{"id":"https://openalex.org/W4312335509","doi":"https://doi.org/10.1109/tcsvt.2022.3222906","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","display_name":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4312335509","doi":"https://doi.org/10.1109/tcsvt.2022.3222906"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3222906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3222906","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5075846335","display_name":"Linhui Dai","orcid":"https://orcid.org/0000-0001-6465-1679"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhui Dai","raw_affiliation_strings":["Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Computer Vision Laboratory, ETH Zürich, Zürich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, ETH Zürich, Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101404098","display_name":"Zhiwei Wu","orcid":"https://orcid.org/0000-0003-4721-1617"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Wu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048813179","display_name":"Pinhao Song","orcid":"https://orcid.org/0000-0002-3950-0403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinhao Song","raw_affiliation_strings":["Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075846335"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":20.5301,"has_fulltext":false,"cited_by_count":220,"citation_normalized_percentile":{"value":0.99707586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"33","issue":"5","first_page":"2342","last_page":"2356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.7687416672706604},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6209298372268677},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6067405939102173},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.573566198348999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160434246063232},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.43575286865234375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38253626227378845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3676746189594269},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08934628963470459},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08332392573356628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687416672706604},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6209298372268677},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6067405939102173},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.573566198348999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160434246063232},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.43575286865234375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38253626227378845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3676746189594269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08934628963470459},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08332392573356628},{"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},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2022.3222906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3222906","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/721079","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/721079","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ieee Transactions On Circuits And Systems For Video Technology, vol. 33 (5), (2342-2356)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2682340759","display_name":null,"funder_award_id":"62073004","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2108598243","https://openalex.org/W2120859393","https://openalex.org/W2222512263","https://openalex.org/W2400138547","https://openalex.org/W2593539516","https://openalex.org/W2594177559","https://openalex.org/W2884561390","https://openalex.org/W2899594603","https://openalex.org/W2908510526","https://openalex.org/W2962749812","https://openalex.org/W2963150697","https://openalex.org/W2963849369","https://openalex.org/W2964979676","https://openalex.org/W2971900262","https://openalex.org/W2982363097","https://openalex.org/W2986357608","https://openalex.org/W2989678931","https://openalex.org/W2991359031","https://openalex.org/W2991363140","https://openalex.org/W3011606420","https://openalex.org/W3015352266","https://openalex.org/W3016916515","https://openalex.org/W3034993937","https://openalex.org/W3046174881","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3106228955","https://openalex.org/W3109055651","https://openalex.org/W3122893743","https://openalex.org/W3136761610","https://openalex.org/W3138516171","https://openalex.org/W3170033848","https://openalex.org/W3175496347","https://openalex.org/W3179092682","https://openalex.org/W3200253799","https://openalex.org/W3209642908","https://openalex.org/W3217491623","https://openalex.org/W4205832794","https://openalex.org/W4211247672","https://openalex.org/W4214627427","https://openalex.org/W4214648418","https://openalex.org/W4226013992","https://openalex.org/W4283800076","https://openalex.org/W4286974534","https://openalex.org/W4286978651","https://openalex.org/W4293584584","https://openalex.org/W4312804579","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6757817989","https://openalex.org/W6760424586","https://openalex.org/W6770886966","https://openalex.org/W6784094891","https://openalex.org/W6788870397","https://openalex.org/W6796087278","https://openalex.org/W6796874202","https://openalex.org/W6804539393","https://openalex.org/W6808005776","https://openalex.org/W6811230874","https://openalex.org/W6840415360","https://openalex.org/W6840596231"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Arbitrary-oriented":[0],"object":[1,56],"detection":[2,57],"(AOOD)":[3],"is":[4,100,129,151],"a":[5,59,146,175],"challenging":[6,183],"task":[7],"to":[8,102,115,131,153],"detect":[9],"objects":[10],"in":[11,119],"the":[12,51,67,117,120,138,155,170,193],"wild":[13],"with":[14],"arbitrary":[15],"orientations":[16],"and":[17,38,46,72,136,143,173],"cluttered":[18],"arrangements.":[19],"Existing":[20],"approaches":[21,54],"are":[22],"mainly":[23],"based":[24],"on":[25,33,181,192],"anchor-based":[26],"boxes":[27],"or":[28],"dense":[29],"points,":[30],"which":[31,88,107],"rely":[32],"complicated":[34],"hand-designed":[35,70],"processing":[36],"steps":[37],"inductive":[39,73],"bias,":[40],"such":[41],"as":[42,58],"anchor":[43],"generation,":[44],"transformation,":[45],"non-maximum":[47],"suppression":[48],"reasoning.":[49],"Recently,":[50],"emerging":[52],"transformer-based":[53],"view":[55],"direct":[60,160],"set":[61,148,161],"prediction":[62,162],"problem":[63],"that":[64,186],"effectively":[65],"removes":[66],"need":[68],"for":[69,112,159],"components":[71],"biases.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"propose":[79],"an":[80,95],"Arbitrary-Oriented":[81],"Object":[82],"DEtection":[83],"TRansformer":[84],"framework,":[85],"termed":[86],"AO2-DETR,":[87],"comprises":[89],"three":[90],"dedicated":[91],"components.":[92],"More":[93],"precisely,":[94],"oriented":[96,105,125],"proposal":[97,126],"generation":[98],"mechanism":[99],"proposed":[101],"explicitly":[103],"generate":[104],"proposals,":[106],"provides":[108],"better":[109],"positional":[110],"priors":[111],"pooling":[113],"features":[114,135,142],"modulate":[116],"cross-attention":[118],"transformer":[121],"decoder.":[122],"An":[123],"adaptive":[124],"refinement":[127],"module":[128],"introduced":[130],"extract":[132],"rotation-invariant":[133],"region":[134,141],"eliminate":[137],"misalignment":[139],"between":[140],"objects.":[144],"And":[145],"rotation-aware":[147],"matching":[149,157],"loss":[150],"used":[152],"ensure":[154],"one-to-one":[156],"process":[158],"without":[163],"duplicate":[164],"predictions.":[165],"Our":[166],"method":[167,188],"considerably":[168],"simplifies":[169],"overall":[171],"pipeline":[172],"presents":[174],"new":[176],"AOOD":[177,194],"paradigm.":[178],"Comprehensive":[179],"experiments":[180],"several":[182],"datasets":[184],"show":[185],"our":[187],"achieves":[189],"superior":[190],"performance":[191],"task.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":90},{"year":2024,"cited_by_count":81},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}