{"id":"https://openalex.org/W4401506914","doi":"https://doi.org/10.1109/tits.2024.3437645","title":"EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving","display_name":"EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving","publication_year":2024,"publication_date":"2024-08-12","ids":{"openalex":"https://openalex.org/W4401506914","doi":"https://doi.org/10.1109/tits.2024.3437645"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3437645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3437645","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-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/A5101566662","display_name":"Jiacheng Lin","orcid":"https://orcid.org/0000-0003-1393-5027"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiacheng Lin","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013026483","display_name":"Jiajun Chen","orcid":"https://orcid.org/0009-0008-9584-202X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["School of Robotics, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017521271","display_name":"Kunyu Peng","orcid":"https://orcid.org/0000-0002-5419-9292"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kunyu Peng","raw_affiliation_strings":["Institute for Robotics and Anthropomatics, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Anthropomatics, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007423796","display_name":"Xuan He","orcid":"https://orcid.org/0000-0001-8150-0135"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan He","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396723","display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["School of Robotics, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087051920","display_name":"Rainer Stiefelhagen","orcid":"https://orcid.org/0000-0001-8046-4945"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Stiefelhagen","raw_affiliation_strings":["Institute for Robotics and Anthropomatics, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Anthropomatics, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027010844","display_name":"Kailun Yang","orcid":"https://orcid.org/0000-0002-1090-667X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailun Yang","raw_affiliation_strings":["School of Robotics, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101566662"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":6.1604,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97297584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"11","first_page":"18964","last_page":"18977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9800999760627747,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9800999760627747,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9761999845504761,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9513999819755554,"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/computer-science","display_name":"Computer science","score":0.6232861876487732},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6087669134140015},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5320032238960266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5301347970962524},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.47770264744758606},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41936856508255005},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.41721513867378235},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14024686813354492},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.06294688582420349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6232861876487732},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6087669134140015},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5320032238960266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5301347970962524},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.47770264744758606},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41936856508255005},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.41721513867378235},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14024686813354492},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.06294688582420349},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3437645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3437645","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4041047505","display_name":null,"funder_award_id":"U23A20341","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W2055022211","https://openalex.org/W2124781496","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2291627510","https://openalex.org/W2603203130","https://openalex.org/W2962803115","https://openalex.org/W2963354481","https://openalex.org/W2963680395","https://openalex.org/W2969535679","https://openalex.org/W2972691802","https://openalex.org/W2983208726","https://openalex.org/W3010309142","https://openalex.org/W3031594087","https://openalex.org/W3034739212","https://openalex.org/W3035097537","https://openalex.org/W3035564946","https://openalex.org/W3086436251","https://openalex.org/W3092514003","https://openalex.org/W3094000868","https://openalex.org/W3104778224","https://openalex.org/W3104844437","https://openalex.org/W3108367559","https://openalex.org/W3115390238","https://openalex.org/W3118333521","https://openalex.org/W3119686997","https://openalex.org/W3164698655","https://openalex.org/W3170088426","https://openalex.org