{"id":"https://openalex.org/W4412872775","doi":"https://doi.org/10.1007/s10489-025-06651-7","title":"Open-vocabulary object detection with regionwise prompt selection and patch-based category-aware maximal activation","display_name":"Open-vocabulary object detection with regionwise prompt selection and patch-based category-aware maximal activation","publication_year":2025,"publication_date":"2025-07-19","ids":{"openalex":"https://openalex.org/W4412872775","doi":"https://doi.org/10.1007/s10489-025-06651-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-025-06651-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-06651-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-06651-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-06651-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109675739","display_name":"Zhaocheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zhaocheng Xu","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022594144","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0003-2899-9816"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]},{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["CN","NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, Ningbo, China","School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004880009","display_name":"Yan Tian","orcid":"https://orcid.org/0000-0003-0596-1209"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Tian","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008188376","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0002-5096-1171"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Information Security Department, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Information Security Department, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004880009"],"corresponding_institution_ids":["https://openalex.org/I75059550"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18125612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9977999925613403,"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":0.9076869487762451},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6420034170150757},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5462399125099182},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.487043172121048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3994961082935333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38431084156036377},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10682931542396545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9076869487762451},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6420034170150757},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5462399125099182},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.487043172121048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3994961082935333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38431084156036377},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10682931542396545},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-025-06651-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-06651-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-06651-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10489-025-06651-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-06651-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-06651-7.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320816","display_name":"Massey University","ror":"https://ror.org/052czxv31"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412872775.pdf","grobid_xml":"https://content.openalex.org/works/W4412872775.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2771653066","https://openalex.org/W2909973745","https://openalex.org/W2948672349","https://openalex.org/W3173859428","https://openalex.org/W3198377975","https://openalex.org/W4220953242","https://openalex.org/W4225949809","https://openalex.org/W4229031440","https://openalex.org/W4281627925","https://openalex.org/W4286498600","https://openalex.org/W4307573784","https://openalex.org/W4309635395","https://openalex.org/W4310557340","https://openalex.org/W4312310776","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312651322","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4386066010","https://openalex.org/W4386071614","https://openalex.org/W4386071855","https://openalex.org/W4386072314","https://openalex.org/W4386075758","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4386091161","https://openalex.org/W4386790226","https://openalex.org/W4388081422","https://openalex.org/W4388233659","https://openalex.org/W4389332059","https://openalex.org/W4390236059","https://openalex.org/W4390872318","https://openalex.org/W4391451889","https://openalex.org/W4394601625","https://openalex.org/W4402660130","https://openalex.org/W4402727672","https://openalex.org/W4402903420","https://openalex.org/W4403346627","https://openalex.org/W4403943254","https://openalex.org/W4405034605","https://openalex.org/W4405175300","https://openalex.org/W4410907222","https://openalex.org/W6600548291","https://openalex.org/W6600612351","https://openalex.org/W6602474744","https://openalex.org/W6604783342"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Object":[1],"detectors":[2],"perform":[3],"unseen":[4,44],"class":[5],"detection":[6,74],"by":[7,67],"fine-tuning":[8],"frozen":[9],"visual-language":[10],"models":[11],"with":[12,91,117,143],"visual":[13,22,37,81,93,115],"prompts":[14,94],"and":[15,62,140,160],"natural":[16],"language":[17],"supervision.":[18],"However,":[19],"the":[20,41,58,63,68,112,120,127,132],"current":[21],"prompt":[23,82],"tuning":[24],"methods":[25],"struggle":[26],"to":[27,40,47,55,86,110,119],"learn":[28],"categorywise":[29],"shared":[30],"knowledge":[31],"when":[32],"using":[33],"only":[34],"one":[35],"single":[36],"prompt,":[38],"due":[39],"inaccessibility":[42],"of":[43],"classes":[45,50,61,159],"referred":[46],"as":[48],"novel":[49,60,158],"during":[51],"training.":[52],"This":[53],"leads":[54],"isolation":[56],"between":[57],"unknown":[59],"base":[64],"classes.":[65],"Inspired":[66],"recently":[69],"developed":[70],"RPN-based":[71],"open-vocabulary":[72,137],"object":[73],"(OVOD)":[75],"methods,":[76],"we":[77,101],"propose":[78],"a":[79,103,150,161],"region-aware":[80],"selection":[83],"(RVPS)":[84],"module":[85,109],"adaptively":[87],"combine":[88],"region":[89],"features":[90],"best-matched":[92],"based":[95],"on":[96,135,155,166],"decoupled":[97],"proxy":[98],"embeddings.":[99],"Additionally,":[100],"introduce":[102],"category-aware":[104],"patchwise":[105],"maximal":[106],"aggregation":[107],"(CPMA)":[108],"explore":[111],"relationships":[113],"among":[114],"patches":[116,124],"respect":[118],"category-specific":[121],"maximum":[122],"activation":[123],"contained":[125],"within":[126],"target":[128],"region.":[129],"We":[130],"evaluate":[131],"proposed":[133],"approach":[134],"an":[136],"benchmarks:":[138],"COCO":[139,156],"LVIS.":[141],"Compared":[142],"other":[144],"state-of-the-art":[145],"approaches,":[146],"our":[147],"method":[148],"achieves":[149],"1.2%":[151],"AP":[152,164],"$$_{50}$$":[153],"improvement":[154,165],"for":[157,168],"0.5%":[162],"mask":[163],"LVIS":[167],"rare":[169],"categories.":[170]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-10-10T00:00:00"}