{"id":"https://openalex.org/W4405429587","doi":"https://doi.org/10.1109/tits.2024.3510117","title":"Zone-YOLO: Vision-Language Object Detection Using Zone Prompt","display_name":"Zone-YOLO: Vision-Language Object Detection Using Zone Prompt","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405429587","doi":"https://doi.org/10.1109/tits.2024.3510117"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3510117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3510117","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/A5026565856","display_name":"Jiaxiong Yang","orcid":"https://orcid.org/0000-0002-7499-2474"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiong Yang","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7499-2474","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709263","display_name":"Ning Jia","orcid":"https://orcid.org/0000-0002-2395-3432"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Jia","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2395-3432","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101422861","display_name":"Xianhui Liu","orcid":"https://orcid.org/0000-0002-5088-3628"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhui Liu","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5088-3628","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Fan","orcid":"https://orcid.org/0000-0003-2593-6596"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Fan","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2593-6596","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690148","display_name":"Yougang Sun","orcid":"https://orcid.org/0000-0002-1549-0108"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yougang Sun","raw_affiliation_strings":["Institute of Rail Transit and the National Maglev Transportation Engineering Research and Development Center, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1549-0108","affiliations":[{"raw_affiliation_string":"Institute of Rail Transit and the National Maglev Transportation Engineering Research and Development Center, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428767","display_name":"Weidong Zhao","orcid":"https://orcid.org/0000-0003-4164-5190"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhao","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.6312,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6691508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"26","issue":"10","first_page":"17510","last_page":"17521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9768000245094299,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9768000245094299,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9711999893188477,"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-vision","display_name":"Computer vision","score":0.6631921529769897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916283130645752},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5709671378135681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5630745887756348},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47344303131103516},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3315697908401489},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.2974005937576294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1718902587890625}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6631921529769897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916283130645752},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5709671378135681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630745887756348},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47344303131103516},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3315697908401489},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.2974005937576294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1718902587890625}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3510117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3510117","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/G1680655759","display_name":null,"funder_award_id":"62403361","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2752782242","https://openalex.org/W2948672349","https://openalex.org/W3035564946","https://openalex.org/W3164576087","https://openalex.org/W3173859428","https://openalex.org/W3198377975","https://openalex.org/W3208645658","https://openalex.org/W4220827132","https://openalex.org/W4289752563","https://openalex.org/W4297676427","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312956471","https://openalex.org/W4377711491","https://openalex.org/W4381733084","https://openalex.org/W4382464354","https://openalex.org/W4385245566","https://openalex.org/W4385338579","https://openalex.org/W4385567175","https://openalex.org/W4386038329","https://openalex.org/W4386065353","https://openalex.org/W4386065936","https://openalex.org/W4386071547","https://openalex.org/W4386113259","https://openalex.org/W4387855642","https://openalex.org/W4387969322","https://openalex.org/W4391097115","https://openalex.org/W4392172801","https://openalex.org/W4393972732","https://openalex.org/W4399152888","https://openalex.org/W4400226311","https://openalex.org/W4402716047","https://openalex.org/W4402716252","https://openalex.org/W4402727669","https://openalex.org/W4403770406"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Object":[0,34],"detection":[1,19],"in":[2,45,58],"complex":[3],"traffic":[4,17,221],"scenarios":[5],"is":[6,92],"crucial":[7],"for":[8,30,71],"Intelligent":[9],"Transportation":[10],"Systems":[11],"(ITS).":[12],"At":[13],"present,":[14],"most":[15],"real-time":[16],"object":[18,72,222],"methods":[20,54,191],"primarily":[21],"rely":[22],"on":[23,67,204,209,219],"YOLO-style":[24],"vision-only":[25],"detectors,":[26],"limiting":[27],"their":[28,65],"potential":[29],"further":[31,213],"improvement.":[32],"Vision-Language":[33],"Detection":[35],"(VLOD)":[36],"has":[37],"made":[38],"promising":[39],"progress":[40],"currently,":[41],"yet":[42],"its":[43],"adoption":[44],"the":[46,59,68,95,99,107,115,131,140,170,177,181,189,215],"realm":[47],"of":[48,98,180,217],"ITS":[49],"remains":[50],"limited.":[51],"Previous":[52],"VLOD":[53,116],"utilize":[55],"text":[56,82,132,163],"features":[57,83,87,135,164],"classification":[60],"task,":[61],"without":[62],"fully":[63,129],"exploring":[64],"impact":[66],"regression":[69,166],"process":[70,167],"localization.":[73],"Besides,":[74],"existing":[75],"multi-modal":[76,141],"fusion":[77],"approaches":[78],"fail":[79],"to":[80,94,113,117,128,138,161],"fuse":[81,139],"with":[84,147],"multi-scale":[85],"image":[86,134],"at":[88,144],"corresponding":[89],"scales,":[90],"which":[91,174],"detrimental":[93],"representation":[96],"capability":[97],"model.":[100,182],"In":[101],"this":[102],"work,":[103],"we":[104,122,153],"dive":[105],"into":[106,165],"limitations":[108],"above":[109],"and":[110,133,136,149,168,201,211],"introduce":[111,162],"Zone-YOLO":[112,187,218],"improve":[114],"a":[118,155,193],"new":[119],"level.":[120],"Specifically,":[121],"propose":[123],"Scale-Aware":[124],"Modal":[125],"Fusion":[126],"(SAMF)":[127],"exploit":[130],"learn":[137],"representations":[142],"seamlessly":[143],"different":[145],"scales":[146],"channel-":[148],"modal-wise":[150],"enhancement.":[151],"Moreover,":[152],"present":[154],"novel":[156],"Zone":[157],"Prompt":[158],"learning":[159],"method":[160],"capture":[169],"zone-class-entity":[171],"triple":[172],"co-occurrence,":[173],"significantly":[175],"improves":[176],"localization":[178],"performance":[179],"Extensive":[183],"experiments":[184],"show":[185],"that":[186],"outperforms":[188],"comparative":[190],"by":[192],"considerable":[194],"margin,":[195],"achieving":[196],"55.1":[197],"AP,":[198],"72.1":[199],"AP50":[200],"71.2":[202],"APL":[203],"COCO.":[205],"The":[206],"competitive":[207],"results":[208],"BDD100K":[210],"VisDrone2019":[212],"demonstrate":[214],"superiority":[216],"efficient":[220],"detection.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}