/W3173209770","https://openalex.org/W3174101598","https://openalex.org/W3179985441","https://openalex.org/W3184439416","https://openalex.org/W3195644833","https://openalex.org/W3195775608","https://openalex.org/W3199871897","https://openalex.org/W3206219722","https://openalex.org/W3207452968","https://openalex.org/W3207740618","https://openalex.org/W3207759028","https://openalex.org/W3209059054","https://openalex.org/W3212750552","https://openalex.org/W4210407300","https://openalex.org/W4212862319","https://openalex.org/W4225765046","https://openalex.org/W4226166791","https://openalex.org/W4286904999","https://openalex.org/W4287657926","https://openalex.org/W4306394127","https://openalex.org/W4312473433","https://openalex.org/W4312504688","https://openalex.org/W4312619242","https://openalex.org/W4312689495","https://openalex.org/W4312689520","https://openalex.org/W4313117614","https://openalex.org/W4313123347","https://openalex.org/W4319300771","https://openalex.org/W4321766229","https://openalex.org/W4365606129","https://openalex.org/W4377864668","https://openalex.org/W4378170107","https://openalex.org/W4385569741","https://openalex.org/W4385714071","https://openalex.org/W4386065815","https://openalex.org/W4386075493","https://openalex.org/W4386076180","https://openalex.org/W4386083103","https://openalex.org/W4386621530","https://openalex.org/W4386918943","https://openalex.org/W4387182937","https://openalex.org/W4387546313","https://openalex.org/W4387925398","https://openalex.org/W4390872419","https://openalex.org/W4390872615","https://openalex.org/W4390872864","https://openalex.org/W4390872914","https://openalex.org/W4390873204","https://openalex.org/W4390905041","https://openalex.org/W4392904092","https://openalex.org/W4393156599","https://openalex.org/W4402726924","https://openalex.org/W6696672603","https://openalex.org/W6757817989","https://openalex.org/W6784094891","https://openalex.org/W6784607962","https://openalex.org/W6785302134","https://openalex.org/W6788023325","https://openalex.org/W6788043773","https://openalex.org/W6798838024","https://openalex.org/W6800584378","https://openalex.org/W6810591155","https://openalex.org/W6851607685","https://openalex.org/W6852713287","https://openalex.org/W6853002730","https://openalex.org/W6856005155","https://openalex.org/W6856594407"],"related_works":["https://openalex.org/W4389065903","https://openalex.org/W2158788032","https://openalex.org/W2385949326","https://openalex.org/W1966005655","https://openalex.org/W3135795035","https://openalex.org/W2789220062","https://openalex.org/W2811496562","https://openalex.org/W2094665863","https://openalex.org/W2071984725","https://openalex.org/W2185534064"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,35,58,67,73,87,92,141,171,176,191,195,198],"task":[4],"of":[5,37,60,69,75,89,94,179,197],"Auditory":[6],"Referring":[7],"Multi-Object":[8],"Tracking":[9,144],"(AR-MOT),":[10],"which":[11,54,125],"dynamically":[12],"tracks":[13],"specific":[14],"objects":[15,157,167],"in":[16,30,41,78],"a":[17,27],"video":[18,130,166],"sequence":[19],"based":[20],"on":[21,50,190],"audio":[22,42,128,164],"expressions":[23,154],"and":[24,43,65,97,129,135,155,165,186,201,207],"appears":[25],"as":[26],"challenging":[28],"problem":[29,88],"autonomous":[31,79],"driving.":[32,80],"Due":[33],"to":[34,148],"lack":[36],"semantic":[38,151],"modeling":[39],"capacity":[40],"video,":[44],"existing":[45],"works":[46],"have":[47],"mainly":[48],"focused":[49],"text-based":[51],"multi-object":[52],"tracking,":[53],"often":[55],"comes":[56],"at":[57,211],"cost":[59],"tracking":[61],"quality,":[62],"interaction":[63],"efficiency,":[64],"even":[66],"safety":[68],"assistance":[70],"systems,":[71],"limiting":[72],"application":[74],"such":[76],"methods":[77],"In":[81],"this":[82],"paper,":[83],"we":[84,139,174],"delve":[85],"into":[86],"AR-MOT":[90,106,181],"from":[91,132,170],"perspective":[93],"audio-video":[95,98],"fusion":[96],"tracking.":[99],"We":[100],"put":[101],"forward":[102],"EchoTrack,":[103],"an":[104],"end-to-end":[105],"framework":[107],"with":[108,117],"dual-stream":[109],"vision":[110],"transformers.":[111],"The":[112,204],"dual":[113],"streams":[114],"are":[115,209],"intertwined":[116],"our":[118],"Bidirectional":[119],"Frequency-domain":[120],"Cross-attention":[121],"Fusion":[122],"Module":[123],"(Bi-FCFM),":[124],"bidirectionally":[126],"fuses":[127],"features":[131,152,161],"both":[133],"frequency-":[134],"spatiotemporal":[136],"domains.":[137],"Moreover,":[138],"propose":[140],"Audio-visual":[142],"Contrastive":[143],"Learning":[145],"(ACTL)":[146],"regime":[147],"extract":[149],"homogeneous":[150,160],"between":[153,162],"visual":[156],"by":[158],"learning":[159],"different":[163],"effectively.":[168],"Aside":[169],"architectural":[172],"design,":[173],"establish":[175],"first":[177],"set":[178],"large-scale":[180],"benchmarks,":[182],"including":[183],"Echo-KITTI,":[184],"Echo-KITTI+,":[185],"Echo-BDD.":[187],"Extensive":[188],"experiments":[189],"established":[192],"benchmarks":[193],"demonstrate":[194],"effectiveness":[196],"proposed":[199],"EchoTrack":[200],"its":[202],"components.":[203],"source":[205],"code":[206],"datasets":[208],"available":[210],"<uri":[212],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[213],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/lab206/EchoTrack</uri>.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}