{"id":"https://openalex.org/W4386072497","doi":"https://doi.org/10.23919/mva57639.2023.10216093","title":"Small Object Detection for Birds with Swin Transformer","display_name":"Small Object Detection for Birds with Swin Transformer","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386072497","doi":"https://doi.org/10.23919/mva57639.2023.10216093"},"language":"en","primary_location":{"id":"doi:10.23919/mva57639.2023.10216093","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva57639.2023.10216093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.22310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087905006","display_name":"Da Huo","orcid":"https://orcid.org/0000-0002-6530-0632"},"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":true,"raw_author_name":"Da Huo","raw_affiliation_strings":["Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907439","display_name":"Marc A. Kastner","orcid":"https://orcid.org/0000-0002-9193-5973"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc A. Kastner","raw_affiliation_strings":["Kyoto University,Sakyo-ku, Kyoto,Japan,606-8501"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Sakyo-ku, Kyoto,Japan,606-8501","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025275705","display_name":"Tingwei 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":"Tingwei Liu","raw_affiliation_strings":["Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"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"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["RIKEN,GRP,Seika-cho, Kyoto,Japan,619-0288","Nagoya University, Chikusa-ku, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN,GRP,Seika-cho, Kyoto,Japan,619-0288","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036735172","display_name":"Takatsugu Hirayama","orcid":"https://orcid.org/0000-0001-6290-9680"},"institutions":[{"id":"https://openalex.org/I84985371","display_name":"University of Human Environments","ror":"https://ror.org/029smmd76","country_code":"JP","type":"education","lineage":["https://openalex.org/I84985371"]},{"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":"Takatsugu Hirayama","raw_affiliation_strings":["University of Human Environments,Okazaki, Aichi,Japan,444-3505","Nagoya University, Chikusa-ku, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"University of Human Environments,Okazaki, Aichi,Japan,444-3505","institution_ids":["https://openalex.org/I84985371"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"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":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"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":"Ichiro Ide","raw_affiliation_strings":["Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Chikusa-ku, Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5087905006"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.8196834,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82326222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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":0.9969000220298767,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8029160499572754},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6981660723686218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.66750168800354},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6394946575164795},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5572254061698914},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42324429750442505},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4203488528728485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40943339467048645},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0873059630393982},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07189181447029114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029160499572754},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6981660723686218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66750168800354},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6394946575164795},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5572254061698914},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42324429750442505},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4203488528728485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40943339467048645},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0873059630393982},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07189181447029114},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/mva57639.2023.10216093","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva57639.2023.10216093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 18th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.22310","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22310","pdf_url":"https://arxiv.org/pdf/2511.22310","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:2511.22310","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22310","pdf_url":"https://arxiv.org/pdf/2511.22310","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":22,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2117539524","https://openalex.org/W2145607950","https://openalex.org/W2476548250","https://openalex.org/W2565639579","https://openalex.org/W2896155169","https://openalex.org/W2963402313","https://openalex.org/W2988452521","https://openalex.org/W2997408160","https://openalex.org/W3121020412","https://openalex.org/W3138516171","https://openalex.org/W3195029460","https://openalex.org/W4293584584","https://openalex.org/W4312706263","https://openalex.org/W4312823573","https://openalex.org/W6639102338","https://openalex.org/W6639824700","https://openalex.org/W6750227808","https://openalex.org/W6750378959","https://openalex.org/W6755240749","https://openalex.org/W6760424586"],"related_works":["https://openalex.org/W2390901981","https://openalex.org/W2109115373","https://openalex.org/W4230691760","https://openalex.org/W4391923333","https://openalex.org/W2393847170","https://openalex.org/W85049056","https://openalex.org/W158465905","https://openalex.org/W577521963","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Object":[0],"detection":[1,15,43],"is":[2,19,28,70,75],"the":[3,14,24,67,111,115,117,120,123,141,147,159,174],"task":[4],"of":[5,16,78,104],"detecting":[6,100],"objects":[7,18,60,79],"in":[8,55,61],"an":[9],"image.":[10],"In":[11,91],"this":[12,92],"task,":[13],"small":[17,25,41,48,71,105,154,189],"particularly":[20],"difficult.":[21],"Other":[22],"than":[23],"size,":[26],"it":[27,84],"also":[29],"accompanied":[30],"by":[31,114,172],"difficulties":[32],"due":[33],"to":[34,47,87,126,139,153,169],"blur,":[35],"occlusion,":[36],"and":[37,49,72,122],"so":[38],"on.":[39],"Current":[40],"object":[42,69,190],"methods":[44],"are":[45],"tailored":[46],"dense":[50],"situations,":[51],"such":[52],"as":[53],"pedestrians":[54],"a":[56,76,96,101,132],"crowd":[57],"or":[58],"far":[59],"remote":[62],"sensing":[63],"scenarios.":[64],"However,":[65],"when":[66],"target":[68],"sparse,":[73],"there":[74],"lack":[77],"available":[80],"for":[81,99,151,188],"training,":[82],"making":[83],"more":[85,128],"difficult":[86],"learn":[88,127],"effective":[89,129],"features.":[90,143],"paper,":[93],"we":[94,109,145],"propose":[95],"specialized":[97],"method":[98],"specific":[102],"category":[103],"objects;":[106],"birds.":[107],"Particularly,":[108],"improve":[110],"features":[112,130],"learned":[113],"neck;":[116],"sub-network":[118],"between":[119],"backbone":[121],"prediction":[124],"head,":[125],"with":[131,165],"hierarchical":[133],"design.":[134],"We":[135,177],"employ":[136],"Swin":[137,161],"Transformer":[138],"upsample":[140],"image":[142],"Moreover,":[144],"change":[146],"shifted":[148],"window":[149,175,182],"size":[150],"adapting":[152],"objects.":[155],"Experiments":[156],"show":[157],"that":[158,180],"proposed":[160],"Transformer-based":[162],"neck":[163],"combined":[164],"CenterNet":[166],"can":[167],"lead":[168],"good":[170],"performance":[171],"changing":[173],"sizes.":[176],"further":[178],"find":[179],"smaller":[181],"sizes":[183],"(default":[184],"2)":[185],"benefit":[186],"mAPs":[187],"detection.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}