{"id":"https://openalex.org/W3091076443","doi":"https://doi.org/10.1109/tgrs.2021.3064316","title":"Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings","display_name":"Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings","publication_year":2021,"publication_date":"2021-03-17","ids":{"openalex":"https://openalex.org/W3091076443","doi":"https://doi.org/10.1109/tgrs.2021.3064316","mag":"3091076443"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2021.3064316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2021.3064316","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.01305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0001-9949-4693"},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongkun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Liu","raw_affiliation_strings":["School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyuan Hao","orcid":"https://orcid.org/0000-0001-8247-4207"},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Hao","raw_affiliation_strings":["School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaoxing Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxing Lu","raw_affiliation_strings":["School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongbin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Liu","raw_affiliation_strings":["BIM Research Center, Qingdao Research Institute of Urban and Rural Construction, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"BIM Research Center, Qingdao Research Institute of Urban and Rural Construction, Qingdao, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Lijian Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijian Zhou","raw_affiliation_strings":["School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44468530"],"apc_list":null,"apc_paid":null,"fwci":0.6782,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.69940351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"60","issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.37380000948905945,"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":0.37380000948905945,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.18459999561309814,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.08229999989271164,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7031000256538391},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6298999786376953},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.600600004196167},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5823000073432922},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49160000681877136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43869999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.600600004196167},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573999881744385},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3894999921321869},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.3176000118255615},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.3109000027179718},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2842000126838684},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgrs.2021.3064316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2021.3064316","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.01305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.01305","pdf_url":"https://arxiv.org/pdf/2010.01305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.01305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.01305","pdf_url":"https://arxiv.org/pdf/2010.01305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1944396096","https://openalex.org/W1946093182","https://openalex.org/W1978338723","https://openalex.org/W1999378860","https://openalex.org/W1999567494","https://openalex.org/W2048852482","https://openalex.org/W2064675550","https://openalex.org/W2081418428","https://openalex.org/W2086604341","https://openalex.org/W2109884388","https://openalex.org/W2117539524","https://openalex.org/W2131774270","https://openalex.org/W2134927309","https://openalex.org/W2145315825","https://openalex.org/W2194775991","https://openalex.org/W2267186426","https://openalex.org/W2295936256","https://openalex.org/W2340897893","https://openalex.org/W2362555197","https://openalex.org/W2593685093","https://openalex.org/W2614445056","https://openalex.org/W2737258237","https://openalex.org/W2741577003","https://openalex.org/W2755090963","https://openalex.org/W2762186317