{"id":"https://openalex.org/W3176278386","doi":"https://doi.org/10.1109/tmm.2021.3090274","title":"Learning Scale-Consistent Attention Part Network for Fine-Grained Image Recognition","display_name":"Learning Scale-Consistent Attention Part Network for Fine-Grained Image Recognition","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3176278386","doi":"https://doi.org/10.1109/tmm.2021.3090274","mag":"3176278386"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3090274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3090274","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5090322671","display_name":"Huabin Liu","orcid":"https://orcid.org/0000-0001-9174-1696"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huabin Liu","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9174-1696","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368377","display_name":"Jianguo Li","orcid":"https://orcid.org/0000-0002-8645-0680"},"institutions":[{"id":"https://openalex.org/I4210090985","display_name":"Zhejiang Financial College","ror":"https://ror.org/00deghz86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210090985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Li","raw_affiliation_strings":["Ant Financial Services Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group, Beijing, China","institution_ids":["https://openalex.org/I4210090985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675450","display_name":"Dian Li","orcid":"https://orcid.org/0000-0002-7183-0090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Li","raw_affiliation_strings":["Tencent Technology (Beijing) Company, Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7183-0090","affiliations":[{"raw_affiliation_string":"Tencent Technology (Beijing) Company, Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076753547","display_name":"John See","orcid":"https://orcid.org/0000-0003-3005-4109"},"institutions":[{"id":"https://openalex.org/I4210085930","display_name":"Heriot-Watt University Malaysia","ror":"https://ror.org/0059w0420","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210085930"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"John See","raw_affiliation_strings":["School of Mathematical and Computing Sciences, Heriot-Watt University, Putrajaya, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computing Sciences, Heriot-Watt University, Putrajaya, Malaysia","institution_ids":["https://openalex.org/I4210085930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059372830","display_name":"Weiyao Lin","orcid":"https://orcid.org/0000-0001-8307-7107"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyao Lin","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8307-7107","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.015,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92868884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"2902","last_page":"2913"},"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":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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":0.8554412126541138},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8305118083953857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6013807058334351},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6010411977767944},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.571438729763031},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5537374019622803},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5299257636070251},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.48573094606399536},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4805658161640167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4581131339073181},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44475552439689636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42205047607421875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41063395142555237},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2405754029750824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554412126541138},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8305118083953857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6013807058334351},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6010411977767944},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.571438729763031},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5537374019622803},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5299257636070251},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.48573094606399536},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4805658161640167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4581131339073181},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44475552439689636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42205047607421875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41063395142555237},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2405754029750824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3090274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3090274","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G659896734","display_name":"\u9762\u5411\u65b0\u4e00\u4ee3\u76d1\u63a7\u89c6\u9891\u6570\u636e\u7684\u8bed\u4e49\u4fe1\u606f\u63d0\u53d6\u4e0e\u7f16\u7801\u7814\u7a76","funder_award_id":"61971277","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/F4320329139","display_name":"Communication University of China","ror":"https://ror.org/04facbs33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1496650988","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W2104657103","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2295107390","https://openalex.org/W2460852148","https://openalex.org/W2479423890","https://openalex.org/W2510373542","https://openalex.org/W2547875792","https://openalex.org/W2554320282","https://openalex.org/W2555741539","https://openalex.org/W2604134068","https://openalex.org/W2604195031","https://openalex.org/W2607855566","https://openalex.org/W2621368668","https://openalex.org/W2737725206","https://openalex.org/W2740620254","https://openalex.org/W2758150123","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2780418809","https://openalex.org/W2798365843","https://openalex.org/W2799215407","https://openalex.org/W2803686446","https://openalex.org/W2807931652","https://openalex.org/W2883502031","https://openalex.org/W2883888092","https://openalex.org/W2884751099","https://openalex.org/W2891951760","https://openalex.org/W2904391528","https://openalex.org/W2940925558","https://openalex.org/W2948519073","https://openalex.org/W2955058313","https://openalex.org/W2961018736","https://openalex.org/W2963090248","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2964080601","https://openalex.org/W2965328380","https://openalex.org/W2982220924","https://openalex.org/W2983446232","https://openalex.org/W2996173702","https://openalex.org/W3009073662","https://openalex.org/W3034676907","https://openalex.org/W3046509394","https://openalex.org/W3098019619","https://openalex.org/W3103844505","https://openalex.org/W3108870912","https://openalex.org/W3124951096","https://openalex.org/W4246193833","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6638677478","https://openalex.org/W6690026940","https://openalex.org/W6729448088","https://openalex.org/W6738893770","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2510961579"],"abstract_inverted_index":{"Discriminative":[0],"region":[1,81],"localization":[2],"and":[3,29,70,91,113,135,146,160],"feature":[4],"learning":[5],"are":[6],"crucial":[7],"for":[8],"fine-grained":[9,154],"visual":[10],"recognition.":[11],"Existing":[12],"approaches":[13],"solve":[14],"this":[15],"issue":[16],"by":[17],"attention":[18,28,62,66,94,106],"mechanism":[19,124],"or":[20],"part":[21,67,71,109],"based":[22,100,131],"methods":[23],"while":[24],"neglecting":[25],"consistency":[26],"between":[27],"local":[30],"parts,":[31],"as":[32,34],"well":[33],"the":[35,79,97,115,122,127],"rich":[36],"relation":[37,72],"information":[38],"among":[39,129],"parts.":[40],"This":[41],"paper":[42],"proposes":[43],"a":[44,83],"Scale-consistent":[45],"Attention":[46],"Part":[47],"Network":[48],"(SCAPNet)":[49],"to":[50,107,125],"address":[51],"that":[52],"issue,":[53],"which":[54],"seamlessly":[55],"integrates":[56],"three":[57],"novel":[58],"modules:":[59],"grid":[60,80],"gate":[61],"unit":[63],"(gGAU),":[64],"scale-consistent":[65],"selection":[68,110,116],"(SCAPS),":[69],"modeling":[73],"(PRM).":[74],"The":[75,102,118],"gGAU":[76],"module":[77,104,120],"represents":[78],"at":[82],"certain":[84],"fine-scale":[85],"with":[86,96],"middle":[87],"layer":[88],"CNN":[89],"features":[90],"produces":[92],"hard":[93],"maps":[95],"lightweight":[98],"Gumbel-Max":[99],"gate.":[101],"SCAPS":[103],"utilizes":[105,121],"guide":[108],"across":[111],"multi-scales":[112],"keep":[114],"scale-consistent.":[117],"PRM":[119],"self-attention":[123],"build":[126],"relationship":[128],"parts":[130],"on":[132,150],"their":[133],"appearance":[134],"relative":[136],"geo-positions.":[137],"SCAPNet":[138],"can":[139],"be":[140],"learned":[141],"in":[142],"an":[143],"end-to-end":[144],"way":[145],"demonstrates":[147],"state-of-the-art":[148],"accuracy":[149],"several":[151],"publicly":[152],"available":[153],"recognition":[155],"datasets":[156],"(CUB-200-2011,":[157],"FGVC-Aircraft,":[158],"Veg200,":[159],"Fru92).":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}