{"id":"https://openalex.org/W4388206816","doi":"https://doi.org/10.1145/3604078.3604108","title":"ML-VehicleDet: A Unified Multi-label Vehicle Detection Framework","display_name":"ML-VehicleDet: A Unified Multi-label Vehicle Detection Framework","publication_year":2023,"publication_date":"2023-05-19","ids":{"openalex":"https://openalex.org/W4388206816","doi":"https://doi.org/10.1145/3604078.3604108"},"language":"en","primary_location":{"id":"doi:10.1145/3604078.3604108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604078.3604108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Digital Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079695819","display_name":"Runwei Guan","orcid":"https://orcid.org/0000-0003-4013-2107"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Runwei Guan","raw_affiliation_strings":["Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of EEE, University of Liverpool, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4013-2107","affiliations":[{"raw_affiliation_string":"Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of EEE, University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397","https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017442556","display_name":"Shanliang Yao","orcid":"https://orcid.org/0000-0001-7596-3598"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Shanliang Yao","raw_affiliation_strings":["Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of Engineering, University of Liverpool, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7596-3598","affiliations":[{"raw_affiliation_string":"Department of Computing, Xi'an Jiaotong-Liverpool University, China and \rSchool of Engineering, University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I69356397","https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059827048","display_name":"Xiaohui Zhu","orcid":"https://orcid.org/0000-0003-1024-5442"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhu","raw_affiliation_strings":["Department of Computing, Xi'an Jiaotong-Liverpool University, China"],"raw_orcid":"https://orcid.org/0000-0003-1024-5442","affiliations":[{"raw_affiliation_string":"Department of Computing, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003757015","display_name":"Jeremy S. Smith","orcid":"https://orcid.org/0000-0002-0212-2365"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeremy Smith","raw_affiliation_strings":["School of EEE, University of Liverpool, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0212-2365","affiliations":[{"raw_affiliation_string":"School of EEE, University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075116069","display_name":"Ka Lok Man","orcid":"https://orcid.org/0000-0002-5787-4716"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ka Lok Man","raw_affiliation_strings":["Department of Computing, Xi'an Jiaotong-Liverpool University, China"],"raw_orcid":"https://orcid.org/0000-0002-5787-4716","affiliations":[{"raw_affiliation_string":"Department of Computing, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052861384","display_name":"Yutao Yue","orcid":"https://orcid.org/0000-0003-4532-0924"},"institutions":[{"id":"https://openalex.org/I4210148486","display_name":"Jiangsu Industry Technology Research Institute","ror":"https://ror.org/044a9d018","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148486"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Yue","raw_affiliation_strings":["Institute of Deep Perception Technology, JITRI, China"],"raw_orcid":"https://orcid.org/0000-0003-4532-0924","affiliations":[{"raw_affiliation_string":"Institute of Deep Perception Technology, JITRI, China","institution_ids":["https://openalex.org/I4210148486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9775999784469604,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9760000109672546,"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/computer-science","display_name":"Computer science","score":0.7780029773712158},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.7545315027236938},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6392072439193726},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5773752927780151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5552718043327332},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5352201461791992},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.46784910559654236},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45842400193214417},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4454458951950073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40883052349090576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40276095271110535},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22860270738601685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09728127717971802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780029773712158},