{"id":"https://openalex.org/W4304080526","doi":"https://doi.org/10.1145/3503161.3547799","title":"Rotation Invariant Transformer for Recognizing Object in UAVs","display_name":"Rotation Invariant Transformer for Recognizing Object in UAVs","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080526","doi":"https://doi.org/10.1145/3503161.3547799"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547799","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018222732","display_name":"Shuoyi Chen","orcid":"https://orcid.org/0000-0001-7507-3309"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuoyi Chen","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["Wuhan University & Hubei Luojia Laboratory, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University & Hubei Luojia Laboratory, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2565","last_page":"2574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":1.0,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":1.0,"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":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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":0.7115370035171509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6800194978713989},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6486195921897888},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5818899869918823},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5372341275215149},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4871063232421875},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4450419247150421},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.4273574948310852},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1463724970817566},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14388200640678406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13743826746940613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115370035171509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6800194978713989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6486195921897888},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5818899869918823},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5372341275215149},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4871063232421875},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4450419247150421},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4273574948310852},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1463724970817566},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14388200640678406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13743826746940613},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547799","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2204750386","https://openalex.org/W2342611082","https://openalex.org/W2586899202","https://openalex.org/W2795758732","https://openalex.org/W2799047769","https://openalex.org/W2962926870","https://openalex.org/W2963091558","https://openalex.org/W2963842104","https://openalex.org/W2963901085","https://openalex.org/W2964260687","https://openalex.org/W2964979676","https://openalex.org/W2981617237","https://openalex.org/W2984145721","https://openalex.org/W2989923292","https://openalex.org/W2991240825","https://openalex.org/W3034580371","https://openalex.org/W3034727830","https://openalex.org/W3035186652","https://openalex.org/W3035216422","https://openalex.org/W3035539956","https://openalex.org/W3035645942","https://openalex.org/W3047363187","https://openalex.org/W3100260313","https://openalex.org/W3100506510","https://openalex.org/W3105077954","https://openalex.org/W3140922383","https://openalex.org/W3171395710","https://openalex.org/W3174873843","https://openalex.org/W3176633985","https://openalex.org/W3180614977","https://openalex.org/W3194341910","https://openalex.org/W3211328899","https://openalex.org/W4200316912","https://openalex.org/W4214891830","https://openalex.org/W6785764235"],"related_works":["https://openalex.org/W2036807459","https://openalex.org/W2541791370","https://openalex.org/W2035976912","https://openalex.org/W2109974539","https://openalex.org/W2738084969","https://openalex.org/W2125927971","https://openalex.org/W2954664659","https://openalex.org/W1999222583","https://openalex.org/W2042311553","https://openalex.org/W4292829955"],"abstract_inverted_index":{"Recognizing":[0],"a":[1,101],"target":[2],"of":[3,53,76,117,120],"interest":[4],"from":[5,30],"the":[6,13,26,36,55,67,81,92,96,115,118,121,127,141,144,148,160,166,176,188,201,205,211],"UAVs":[7,27],"is":[8,64,170,223],"much":[9],"more":[10],"challenging":[11],"than":[12,175],"existing":[14],"object":[15,37],"re-identification":[16,190],"tasks":[17],"across":[18],"multiple":[19],"city":[20,50,194],"cameras.":[21,195],"The":[22],"images":[23],"taken":[24],"by":[25],"usually":[28,47],"suffer":[29],"significant":[31],"size":[32],"difference":[33],"when":[34,79],"generating":[35],"bounding":[38],"boxes":[39],"and":[40,147,172,179,215],"uncertain":[41],"rotation":[42,56,69,93,103,131,153],"variations.":[43],"Existing":[44],"methods":[45],"are":[46],"designed":[48],"for":[49,187],"cameras,":[51],"incapable":[52],"handing":[54],"issue":[57],"in":[58,204,210,219],"UAV":[59,162],"scenarios.":[60],"A":[61],"straightforward":[62],"solution":[63,199],"to":[65,90,139],"perform":[66],"image-level":[68],"augmentation,":[70],"but":[71],"it":[72],"would":[73],"cause":[74],"loss":[75],"useful":[77],"information":[78],"inputting":[80],"powerful":[82],"vision":[83,105,122],"transformer":[84,106,123,157],"as":[85],"patches.":[86],"This":[87,108],"motivates":[88],"us":[89],"simulate":[91],"operation":[94],"at":[95,225],"patch":[97],"feature":[98,146],"level,":[99],"proposing":[100],"novel":[102],"invariant":[104],"(RotTrans).":[107],"strategy":[109],"builds":[110],"on":[111,159,192],"high-level":[112],"features":[113],"with":[114],"help":[116],"specificity":[119],"structure,":[124],"which":[125,169],"enhances":[126],"robustness":[128],"against":[129],"large":[130],"differences.":[132],"In":[133,196],"addition,":[134],"we":[135],"design":[136],"invariance":[137],"constraint":[138],"establish":[140],"relationship":[142],"between":[143],"original":[145],"rotated":[149],"features,":[150],"achieving":[151],"stronger":[152],"invariance.":[154],"Our":[155],"proposed":[156],"tested":[158],"latest":[161],"datasets":[163],"greatly":[164],"outperforms":[165],"current":[167],"state-of-the-arts,":[168],"5.9%":[171],"4.8%":[173],"higher":[174],"highest":[177],"mAP":[178],"Rank1.":[180],"Notably,":[181],"our":[182,198],"model":[183],"also":[184],"performs":[185],"competitively":[186],"person":[189,207],"task":[191],"traditional":[193],"particular,":[197],"wins":[200],"first":[202],"place":[203],"UAV-based":[206],"re-recognition":[208],"track":[209],"Multi-Modal":[212],"Video":[213],"Reasoning":[214],"Analyzing":[216],"Competition":[217],"held":[218],"ICCV":[220],"2021.":[221],"Code":[222],"available":[224],"https://github.com/whucsy/RotTrans.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}