{"id":"https://openalex.org/W4416252330","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227349","title":"LOVD: Open-Vocabulary Object Detection Based on LLM-Enhanced Agents","display_name":"LOVD: Open-Vocabulary Object Detection Based on LLM-Enhanced Agents","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252330","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227349"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100611711","display_name":"Xinhao Li","orcid":"https://orcid.org/0000-0002-0664-7775"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinhao Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016973102","display_name":"Jungang Xu","orcid":"https://orcid.org/0000-0002-3994-1401"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jungang Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100611711"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37601822,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5654000043869019,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5654000043869019,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.33820000290870667,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.033399999141693115,"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/object-detection","display_name":"Object detection","score":0.7766000032424927},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7055000066757202},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.621999979019165},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6047999858856201},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5647000074386597},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.5430999994277954},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818999886512756},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7766000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7330999970436096},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.5430999994277954},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5364999771118164},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.39089998602867126},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C512554520","wikidata":"https://www.wikidata.org/wiki/Q815844","display_name":"Method","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2948672349","https://openalex.org/W2952122856","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963857746","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W3035396860","https://openalex.org/W3042011474","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3167976421","https://openalex.org/W3173859428","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312956471","https://openalex.org/W4385245566","https://openalex.org/W4386076325","https://openalex.org/W4396918822","https://openalex.org/W4402716047","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,11,21,32,39,74],"detection":[2,22],"has":[3],"emerged":[4],"as":[5],"a":[6,28,71,84,89,97,102],"prominent":[7],"trend":[8],"in":[9,142],"modern":[10],"detection,":[12],"aiming":[13],"to":[14,44,115],"identify":[15],"objects":[16],"beyond":[17],"predefined":[18],"categories.":[19],"Early":[20],"methods":[23,54,141],"typically":[24],"trained":[25],"detectors":[26],"on":[27,37,57,127],"set":[29],"of":[30,49,135,144],"basic":[31],"categories":[33],"and":[34,88,101,121,146],"evaluated":[35],"them":[36,61],"novel":[38],"categories,":[40],"or":[41],"required":[42],"users":[43],"input":[45],"the":[46,50,113,128,133],"category":[47],"label":[48],"object.":[51],"However,":[52],"these":[53],"heavily":[55],"rely":[56],"prior":[58],"knowledge,":[59],"making":[60],"unsuitable":[62],"for":[63,78,106],"real-world":[64],"scenarios.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"LLM-enhanced":[72],"Open-Vocabulary":[73],"Detection":[75],"framework":[76],"(LOVD)":[77],"practical":[79],"applications.":[80],"Our":[81],"method":[82],"incorporates":[83],"text":[85],"generation":[86],"agent":[87],"visual-semantic":[90],"feature":[91,109],"alignment":[92],"agent,":[93],"both":[94,117],"enhanced":[95],"by":[96],"large":[98],"language":[99],"model,":[100],"lightweight":[103],"YOLO":[104],"backbone":[105],"efficient":[107],"image":[108],"extraction,":[110],"which":[111],"enables":[112],"model":[114],"achieve":[116],"high":[118],"inference":[119],"efficiency":[120],"strong":[122],"generalization":[123],"capabilities.":[124],"Experimental":[125],"results":[126],"challenging":[129],"LVIS":[130],"dataset":[131],"demonstrate":[132],"effectiveness":[134],"our":[136],"method,":[137],"outperforming":[138],"many":[139],"advanced":[140],"terms":[143],"accuracy":[145],"speed.":[147]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}