{"id":"https://openalex.org/W2608734801","doi":"https://doi.org/10.1109/icpr.2016.7900219","title":"An attention model based on spatial transformers for scene recognition","display_name":"An attention model based on spatial transformers for scene recognition","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2608734801","doi":"https://doi.org/10.1109/icpr.2016.7900219","mag":"2608734801"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","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/A5011781002","display_name":"Shuxuan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuxuan Guo","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757829","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8598-0831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025657211","display_name":"Songyang Lao","orcid":"https://orcid.org/0000-0002-8025-3766"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyang Lao","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology Institute of Automation, Chinese Academy of Sciences","Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition"],"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011781002"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.202712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3757","last_page":"3762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T11714","display_name":"Multimodal Machine Learning 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8269025683403015},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7571896314620972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7229638695716858},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6346514225006104},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5913932919502258},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5781493186950684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5549036860466003},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5290664434432983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3416344225406647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269025683403015},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7571896314620972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7229638695716858},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6346514225006104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5913932919502258},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5781493186950684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5549036860466003},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5290664434432983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3416344225406647},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/icpr.2016.7900219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1724369340","https://openalex.org/W1836465849","https://openalex.org/W1899185266","https://openalex.org/W1987150989","https://openalex.org/W1991367009","https://openalex.org/W2017814585","https://openalex.org/W2107034620","https://openalex.org/W2134670479","https://openalex.org/W2152161678","https://openalex.org/W2154071538","https://openalex.org/W2191616647","https://openalex.org/W2216949779","https://openalex.org/W2295107390","https://openalex.org/W2618530766","https://openalex.org/W2950328304","https://openalex.org/W6618372016","https://openalex.org/W6628927728","https://openalex.org/W6630875275","https://openalex.org/W6637556369","https://openalex.org/W6639927594","https://openalex.org/W6679792166","https://openalex.org/W6688365552","https://openalex.org/W6697443983","https://openalex.org/W7075742223"],"related_works":["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/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Scene":[0],"recognition":[1],"is":[2,45,72,91,94,155],"an":[3,13,101],"important":[4],"and":[5,57,130],"challenging":[6],"task":[7],"in":[8,103],"computer":[9],"vision.":[10],"We":[11,111,150],"propose":[12],"end-to-end":[14],"pipeline":[15],"by":[16,82],"combing":[17],"convolutional":[18],"neural":[19],"networks":[20],"(CNNs)":[21],"with":[22,146],"explicit":[23],"attention":[24,49,62,160],"model":[25,135,154],"to":[26,96,121,157],"determine":[27],"several":[28],"meaningful":[29],"regions":[30,99,161],"of":[31,59,61,78,87,117,125],"original":[32],"images":[33],"for":[34,65,162],"scene":[35,164],"recognition.":[36],"In":[37],"the":[38,41,48,55,68,75,118,123,126,131,142],"proposed":[39,89,127],"pipeline,":[40],"spatial":[42],"transformer":[43],"network":[44,90,129],"leveraged":[46],"as":[47],"module,":[50],"which":[51],"can":[52],"automatically":[53],"learn":[54,158],"scales":[56],"movements":[58],"centers":[60],"windows.":[63],"As":[64],"feature":[66,83],"extraction,":[67],"basic":[69,128],"CNN":[70],"architecture":[71],"utilized.":[73],"Furthermore,":[74],"stronger":[76],"descriptors":[77],"scenes":[79],"are":[80],"constructed":[81],"fusion.":[84],"The":[85],"highlight":[86],"our":[88,153],"that":[92,152],"it":[93],"capable":[95],"localize":[97],"discriminative":[98],"from":[100],"image":[102],"a":[104,115],"data-driven":[105],"manner":[106],"without":[107],"any":[108],"additional":[109],"supervision.":[110],"conduct":[112],"experiments":[113],"on":[114,141],"subset":[116],"Places205":[119],"database":[120],"evaluate":[122],"performance":[124],"involved":[132],"parameters.":[133],"Our":[134],"achieves":[136],"state-of-the-art":[137],"top-1":[138],"accuracy":[139],"82.10%":[140],"evaluation":[143],"dataset":[144],"comparing":[145],"fine-tuned":[147],"PlacesCNN":[148],"(80.98%).":[149],"find":[151],"able":[156],"informative":[159],"discriminating":[163],"categories.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}