{"id":"https://openalex.org/W3211329537","doi":"https://doi.org/10.3390/rs13214441","title":"Building Extraction from Remote Sensing Images with Sparse Token Transformers","display_name":"Building Extraction from Remote Sensing Images with Sparse Token Transformers","publication_year":2021,"publication_date":"2021-11-04","ids":{"openalex":"https://openalex.org/W3211329537","doi":"https://doi.org/10.3390/rs13214441","mag":"3211329537"},"language":"en","primary_location":{"id":"doi:10.3390/rs13214441","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs13214441","pdf_url":"https://www.mdpi.com/2072-4292/13/21/4441/pdf?version=1636075865","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/13/21/4441/pdf?version=1636075865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518544","display_name":"Keyan Chen","orcid":"https://orcid.org/0000-0003-0483-1306"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyan Chen","raw_affiliation_strings":["Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China","Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China","State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088611151","display_name":"Zhengxia Zou","orcid":"https://orcid.org/0000-0003-1774-552X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengxia Zou","raw_affiliation_strings":["Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058849690","display_name":"Zhenwei Shi","orcid":"https://orcid.org/0000-0002-4772-3172"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenwei Shi","raw_affiliation_strings":["Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China","Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China","State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058849690"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":13.8614,"has_fulltext":true,"cited_by_count":166,"citation_normalized_percentile":{"value":0.99094969,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"13","issue":"21","first_page":"4441","last_page":"4441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8415369391441345},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6966465711593628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6159287691116333},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5709514617919922},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5603799819946289},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47709327936172485},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42023757100105286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3932207226753235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3688507378101349},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07257801294326782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415369391441345},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6966465711593628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6159287691116333},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5709514617919922},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5603799819946289},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47709327936172485},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42023757100105286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3932207226753235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3688507378101349},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07257801294326782},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/rs13214441","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs13214441","pdf_url":"https://www.mdpi.com/2072-4292/13/21/4441/pdf?version=1636075865","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7be1cf5f7cac4b119ac30e1cde47d610","is_oa":true,"landing_page_url":"https://doaj.org/article/7be1cf5f7cac4b119ac30e1cde47d610","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 13, Iss 21, p 4441 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2072-4292/13/21/4441/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/rs13214441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing; Volume 13; Issue 21; Pages: 4441","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/rs13214441","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs13214441","pdf_url":"https://www.mdpi.com/2072-4292/13/21/4441/pdf?version=1636075865","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G8320858330","display_name":null,"funder_award_id":"62125102","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211329537.pdf","grobid_xml":"https://content.openalex.org/works/W3211329537.