{"id":"https://openalex.org/W2993465544","doi":"https://doi.org/10.1587/transinf.2019edp7045","title":"Attention-Guided Spatial Transformer Networks for Fine-Grained Visual Recognition","display_name":"Attention-Guided Spatial Transformer Networks for Fine-Grained Visual Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2993465544","doi":"https://doi.org/10.1587/transinf.2019edp7045","mag":"2993465544"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7045","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7045","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/12/E102.D_2019EDP7045/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/12/E102.D_2019EDP7045/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102851580","display_name":"Dichao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dichao LIU","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445359","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3008-8712"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu WANG","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080180020","display_name":"Jien Kato","orcid":"https://orcid.org/0000-0002-0196-4405"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jien KATO","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1985,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55213447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"E102.D","issue":"12","first_page":"2577","last_page":"2586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.8703795671463013},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6735400557518005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42712974548339844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35166868567466736},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1123792827129364},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05606579780578613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8703795671463013},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6735400557518005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42712974548339844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35166868567466736},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1123792827129364},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05606579780578613},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7045","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7045","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/12/E102.D_2019EDP7045/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7045","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7045","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/12/E102.D_2019EDP7045/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6287957481","display_name":"Tactile texture feature extraction based on visual texture analysis","funder_award_id":"20K20399","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2993465544.pdf","grobid_xml":"https://content.openalex.org/works/W2993465544.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1586730761","https://openalex.org/W1686810756","https://openalex.org/W1744759976","https://openalex.org/W1898560071","https://openalex.org/W1944615693","https://openalex.org/W1956526898","https://openalex.org/W1999192586","https://openalex.org/W2016053056","https://openalex.org/W2019660985","https://openalex.org/W2068611653","https://openalex.org/W2126574503","https://openalex.org/W2142194269","https://openalex.org/W2147238549","https://openalex.org/W2156303437","https://openalex.org/W2172806452","https://openalex.org/W2194775991","https://openalex.org/W2197033286","https://openalex.org/W2211996548","https://openalex.org/W2342662179","https://openalex.org/W2461621749","https://openalex.org/W2479109623","https://openalex.org/W2495387757","https://openalex.org/W2554320282","https://openalex.org/W2613635555","https://openalex.org/W2613763509","https://openalex.org/W2737725206","https://openalex.org/W2740620254","https://openalex.org/W2773003563","https://openalex.org/W2807931652","https://openalex.org/W2883888092","https://openalex.org/W2889469641","https://openalex.org/W2962858109","https://openalex.org/W2963066927","https://openalex.org/W2963246338","https://openalex.org/W2963446712","https://openalex.org/W2964308810","https://openalex.org/W2964350570"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,21,68,118,131],"this":[3,92],"paper":[4],"is":[5,75,84],"to":[6,77,97,108,123],"propose":[7,27],"effective":[8],"attentional":[9,46,101,110,119],"regions":[10,47],"for":[11,87],"fine-grained":[12],"visual":[13],"recognition.":[14],"Based":[15],"on":[16],"the":[17,31,41,58,63,69,78,104],"Spatial":[18,33,42],"Transformers'":[19],"capability":[20],"spatial":[22],"manipulation":[23],"within":[24],"networks,":[25],"we":[26,94],"an":[28],"extension":[29],"model,":[30,93],"Attention-Guided":[32],"Transformer":[34],"Networks":[35],"(AG-STNs).":[36],"This":[37],"model":[38,60],"can":[39,53],"guide":[40],"Transformers":[43],"with":[44],"hard-coded":[45],"at":[48],"first.":[49],"Then":[50],"such":[51],"guidance":[52],"be":[54],"turned":[55],"off,":[56],"and":[57,71,115],"network":[59],"will":[61],"adjust":[62],"region":[64],"learning":[65],"in":[66,112,126],"terms":[67],"location":[70],"scale.":[72],"Such":[73],"adjustment":[74],"conditioned":[76],"classification":[79],"loss":[80],"so":[81],"that":[82],"it":[83],"actually":[85],"optimized":[86],"better":[88,134],"recognition":[89],"results.":[90,135],"With":[91],"are":[95,106,121],"able":[96,107],"successfully":[98],"capture":[99,109],"detailed":[100],"information.":[102],"Also,":[103],"AG-STNs":[105],"information":[111,120],"multiple":[113],"levels,":[114],"different":[116],"levels":[117],"complementary":[122],"each":[124],"other":[125],"our":[127],"experiments.":[128],"A":[129],"fusion":[130],"them":[132],"brings":[133]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}