","https://openalex.org/W2767106145","https://openalex.org/W2768124800","https://openalex.org/W2781228439","https://openalex.org/W2883820570","https://openalex.org/W2893256830","https://openalex.org/W2900849519","https://openalex.org/W2911555398","https://openalex.org/W2921479043","https://openalex.org/W2937970997","https://openalex.org/W2943325261","https://openalex.org/W2947698013","https://openalex.org/W2948777210","https://openalex.org/W2952234521","https://openalex.org/W2961334035","https://openalex.org/W2962858109","https://openalex.org/W2963049618","https://openalex.org/W2963126277","https://openalex.org/W2963420272","https://openalex.org/W2963881378","https://openalex.org/W2964199361","https://openalex.org/W2964294898","https://openalex.org/W2969936457","https://openalex.org/W2987094173","https://openalex.org/W2989676862","https://openalex.org/W3012111773","https://openalex.org/W6631190155","https://openalex.org/W6679792166","https://openalex.org/W6685322675","https://openalex.org/W6739901393","https://openalex.org/W6758645304","https://openalex.org/W6764322716","https://openalex.org/W6781905506","https://openalex.org/W6891808250"],"related_works":[],"abstract_inverted_index":{"Street":[0],"view":[1,102,161,212,232],"image":[2,74,162,233],"classification":[3,39,234],"aiming":[4],"at":[5,271],"the":[6,14,28,72,87,95,115,130,154,159,186,219,246],"urban":[7],"land":[8,155],"use":[9,156],"analysis":[10],"is":[11,64,124],"difficult":[12],"because":[13],"class":[15],"labels":[16],"(e.g.,":[17,34],"commercial":[18],"area)":[19],"are":[20,148,269],"concepts":[21],"with":[22,145],"higher":[23,192],"abstract":[24,193],"levels":[25],"compared":[26],"to":[27,47,150,180],"ones":[29],"of":[30,67,71,98,118,135,158,209],"general":[31],"visual":[32,43,69,189],"tasks":[33],"persons":[35],"and":[36,61,121,191,214,256,266],"cars).":[37],"Therefore,":[38],"models":[40,79],"using":[41,68],"only":[42,229],"features":[44,70,190],"often":[45],"fail":[46],"achieve":[48],"satisfactory":[49],"performance.":[50],"In":[51,176],"this":[52],"article,":[53],"a":[54,59,105,164,171,197,250],"novel":[55],"approach":[56,248],"based":[57,80,217],"on":[58,81,218,242,254,258],"&#x201C;bottom-up":[60],"top-down&#x201D;":[62],"framework":[63,89],"proposed.":[65],"Instead":[66],"whole":[73],"directly":[75],"as":[76,114,185],"common":[77],"image-level":[78,261],"convolutional":[82],"neural":[83,173],"networks":[84],"(CNNs)":[85],"do,":[86],"proposed":[88,131,247],"first":[90],"obtains":[91],"low-level":[92,183],"semantic,":[93,152],"namely,":[94,153],"bounding":[96],"boxes":[97],"buildings":[99,216],"in":[100,178],"street":[101,160,211,231],"images":[103,213],"through":[104,163],"bottom-up":[106],"object":[107],"discovery":[108],"process.":[109],"Their":[110],"contextual":[111],"information,":[112],"such":[113],"co-occurrence":[116],"patterns":[117],"building":[119,239],"classes":[120],"their":[122],"layout,":[123],"then":[125],"encoded":[126,144],"into":[127],"metadata":[128,141],"by":[129,170],"algorithm":[132],"&#x201C;Context":[133],"encOding":[134],"Detected":[136],"buildINGs&#x201D;":[137],"(CODING).":[138],"Finally,":[139],"these":[140],"(low-level":[142],"semantic":[143,166,184],"context":[146],"information)":[147],"abstracted":[149],"high-level":[151],"label":[157],"top-down":[165],"aggregation":[167],"process":[168],"implemented":[169],"recurrent":[172],"network":[174],"(RNN).":[175],"addition,":[177],"order":[179],"effectively":[181],"discover":[182],"bridge":[187],"between":[188],"concepts,":[194],"we":[195],"made":[196],"dual-labeled":[198],"data":[199,223,267],"set":[200,224,268],"named":[201],"&#x201C;Building":[202],"dEtection":[203],"And":[204],"Urban":[205],"funcTional-zone":[206],"portraYing&#x201D;":[207],"(BEAUTY)":[208],"19070":[210],"38857":[215],"existing":[220],"BIC&#x005F;GSV.":[221],"The":[222],"can":[225],"be":[226],"used":[227],"not":[228],"for":[230,237],"but":[235],"also":[236],"multiclass":[238],"detection.":[240],"Experiments":[241],"&#x201C;BEAUTY&#x201D;":[243],"show":[244],"that":[245],"achieves":[249],"12.65&#x0025;":[251],"performance":[252],"improvement":[253],"macroprecision":[255],"12&#x0025;":[257],"macrorecall":[259],"over":[260],"CNN-based":[262],"models.":[263],"Our":[264],"code":[265],"available":[270],"<uri>https://github.com/kyle-one/Context-Encoding-of-Detected-Buildings/</uri>.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-10-08T00:00:00"}