{"id":"https://openalex.org/W4403780575","doi":"https://doi.org/10.1145/3664647.3681212","title":"Uni-YOLO: Vision-Language Model-Guided YOLO for Robust and Fast Universal Detection in the Open World","display_name":"Uni-YOLO: Vision-Language Model-Guided YOLO for Robust and Fast Universal Detection in the Open World","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780575","doi":"https://doi.org/10.1145/3664647.3681212"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681212","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681212","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681212","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103204090","display_name":"Xudong Wang","orcid":"https://orcid.org/0009-0008-3278-0028"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xudong Wang","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences & University of the Chinese Academy of Sciences, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences & University of the Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072203497","display_name":"Weihong Ren","orcid":"https://orcid.org/0000-0003-3839-0078"},"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":"Weihong Ren","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023023880","display_name":"Xi\u2019ai Chen","orcid":"https://orcid.org/0000-0003-4756-3962"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi'ai Chen","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001938430","display_name":"Huijie Fan","orcid":"https://orcid.org/0000-0002-8548-861X"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijie Fan","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091319287","display_name":"Yandong Tang","orcid":"https://orcid.org/0000-0003-3805-7654"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yandong Tang","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001277681","display_name":"Zhi Han","orcid":"https://orcid.org/0000-0002-8039-6679"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Han","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103204090"],"corresponding_institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.7479,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73009932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1991","last_page":"2000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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":0.6600966453552246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333153605461121},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5072338581085205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600966453552246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333153605461121},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5072338581085205}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681212","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681212","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681212","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681212","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2109616376","https://openalex.org/W2331128040","https://openalex.org/W2779176852","https://openalex.org/W2789366140","https://openalex.org/W2963037989","https://openalex.org/W2963152299","https://openalex.org/W2963766909","https://openalex.org/W2963928582","https://openalex.org/W2983943451","https://openalex.org/W2997998901","https://openalex.org/W2998249728","https://openalex.org/W3034199269","https://openalex.org/W3095204565","https://openalex.org/W3096609285","https://openalex.org/W3173859428","https://openalex.org/W3177127346","https://openalex.org/W3194790201","https://openalex.org/W3203003533","https://openalex.org/W3213646008","https://openalex.org/W4226042837","https://openalex.org/W4288083516","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312956471","https://openalex.org/W4313892909","https://openalex.org/W4327808545","https://openalex.org/W4386065367","https://openalex.org/W4386066015","https://openalex.org/W4386066362","https://openalex.org/W4386076029","https://openalex.org/W4386076325","https://openalex.org/W4386076396","https://openalex.org/W4387475679","https://openalex.org/W4387967874","https://openalex.org/W4387967967","https://openalex.org/W4387968091","https://openalex.org/W4387968307","https://openalex.org/W4387968313","https://openalex.org/W4387969003","https://openalex.org/W4387969315","https://openalex.org/W4387969332","https://openalex.org/W4387969342","https://openalex.org/W4387969566","https://openalex.org/W4388188610","https://openalex.org/W4388820220","https://openalex.org/W4390871875","https://openalex.org/W4402716047"],"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":{"Universal":[0],"object":[1,7,21,57,62,118],"detectors":[2,22],"aim":[3],"to":[4,64,123,143,146,170],"detect":[5],"any":[6,9],"in":[8,26,84,126,155],"scene":[10],"without":[11],"human":[12],"annotation,":[13],"exhibiting":[14],"superior":[15],"generalization.":[16],"However,":[17],"the":[18,88,109,113],"current":[19],"universal":[20,44],"show":[23],"degraded":[24],"performance":[25],"harsh":[27,85],"weather,":[28],"and":[29,68,70,103,164,174],"their":[30,35],"insufficient":[31],"real-time":[32,51,78],"capabilities":[33],"limit":[34],"application.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"Uni-YOLO,":[42],"a":[43,55,72,96,156,165],"detector":[45,58],"designed":[46],"for":[47,77],"complex":[48],"scenes":[49],"with":[50,95,133],"performance.":[52],"Uni-YOLO":[53,91,105,145],"is":[54,92,106,121,141],"one-stage":[56],"that":[59],"uses":[60],"general":[61],"confidence":[63],"distinguish":[65],"between":[66],"objects":[67,151],"backgrounds,":[69],"employs":[71],"grid":[73],"cell":[74],"regression":[75],"method":[76,120,140],"detection.":[79],"To":[80],"improve":[81,124],"its":[82,172],"robustness":[83],"weather":[86],"conditions,":[87],"input":[89],"of":[90,112],"adaptively":[93],"enhanced":[94],"physical":[97],"model-based":[98],"enhancement":[99],"module.":[100],"During":[101],"training":[102,127],"inference,":[104],"guided":[107],"by":[108,128],"extensive":[110],"knowledge":[111],"vision-language":[114],"model":[115],"CLIP.":[116],"An":[117],"augmentation":[119],"proposed":[122,142],"generalization":[125],"utilizing":[129],"multiple":[130],"source":[131],"datasets":[132],"heterogeneous":[134],"annotations.":[135],"Furthermore,":[136],"an":[137],"online":[138],"self-enhancement":[139],"allow":[144],"further":[147],"focus":[148],"on":[149,161],"specific":[150],"through":[152],"self-supervised":[153],"fine-tuning":[154],"given":[157],"scene.":[158],"Extensive":[159],"experiments":[160],"public":[162],"benchmarks":[163],"UAV":[166],"deployment":[167],"are":[168],"conducted":[169],"validate":[171],"superiority":[173],"practical":[175],"value.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}