{"id":"https://openalex.org/W4408345927","doi":"https://doi.org/10.1109/icassp49660.2025.10889208","title":"Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained Model for Acoustic Traffic Monitoring","display_name":"Graph-Enhanced Dual-Stream Feature Fusion with Pre-Trained Model for Acoustic Traffic Monitoring","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345927","doi":"https://doi.org/10.1109/icassp49660.2025.10889208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031216167","display_name":"Shitong Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shitong Fan","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062281933","display_name":"Feiyang Xiao","orcid":"https://orcid.org/0000-0001-9359-4554"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Xiao","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenbo Wang","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"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenbo Wang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","University of Surrey,Centre for Vision, Speech and Signal Processing,Guildford,UK"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050911130","display_name":"Shuhan Qi","orcid":"https://orcid.org/0000-0002-6903-145X"},"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":"Shuhan Qi","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104012520","display_name":"Qiaoxi Zhu","orcid":"https://orcid.org/0000-0003-3942-0945"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiaoxi Zhu","raw_affiliation_strings":["University of Technology Sydney,Acoustics Lab,Ultimo,Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Acoustics Lab,Ultimo,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"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"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","University of Surrey,Centre for Vision, Speech and Signal Processing,Guildford,UK"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing,Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059231561","display_name":"Jian Guan","orcid":"https://orcid.org/0000-0002-0945-1081"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Guan","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031216167"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03869185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9962000250816345,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9835000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6960311532020569},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5147757530212402},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4649563729763031},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4485814869403839},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.41827869415283203},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37440329790115356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3595762848854065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.355404257774353},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14457327127456665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960311532020569},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5147757530212402},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4649563729763031},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4485814869403839},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.41827869415283203},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37440329790115356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3595762848854065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.355404257774353},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14457327127456665},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2032898308","https://openalex.org/W2037684811","https://openalex.org/W2141996170","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2613579606","https://openalex.org/W2903924980","https://openalex.org/W2950635152","https://openalex.org/W3094550259","https://openalex.org/W3120053842","https://openalex.org/W3216115978","https://openalex.org/W4205506486","https://openalex.org/W4220839293","https://openalex.org/W4364373974","https://openalex.org/W4385245566","https://openalex.org/W4392909683","https://openalex.org/W4402111235","https://openalex.org/W6637373629","https://openalex.org/W6922580442"],"related_works":["https://openalex.org/W2317351040","https://openalex.org/W2952466936","https://openalex.org/W1988622314","https://openalex.org/W2393949104","https://openalex.org/W2099421762","https://openalex.org/W4236344264","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Microphone":[0],"array":[1],"techniques":[2],"are":[3],"widely":[4],"used":[5,138],"in":[6,139,183,203],"sound":[7],"source":[8],"localization":[9],"and":[10,32,35,58,87,117,127,147,162,175],"smart":[11],"city":[12],"acoustic-based":[13],"traffic":[14,29,80],"monitoring,":[15,81],"but":[16],"these":[17,168],"applications":[18],"face":[19],"significant":[20],"challenges":[21],"due":[22],"to":[23,51,89,123,143,158],"the":[24,33,125,140,149,189,204],"scarcity":[25,146],"of":[26,37,102,173,191],"labeled":[27],"real-world":[28],"audio":[30,49,165],"data":[31,145],"complexity":[34],"diversity":[36],"application":[38],"scenarios.":[39],"The":[40,170],"DCASE":[41,205],"Challenge\u2019s":[42],"Task":[43,208],"10":[44],"focuses":[45],"on":[46],"using":[47],"multi-channel":[48],"signals":[50],"count":[52],"vehicles":[53],"(cars":[54],"or":[55,63],"commercial":[56],"vehicles)":[57],"identify":[59],"their":[60],"directions":[61],"(left-to-right":[62],"vice":[64],"versa).":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70,93],"a":[71,94,103,110,118,154],"graph-enhanced":[72,95],"dual-stream":[73,96],"feature":[74,97,106,113,120,129,180],"fusion":[75,98,121,172],"network":[76],"(GEDF-Net)":[77],"for":[78,130],"acoustic":[79],"which":[82,100],"simultaneously":[83],"considers":[84],"vehicle":[85,104,111],"type":[86,105,126,150,176],"direction":[88,112,128,174],"improve":[90],"detection.":[91],"We":[92],"strategy":[99],"consists":[101],"extraction":[107,114],"(VTFE)":[108],"branch,":[109,116],"(VDFE)":[115],"frame-level":[119,171],"module":[122],"combine":[124],"enhanced":[131],"performance.":[132,186],"A":[133],"pre-trained":[134],"model":[135],"(PANNs)":[136],"is":[137,196],"VTFE":[141],"branch":[142],"mitigate":[144],"enhance":[148],"features,":[151],"followed":[152],"by":[153],"graph":[155],"attention":[156],"mechanism":[157],"exploit":[159],"temporal":[160],"relationships":[161],"highlight":[163],"important":[164],"events":[166],"within":[167],"features.":[169],"features":[177],"enables":[178],"fine-grained":[179],"representation,":[181],"resulting":[182],"better":[184],"detection":[185],"Experiments":[187],"demonstrate":[188],"effectiveness":[190],"our":[192,197],"proposed":[193],"method.":[194],"GEDF-Net":[195],"submission":[198],"that":[199],"achieved":[200],"1st":[201],"place":[202],"2024":[206],"Challenge":[207],"10.":[209]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}