{"id":"https://openalex.org/W2462457117","doi":"https://doi.org/10.1109/cvpr.2016.129","title":"SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition","display_name":"SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2462457117","doi":"https://doi.org/10.1109/cvpr.2016.129","mag":"2462457117"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2016.129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2016.129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100399257","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0001-7072-2189"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Han Zhang","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621909","display_name":"Tao Xu","orcid":"https://orcid.org/0000-0003-3705-4152"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, Lehigh University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101980904","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0002-6647-6787"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000467703","display_name":"Xiaolei Huang","orcid":"https://orcid.org/0000-0003-2338-6535"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolei Huang","raw_affiliation_strings":["Department of Computer Science and Engineering, Lehigh University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066553616","display_name":"Shaoting Zhang","orcid":"https://orcid.org/0000-0002-8719-448X"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoting Zhang","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Charlotte"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Charlotte","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039640321","display_name":"Ahmed Elgammal","orcid":"https://orcid.org/0000-0003-2761-4822"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ahmed Elgammal","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109600054","display_name":"Dimitris Metaxas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dimitris Metaxas","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100399257"],"corresponding_institution_ids":["https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":21.0426,"has_fulltext":false,"cited_by_count":304,"citation_normalized_percentile":{"value":0.99551916,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1143","last_page":"1152"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.998199999332428,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9980000257492065,"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":0.8800156712532043},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7483203411102295},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7048662900924683},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6527422070503235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316213607788086},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6160393357276917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6104933619499207},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4994471073150635},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48172619938850403},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4497959613800049},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4347696900367737},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42568543553352356},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.415221631526947},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27683889865875244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23918601870536804},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11159619688987732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8800156712532043},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7483203411102295},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7048662900924683},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6527422070503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316213607788086},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6160393357276917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6104933619499207},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4994471073150635},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48172619938850403},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4497959613800049},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4347696900367737},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42568543553352356},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.415221631526947},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27683889865875244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23918601870536804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11159619688987732},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2016.129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2016.129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W56385144","https://openalex.org/W166750225","https://openalex.org/W196211074","https://openalex.org/W326271615","https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1489081407","https://openalex.org/W1496650988","https://openalex.org/W1536680647","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1849277567","https://openalex.org/W1898560071","https://openalex.org/W1923115158","https://openalex.org/W1928906481","https://openalex.org/W1948751323","https://openalex.org/W1955942245","https://openalex.org/W1984514441","https://openalex.org/W1991367009","https://openalex.org/W1995543189","https://openalex.org/W2005286252","https://openalex.org/W2046382188","https://openalex.org/W2049750909","https://openalex.org/W2079789819","https://openalex.org/W2088049833","https://openalex.org/W2091759811","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2109255472","https://openalex.org/W2110765924","https://openalex.org/W2118696714","https://openalex.org/W2135706578","https://openalex.org/W2138011018","https://openalex.org/W2145287260","https://openalex.org/W2155839910","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2168356304","https://openalex.org/W2535410496","https://openalex.org/W2613718673","https://openalex.org/W2950094539","https://openalex.org/W2963542991","https://openalex.org/W4285719527","https://openalex.org/W6600313631","https://openalex.org/W6600609147","https://openalex.org/W6602324145","https://openalex.org/W6606767076","https://openalex.org/W6607973782","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6629368666","https://openalex.org/W6638319203","https://openalex.org/W6638677478","https://openalex.org/W6639204139","https://openalex.org/W6640376812","https://openalex.org/W6646201289","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2045155990","https://openalex.org/W2979236518","https://openalex.org/W4387272257","https://openalex.org/W4200301313"],"abstract_inverted_index":{"Most":[0],"convolutional":[1,163],"neural":[2],"networks":[3],"(CNNs)":[4],"lack":[5],"midlevel":[6],"layers":[7,35,117],"that":[8,70,118,143,158],"model":[9],"semantic":[10,28,72,106,149],"parts":[11,29,122,176],"of":[12,40,58,147,162,181,188],"objects.":[13],"This":[14,51],"limits":[15],"CNN-based":[16],"methods":[17,169],"from":[18,121],"reaching":[19],"their":[20],"full":[21],"potential":[22],"in":[23,30,55],"detecting":[24,191],"and":[25,75,90,128,151],"utilizing":[26],"small":[27,105,175],"recognition.":[31,60,93,132],"Introducing":[32],"such":[33],"mid-level":[34],"can":[36,44],"facilitate":[37],"the":[38,56,125,136,160,184,192,201],"extraction":[39],"part-specific":[41],"features":[42,120],"which":[43],"be":[45],"utilized":[46],"for":[47,78,88,92,109,131,174,190],"better":[48],"recognition":[49,154],"performance.":[50],"is":[52],"particularly":[53],"important":[54],"domain":[57],"fine-grained":[59,79],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"a":[66,98,134,171],"new":[67],"CNN":[68],"architecture":[69,138],"integrates":[71],"part":[73,107,116],"detection":[74,89,95,126,177],"abstraction":[76],"(SPDACNN)":[77],"classification.":[80],"The":[81,94,111],"proposed":[82,137],"network":[83,142],"has":[84,97],"two":[85],"sub-networks:":[86],"one":[87,91,156],"sub-network":[96,113],"novel":[99,115],"top-down":[100],"proposal":[101],"method":[102,166],"to":[103,200],"generate":[104],"candidates":[108],"detection.":[110],"classification":[112],"introduces":[114],"extract":[119],"detected":[123],"by":[124],"sub-network,":[127],"combine":[129],"them":[130],"As":[133],"result,":[135],"provides":[139],"an":[140],"end-to-end":[141],"performs":[144],"detection,":[145],"localization":[146],"multiple":[148],"parts,":[150],"whole":[152],"object":[153],"within":[155],"framework":[157],"shares":[159],"computation":[161],"filters.":[164],"Our":[165],"outperforms":[167],"state-of-theart":[168],"with":[170],"large":[172],"margin":[173],"(e.g.":[178],"our":[179],"precision":[180,187],"93.40%":[182],"vs":[183],"best":[185],"previous":[186],"74.00%":[189],"head":[193],"on":[194,204,212],"CUB-2011).":[195],"It":[196],"also":[197],"compares":[198],"favorably":[199],"existing":[202],"state-of-the-art":[203],"finegrained":[205],"classification,":[206],"e.g.":[207],"it":[208],"achieves":[209],"85.14%":[210],"accuracy":[211],"CUB-2011.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":39},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":57},{"year":2018,"cited_by_count":39},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}