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.7545315027236938},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6392072439193726},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5773752927780151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552718043327332},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5352201461791992},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.46784910559654236},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45842400193214417},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4454458951950073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40883052349090576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40276095271110535},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22860270738601685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09728127717971802},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604078.3604108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604078.3604108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Digital Image Processing","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":13,"referenced_works":["https://openalex.org/W2521457681","https://openalex.org/W2613718673","https://openalex.org/W2787518933","https://openalex.org/W2932399282","https://openalex.org/W2963351448","https://openalex.org/W3035694605","https://openalex.org/W3081211609","https://openalex.org/W3138516171","https://openalex.org/W3184439416","https://openalex.org/W3192931333","https://openalex.org/W4289885562","https://openalex.org/W6658049321","https://openalex.org/W6795276571"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Vehicle":[0],"detection":[1,21,98,118,130,161,247,265],"based":[2],"on":[3,24,115],"deep":[4],"learning":[5],"has":[6,35,111],"been":[7,112],"developed":[8],"rapidly":[9],"and":[10,58,124,143,165,200,275],"basically":[11],"formed":[12],"a":[13,33,42,48,72,85,95,126,157,176,185,222,244],"certain":[14],"pattern.":[15],"Almost":[16],"all":[17],"works":[18],"in":[19,29,216],"vehicle":[20,34,86,97,107,117,129,147,246,264],"are":[22,66],"concentrated":[23],"single-label":[25],"object":[26,160],"detection.":[27],"However,":[28],"the":[30,39,105,137,146,149,212,253,260,279,282],"real":[31],"world,":[32],"multiple":[36,82,234],"attributes":[37],"from":[38],"perspective":[40],"of":[41,63,84,145,206,255,281],"human":[43],"being.":[44],"When":[45],"we":[46,50,122,155,183,220,240,284],"observe":[47],"car,":[49],"tend":[51],"to":[52,80,229],"perceive":[53],"its":[54,89],"type,":[55,141],"color,":[56],"orientation,":[57],"other":[59],"attributes.":[60],"The":[61],"categories":[62],"these":[64],"labels":[65,83,235],"neither":[67],"relevant":[68],"nor":[69],"hierarchical.":[70],"For":[71,92],"neural":[73],"network,":[74],"this":[75],"means":[76],"that":[77],"it":[78],"needs":[79],"output":[81],"while":[87],"regressing":[88],"bounding":[90,231],"box.":[91],"traffic":[93],"supervisors,":[94],"multi-label":[96,116,128,207,217,245,263],"system":[99],"could":[100],"help":[101],"them":[102],"find":[103],"out":[104],"targeted":[106],"efficiently.":[108],"Moreover,":[109],"there":[110],"no":[113],"research":[114],"so":[119],"far.":[120],"Therefore,":[121],"design":[123,156,184,221],"develop":[125],"unified":[127,262],"framework":[131,189],"called":[132,167,190,226,250],"ML-VehicleDet,":[133,153],"which":[134,172,193],"can":[135],"detect":[136],"location":[138],"(bounding":[139],"box),":[140],"color":[142],"orientation":[144],"at":[148,287],"same":[150],"time.":[151],"In":[152],"firstly,":[154],"hybrid":[158],"one-stage":[159],"NN":[162],"with":[163,233],"ViT-encoder":[164],"CNN-decoder":[166],"Swin":[168],"Only":[169],"Look":[170],"Once,":[171],"abbreviates":[173],"SOLO.":[174],"Such":[175],"SOLO":[177],"is":[178,259],"an":[179],"anchor-free":[180],"detector.":[181],"Secondly,":[182],"practical":[186],"loss":[187,196],"function":[188],"MLC":[191],"Loss,":[192],"includes":[194],"two":[195,203],"functions":[197],"namely":[198],"MLC-OM":[199],"MLC-OO":[201],"for":[202,210,236],"different":[204],"annotations":[205],"detection,":[208],"specialized":[209,228],"alleviating":[211],"mutual":[213],"inhibition":[214],"problem":[215],"classification.":[218],"Thirdly,":[219],"low-cost":[223],"NMS":[224],"algorithm":[225],"ML-NMS,":[227],"merge":[230],"boxes":[232],"one":[237],"vehicle.":[238],"Furthermore,":[239],"reconstruct":[241],"UA-DETRAC":[242],"as":[243],"dataset":[248],"(benchmark),":[249],"UA-DETRAC-ML.":[251],"To":[252,277],"best":[254],"our":[256],"knowledge,":[257],"UA-DETRAC-ML":[258,286],"first":[261],"dataset.":[266],"On":[267],"UA-DETRAC-ML,":[268],"ML-VehicleDet":[269],"achieves":[270],"70.23%":[271],"mAP,":[272],"outperforming":[273],"YOLOv5-M":[274],"YOLOX-M.":[276],"promote":[278],"development":[280],"community,":[283],"release":[285],"https://github.com/GuanRunwei/UA-DETRAC-ML.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}