{"id":"https://openalex.org/W4387974934","doi":"https://doi.org/10.1007/s13042-023-01996-2","title":"IntelPVT: intelligent patch-based pyramid vision transformers for object detection and classification","display_name":"IntelPVT: intelligent patch-based pyramid vision transformers for object detection and classification","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387974934","doi":"https://doi.org/10.1007/s13042-023-01996-2"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-023-01996-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01996-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01996-2.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","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/s13042-023-01996-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093131880","display_name":"Divya Nimma","orcid":"https://orcid.org/0009-0005-1525-2395"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divya Nimma","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, 118 College Dr., Hattiesburg, MS, 39406, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, 118 College Dr., Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001575594","display_name":"Zhaoxian Zhou","orcid":"https://orcid.org/0000-0001-6789-166X"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaoxian Zhou","raw_affiliation_strings":["School of Computing Sciences and Computer Engineering, University of Southern Mississippi, 118 College Dr., Hattiesburg, MS, 39406, USA"],"raw_orcid":"https://orcid.org/0000-0001-6789-166X","affiliations":[{"raw_affiliation_string":"School of Computing Sciences and Computer Engineering, University of Southern Mississippi, 118 College Dr., Hattiesburg, MS, 39406, USA","institution_ids":["https://openalex.org/I44854399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001575594"],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":{"value":3990,"currency":"USD","value_usd":3990},"apc_paid":{"value":3990,"currency":"USD","value_usd":3990},"fwci":0.9498,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73965647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"15","issue":"5","first_page":"1767","last_page":"1778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.996999979019165,"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":0.7857100963592529},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7596458196640015},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.7460222244262695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7245904207229614},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5884768962860107},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5681067109107971},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.4418858587741852},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38032978773117065},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.15079501271247864},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08112436532974243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857100963592529},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7596458196640015},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7460222244262695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7245904207229614},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5884768962860107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5681067109107971},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.4418858587741852},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38032978773117065},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.15079501271247864},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08112436532974243},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-023-01996-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01996-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01996-2.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s13042-023-01996-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13042-023-01996-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13042-023-01996-2.pdf","source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387974934.pdf","grobid_xml":"https://content.openalex.org/works/W4387974934.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2037227137","https://openalex.org/W2192176479","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2355370852","https://openalex.org/W2601564443","https://openalex.org/W2737725206","https://openalex.org/W2752782242","https://openalex.org/W3007663754","https://openalex.org/W3096609285","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3137278571","https://openalex.org/W3138516171","https://openalex.org/W3145185940","https://openalex.org/W3146497429","https://openalex.org/W3172509117","https://openalex.org/W3176659256","https://openalex.org/W3203974803","https://openalex.org/W4214893857"],"related_works":["https://openalex.org/W3177249605","https://openalex.org/W4376620596","https://openalex.org/W2534152068","https://openalex.org/W4299545679","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W2549121492","https://openalex.org/W3138508047","https://openalex.org/W2953362004"],"abstract_inverted_index":{"Abstract":[0],"Since":[1],"the":[2,19,51,60,74,83,103],"advent":[3],"of":[4,21,30,47,53,85],"Transformers":[5,9],"followed":[6],"by":[7,16],"Vision":[8],"(ViTs),":[10],"enormous":[11],"success":[12],"has":[13],"been":[14],"achieved":[15],"researchers":[17],"in":[18,40,45,120,142,146,155],"field":[20],"computer":[22],"vision":[23],"and":[24,43,56,69,92,100,129,134,158],"object":[25,54,132,156],"detection.":[26],"The":[27,79,136],"difficulty":[28],"mechanism":[29,68],"splitting":[31],"images":[32,99],"into":[33,73],"fixed":[34],"patches":[35,86],"posed":[36],"a":[37,152],"serious":[38],"challenge":[39],"this":[41],"arena":[42],"resulted":[44],"loss":[46],"useful":[48],"information":[49],"at":[50],"time":[52],"detection":[55,133,157],"classification.":[57,135],"To":[58],"overcome":[59],"challengers,":[61],"we":[62],"propose":[63],"an":[64],"innovative":[65],"Intelligent-based":[66],"patching":[67],"integrated":[70],"it":[71,151],"seamlessly":[72],"conventional":[75,107],"Patch-based":[76],"ViT":[77],"framework.":[78],"proposed":[80],"method":[81,110],"enables":[82],"utilization":[84],"with":[87,106,113],"flexible":[88],"sizes":[89],"to":[90],"capture":[91],"retain":[93],"essential":[94],"semantic":[95],"content":[96],"from":[97],"input":[98],"therefore":[101],"increases":[102],"performance":[104],"compared":[105],"methods.":[108],"Our":[109],"was":[111],"evaluated":[112],"three":[114],"renowned":[115],"datasets":[116],"Microsoft":[117],"Common":[118],"Objects":[119],"Context":[121],"(MSCOCO-2017),":[122],"Pascal":[123],"VOC":[124],"(Visual":[125],"Object":[126],"Classes":[127],"Challenge)":[128],"Cityscapes":[130],"upon":[131],"experimental":[137],"results":[138],"showed":[139],"promising":[140],"improvements":[141],"specific":[143],"metrics,":[144],"particularly":[145],"higher":[147],"confidence":[148],"thresholds,":[149],"making":[150],"notable":[153],"performer":[154],"classification":[159],"tasks.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}