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2039743515","https://openalex.org/W2055702796","https://openalex.org/W2078558728","https://openalex.org/W2107053193","https://openalex.org/W2141573384","https://openalex.org/W2158393484","https://openalex.org/W2168548458","https://openalex.org/W2184175677","https://openalex.org/W2194775991","https://openalex.org/W2412782625","https://openalex.org/W2476548250","https://openalex.org/W2592583011","https://openalex.org/W2609402060","https://openalex.org/W2771784662","https://openalex.org/W2787614951","https://openalex.org/W2900094710","https://openalex.org/W2903387688","https://openalex.org/W2908320224","https://openalex.org/W2912114399","https://openalex.org/W2934268922","https://openalex.org/W2938425859","https://openalex.org/W2939647427","https://openalex.org/W2944512710","https://openalex.org/W2955058313","https://openalex.org/W2963881378","https://openalex.org/W2964309882","https://openalex.org/W2966450079","https://openalex.org/W2967087542","https://openalex.org/W2972623730","https://openalex.org/W2980346985","https://openalex.org/W2982092116","https://openalex.org/W2982206001","https://openalex.org/W2991441757","https://openalex.org/W2997019934","https://openalex.org/W3000086214","https://openalex.org/W3004265084","https://openalex.org/W3006025044","https://openalex.org/W3011515952","https://openalex.org/W3014060899","https://openalex.org/W3022397457","https://openalex.org/W3022935549","https://openalex.org/W3042724941","https://openalex.org/W3044310826","https://openalex.org/W3053564872","https://openalex.org/W3088431851","https://openalex.org/W3096609285","https://openalex.org/W3104035745","https://openalex.org/W3111683216","https://openalex.org/W3112929693","https://openalex.org/W3112979587","https://openalex.org/W3122259118","https://openalex.org/W3126435384","https://openalex.org/W3128592650","https://openalex.org/W3128776197","https://openalex.org/W3130494073","https://openalex.org/W3139912591","https://openalex.org/W3148283428","https://openalex.org/W3153239544","https://openalex.org/W3156066202","https://openalex.org/W3161825146","https://openalex.org/W3170841864","https://openalex.org/W3171853541","https://openalex.org/W3172509117","https://openalex.org/W3180045188","https://openalex.org/W3186032668","https://openalex.org/W6660425701"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"methods":[2,16,193],"have":[3,27],"achieved":[4,202],"considerable":[5],"progress":[6],"in":[7,36,76,95,120,140],"remote":[8,96],"sensing":[9,97],"image":[10,108],"building":[11,14,60,89,197],"extraction.":[12,61],"Most":[13],"extraction":[15,90,198],"are":[17],"based":[18],"on":[19,87,163],"Convolutional":[20],"Neural":[21],"Networks":[22],"(CNN).":[23],"Recently,":[24],"vision":[25],"transformers":[26,57,141],"provided":[28],"a":[29,102,114,126,135],"better":[30],"perspective":[31],"for":[32,58],"modeling":[33],"long-range":[34],"context":[35],"images,":[37],"but":[38],"usually":[39,99],"suffer":[40],"from":[41],"high":[42],"computational":[43,138],"complexity":[44,139],"and":[45,80,83,171,182,194],"memory":[46],"usage.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,110],"explored":[52],"the":[53,71,107,137,164,172,180,203],"potential":[54],"of":[55,74,106,116,149,184],"using":[56],"efficient":[59,65],"We":[62,151],"design":[63],"an":[64,147],"dual-pathway":[66],"transformer":[67],"structure":[68],"that":[69],"learns":[70],"long-term":[72],"dependency":[73],"tokens":[75],"both":[77],"their":[78,121],"spatial":[79],"channel":[81],"dimensions":[82],"achieves":[84],"state-of-the-art":[85,196],"accuracy":[86],"benchmark":[88],"datasets.":[91],"Since":[92],"single":[93],"buildings":[94,112],"images":[98],"only":[100],"occupy":[101],"very":[103],"small":[104],"part":[105],"pixels,":[109],"represent":[111],"as":[113,156],"set":[115],"\u201csparse\u201d":[117],"feature":[118,122],"vectors":[119],"space":[123],"by":[124],"introducing":[125],"new":[127],"module":[128],"called":[129],"\u201csparse":[130],"token":[131],"sampler\u201d.":[132],"With":[133],"such":[134],"design,":[136],"can":[142],"be":[143],"greatly":[144],"reduced":[145],"over":[146],"order":[148],"magnitude.":[150],"refer":[152],"to":[153],"our":[154,185],"method":[155],"Sparse":[157],"Token":[158],"Transformers":[159],"(STT).":[160],"Experiments":[161],"conducted":[162],"Wuhan":[165],"University":[166],"Aerial":[167,174],"Building":[168],"Dataset":[169,177],"(WHU)":[170],"Inria":[173],"Image":[175],"Labeling":[176],"(INRIA)":[178],"suggest":[179],"effectiveness":[181],"efficiency":[183],"method.":[186],"Compared":[187],"with":[188,206],"some":[189,195],"widely":[190],"used":[191],"segmentation":[192],"methods,":[199],"STT":[200],"has":[201],"best":[204],"performance":[205],"low":[207],"time":[208],"cost.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}