],"evaluations":[196],"our":[198,208,239],"approach":[199,240],"two":[201],"large-scale":[202],"naturalistic":[203],"datasets":[204],"show":[206],"method":[209],"achieves":[210],"state-of-the-art":[211],"by":[213],"improving":[214],"samples.":[222],"Furthermore,":[223],"perform":[225],"experiments":[226],"subset":[229],"highlight":[234],"additional":[236],"benefit":[237],"reducing":[242],"bias.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}