{"id":"https://openalex.org/W2951464224","doi":"https://doi.org/10.1109/tip.2019.2921876","title":"Learning Rich Part Hierarchies With Progressive Attention Networks for Fine-Grained Image Recognition","display_name":"Learning Rich Part Hierarchies With Progressive Attention Networks for Fine-Grained Image Recognition","publication_year":2019,"publication_date":"2019-06-14","ids":{"openalex":"https://openalex.org/W2951464224","doi":"https://doi.org/10.1109/tip.2019.2921876","mag":"2951464224","pmid":"https://pubmed.ncbi.nlm.nih.gov/31217107"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2019.2921876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2921876","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102507347","display_name":"Heliang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heliang Zheng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1025-2012","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2510-8993","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["AI Research, JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-7732","affiliations":[{"raw_affiliation_string":"AI Research, JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5582,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.96747082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"476","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8443106412887573},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7871226072311401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497321367263794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7269826531410217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6952444314956665},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6134548187255859},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5438433885574341},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5266547203063965},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42739999294281006},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4044477343559265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35507529973983765}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8443106412887573},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7871226072311401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497321367263794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7269826531410217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6952444314956665},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6134548187255859},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5438433885574341},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5266547203063965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4044477343559265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35507529973983765},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2019.2921876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2921876","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:31217107","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31217107","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2988286480","display_name":null,"funder_award_id":"2017YFB1300201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4530701113","display_name":null,"funder_award_id":"WK2100100030","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5276383603","display_name":null,"funder_award_id":"61622211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6197875348","display_name":null,"funder_award_id":"61620106009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W603908379","https://openalex.org/W1496650988","https://openalex.org/W1524680991","https://openalex.org/W1536680647","https://openalex.org/W1616462885","https://openalex.org/W1686810756","https://openalex.org/W1846799578","https://openalex.org/W1898560071","https://openalex.org/W1903029394","https://openalex.org/W1909952827","https://openalex.org/W1928906481","https://openalex.org/W1955942245","https://openalex.org/W1967632700","https://openalex.org/W1993309459","https://openalex.org/W2039507552","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2117539524","https://openalex.org/W2138011018","https://openalex.org/W2143238378","https://openalex.org/W2150856297","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2202499615","https://openalex.org/W2207849498","https://openalex.org/W2235526797","https://openalex.org/W2287418003","https://openalex.org/W2295107390","https://openalex.org/W2462457117","https://openalex.org/W2479109623","https://openalex.org/W2512434173","https://openalex.org/W2554320282","https://openalex.org/W2556967412","https://openalex.org/W2601789736","https://openalex.org/W2604702198","https://openalex.org/W2737725206","https://openalex.org/W2740620254","https://openalex.org/W2741910023","https://openalex.org/W2758150123","https://openalex.org/W2763070548","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2780838211","https://openalex.org/W2808269424","https://openalex.org/W2949846184","https://openalex.org/W2962761264","https://openalex.org/W2962835968","https://openalex.org/W2963066927","https://openalex.org/W2963321359","https://openalex.org/W2963954913","https://openalex.org/W2964036919","https://openalex.org/W2964275061","https://openalex.org/W2964350570","https://openalex.org/W3103844505","https://openalex.org/W3124951096","https://openalex.org/W4285719527","https://openalex.org/W6600609147","https://openalex.org/W6618372016","https://openalex.org/W6636475194","https://openalex.org/W6637373629","https://openalex.org/W6638677478","https://openalex.org/W6640376812","https://openalex.org/W6684191040","https://openalex.org/W6687751829","https://openalex.org/W6729983426","https://openalex.org/W6736321067","https://openalex.org/W6790300624"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,15,87,96,118,132],"localization":[3],"of":[4,95,114],"subtle":[5],"yet":[6],"discriminative":[7],"parts":[8,19,51,58,166],"for":[9,121],"fine-grained":[10,115,185],"image":[11],"recognition.":[12],"Based":[13],"on":[14],"observation":[16],"that":[17,161,177],"such":[18],"typically":[20],"exist":[21],"within":[22],"a":[23,28,32,41,63,74,106,122,125,135,139,148,155],"hierarchical":[24],"structure":[25],"(e.g.,":[26,143],"from":[27,82,131],"coarse-scale":[29],"\"head\"":[30],"to":[31,48,102,111,151],"fine-scale":[33],"\"eye\"":[34],"when":[35],"recognizing":[36],"bird":[37],"species),":[38],"we":[39],"propose":[40],"novel":[42],"progressive-attention":[43],"convolutional":[44,119],"neural":[45],"network":[46,66,77],"(PA-CNN)":[47],"progressively":[49],"localize":[50],"at":[52,124,134],"multiple":[53,69],"scales.":[54],"The":[55],"PA-CNN":[56,162,178],"localizes":[57],"in":[59,105,147,154,182],"two":[60],"steps,":[61],"where":[62],"part":[64,75,91,141],"proposal":[65,84],"(PPN)":[67],"generates":[68],"local":[70],"attention":[71],"maps,":[72],"and":[73,85,98,145,191],"rectification":[76],"(PRN)":[78],"learns":[79],"part-specific":[80],"features":[81],"each":[83],"provides":[86],"PPN":[88,97,123],"with":[89],"refined":[90],"locations.":[92],"This":[93],"coupling":[94],"PRN":[99,133],"allows":[100],"them":[101],"be":[103,129,152],"optimized":[104],"mutually":[107],"reinforcing":[108],"manner,":[109],"leading":[110],"improved":[112],"pinpointing":[113],"parts.":[116],"Moreover,":[117],"parameters":[120],"finer":[126],"scale":[127],"can":[128,163],"inherited":[130],"coarser":[136],"scale,":[137],"enabling":[138],"rich":[140],"hierarchy":[142],"eye":[144],"beak":[146],"bird's":[149],"head)":[150],"learned":[153],"stacked":[156],"fashion.":[157],"Case":[158],"studies":[159],"show":[160],"precisely":[164],"identify":[165],"without":[167],"using":[168],"bounding":[169],"box/part":[170],"annotations.":[171],"In":[172],"addition,":[173],"quantitative":[174],"evaluations":[175],"demonstrate":[176],"yields":[179],"state-of-the-art":[180],"performance":[181],"three":[183],"challenging":[184],"recognition":[186],"tasks.":[187],"i.e.,":[188],"CUB-200-2011,":[189],"FGVC-Aircraft,":[190],"Stanford":[192],"Cars.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}