{"id":"https://openalex.org/W4394593100","doi":"https://doi.org/10.1109/wacv57701.2024.00698","title":"BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping","display_name":"BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394593100","doi":"https://doi.org/10.1109/wacv57701.2024.00698"},"language":"en","primary_location":{"id":"doi:10.1109/wacv57701.2024.00698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5089378935","display_name":"Srikumar Sastry","orcid":"https://orcid.org/0000-0002-4646-9416"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikumar Sastry","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038402302","display_name":"Subash Khanal","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subash Khanal","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108919727","display_name":"Aayush Dhakal","orcid":"https://orcid.org/0000-0003-4431-0628"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aayush Dhakal","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029557305","display_name":"Nathan Jacobs","orcid":"https://orcid.org/0000-0002-4242-8967"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Jacobs","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6219,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80796904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7121","last_page":"7130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9969000220298767,"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/T12644","display_name":"Wildlife-Road Interactions and Conservation","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"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/T10199","display_name":"Wildlife Ecology and Conservation","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.6499371528625488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6303874254226685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42918169498443604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39397960901260376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499371528625488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6303874254226685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42918169498443604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39397960901260376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv57701.2024.00698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1585779673","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1954152232","https://openalex.org/W2042718506","https://openalex.org/W2138011018","https://openalex.org/W2183341477","https://openalex.org/W2398118205","https://openalex.org/W2604195031","https://openalex.org/W2737725206","https://openalex.org/W2773003563","https://openalex.org/W2797977484","https://openalex.org/W2882999943","https://openalex.org/W2883888092","https://openalex.org/W2885097192","https://openalex.org/W2891951760","https://openalex.org/W2896457183","https://openalex.org/W2963407932","https://openalex.org/W2992308087","https://openalex.org/W3009561768","https://openalex.org/W3010977521","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3035738719","https://openalex.org/W3175227919","https://openalex.org/W3202897123","https://openalex.org/W4200626011","https://openalex.org/W4214644404","https://openalex.org/W4221154675","https://openalex.org/W4221167396","https://openalex.org/W4223574620","https://openalex.org/W4281899128","https://openalex.org/W4286233797","https://openalex.org/W4287064209","https://openalex.org/W4307823382","https://openalex.org/W4312685069","https://openalex.org/W4312795296","https://openalex.org/W4313156423","https://openalex.org/W4317438003","https://openalex.org/W4320477735","https://openalex.org/W4324314567","https://openalex.org/W4366377626","https://openalex.org/W4386057726","https://openalex.org/W4389104669","https://openalex.org/W4390874379","https://openalex.org/W4402916161","https://openalex.org/W6638319203","https://openalex.org/W6638677478","https://openalex.org/W6726497184","https://openalex.org/W6757817989","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6791353385","https://openalex.org/W6797235774","https://openalex.org/W6810265253","https://openalex.org/W6810310139","https://openalex.org/W6838540985","https://openalex.org/W6840202747","https://openalex.org/W6840501922","https://openalex.org/W6849153078","https://openalex.org/W6849762702","https://openalex.org/W6850524417","https://openalex.org/W6852490124","https://openalex.org/W6856406217","https://openalex.org/W6857016583"],"related_works":["https://openalex.org/W4391375266","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/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,49,74],"propose":[1],"a":[2,57],"metadata-aware":[3],"self-supervised":[4],"learning":[5,117],"(SSL)":[6],"framework":[7,22,105],"useful":[8],"for":[9,119],"fine-grained":[10,80,93],"classification":[11,95],"and":[12,30,53,70,81,97,114,121,146],"ecological":[13],"mapping":[14],"of":[15,47,85,111,130,136],"bird":[16,61],"species":[17,62,137],"around":[18],"the":[19,38,125,134],"world.":[20],"Our":[21],"unifies":[23],"two":[24,90],"SSL":[25],"strategies:":[26],"Contrastive":[27],"Learning":[28],"(CL)":[29],"Masked":[31],"Image":[32],"Modeling":[33],"(MIM),":[34],"while":[35],"also":[36],"enriching":[37],"embedding":[39],"space":[40],"with":[41,44],"metadata":[42,67],"available":[43],"ground-level":[45,65],"imagery":[46],"birds.":[48],"separately":[50],"train":[51],"uni-modal":[52],"cross-modal":[54,98,127],"ViT":[55],"on":[56,89,109],"novel":[58],"cross-view":[59],"global":[60],"dataset":[63,145],"containing":[64],"imagery,":[66],"(location,":[68],"time),":[69],"corresponding":[71],"satellite":[72],"imagery.":[73],"demonstrate":[75],"that":[76],"our":[77,104,131],"models":[78,101],"learn":[79],"geographically":[82],"conditioned":[83],"features":[84],"birds,":[86],"by":[87],"evaluating":[88],"downstream":[91],"tasks:":[92],"visual":[94],"(FGVC)":[96],"retrieval.":[99],"Pre-trained":[100],"learned":[102],"using":[103],"achieve":[106],"SotA":[107],"performance":[108,129],"FGVC":[110],"iNAT-2021":[112],"birds":[113],"in":[115],"transfer":[116],"settings":[118],"CUB-200-2011":[120],"NABirds":[122],"datasets.":[123],"Moreover,":[124],"impressive":[126],"retrieval":[128],"model":[132],"enables":[133],"creation":[135],"distribution":[138],"maps":[139],"across":[140],"any":[141],"geographic":[142],"region.":[143],"The":[144],"source":[147],"code":[148],"will":[149],"be":[150],"released":[151],"at":[152],"https://github.com/mvrl/BirdSAT.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
