{"id":"https://openalex.org/W4377079900","doi":"https://doi.org/10.1109/tcsvt.2023.3277621","title":"Diag-IoU Loss for Object Detection","display_name":"Diag-IoU Loss for Object Detection","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377079900","doi":"https://doi.org/10.1109/tcsvt.2023.3277621"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3277621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3277621","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/A5114928684","display_name":"Shuangqing Zhang","orcid":"https://orcid.org/0009-0008-3286-2672"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuangqing Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023640358","display_name":"Zhen Jia","orcid":"https://orcid.org/0000-0002-6810-2279"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Jia","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349638","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0003-2749-5528"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, and the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599309","display_name":"Zhang Zhang","orcid":"https://orcid.org/0000-0001-9425-3065"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Zhang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114928684"],"corresponding_institution_ids":["https://openalex.org/I143868143","https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":3.2552,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93711506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"12","first_page":"7671","last_page":"7683"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9952999949455261,"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":0.9939000010490417,"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":0.687158465385437},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.6424154043197632},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5793058276176453},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5152645111083984},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47432205080986023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4659114181995392},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.43746933341026306},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4138188064098358},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40579158067703247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39093443751335144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22334182262420654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19740229845046997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687158465385437},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.6424154043197632},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5793058276176453},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5152645111083984},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47432205080986023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659114181995392},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.43746933341026306},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4138188064098358},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40579158067703247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39093443751335144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22334182262420654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19740229845046997},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3277621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3277621","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3901020816","display_name":null,"funder_award_id":"2022ZD0117901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4664901819","display_name":null,"funder_award_id":"62106260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5156147101","display_name":null,"funder_award_id":"62236010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G808462669","display_name":null,"funder_award_id":"62076078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G849060900","display_name":null,"funder_award_id":"2208085J18","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2169954311","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2504335775","https://openalex.org/W2896991173","https://openalex.org/W2913960518","https://openalex.org/W2962677013","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963299996","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2997747012","https://openalex.org/W3011606420","https://openalex.org/W3012573144","https://openalex.org/W3035396860","https://openalex.org/W3048145096","https://openalex.org/W3096609285","https://openalex.org/W3100179319","https://openalex.org/W3102494826","https://openalex.org/W3106250896","https://openalex.org/W3122173535","https://openalex.org/W3122239467","https://openalex.org/W3138516171","https://openalex.org/W3145410920","https://openalex.org/W3161083802","https://openalex.org/W3161927037","https://openalex.org/W3172752666","https://openalex.org/W3176566042","https://openalex.org/W3194790201","https://openalex.org/W3200932651","https://openalex.org/W4221143432","https://openalex.org/W4281790833","https://openalex.org/W4288325606","https://openalex.org/W4290994873","https://openalex.org/W4293584584","https://openalex.org/W4296425725","https://openalex.org/W4302029029","https://openalex.org/W4312291425","https://openalex.org/W4312312588","https://openalex.org/W4312313652","https://openalex.org/W4312443415","https://openalex.org/W4312692509","https://openalex.org/W4312781996","https://openalex.org/W4313119505","https://openalex.org/W4386076325","https://openalex.org/W6637373629","https://openalex.org/W6682751323","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6760424586","https://openalex.org/W6764322716","https://openalex.org/W6784094891","https://openalex.org/W6788520541","https://openalex.org/W6838547440","https://openalex.org/W6849520326"],"related_works":["https://openalex.org/W1495267108","https://openalex.org/W2625952574","https://openalex.org/W3089513339","https://openalex.org/W2949086864","https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W4210851927","https://openalex.org/W1689909837","https://openalex.org/W2953362004","https://openalex.org/W4298525700"],"abstract_inverted_index":{"Existing":[0],"IoU-based":[1,213],"loss":[2,169,209],"functions":[3],"have":[4],"achieved":[5],"promising":[6],"performance":[7,204],"for":[8],"bounding":[9],"box":[10,32,54,74,92,95,124,155],"regression":[11],"in":[12,28,70,141,151],"object":[13,173,191],"detection.":[14],"However,":[15],"they":[16],"cannot":[17],"fully":[18],"reflect":[19],"the":[20,23,29,53,61,64,71,106,110,120,128,148,152,159,162,167,185,202,206],"relation":[21],"between":[22,63],"predicted":[24,65,121],"and":[25,34,40,66,76,82,100,104,122,145,180,188,198],"target":[26,67,123],"boxes":[27,68,144,150],"case":[30,72,153],"of":[31,73,112,115,154,161,205],"inclusions,":[33,75],"might":[35],"thus":[36,77,146],"deteriorate":[37],"detection":[38,192],"accuracy":[39,81],"efficiency.":[41],"In":[42,85],"this":[43],"paper,":[44],"we":[45,87,130,165],"design":[46,131],"a":[47,90,113,132],"novel":[48],"similarity":[49],"measurement":[50],"based":[51,108],"on":[52,109,127,184],"diagonal":[55],"called":[56],"Diag-IoU":[57,107,134,168,208],"to":[58,170,211],"well":[59,216],"represent":[60,89],"divergence":[62],"even":[69],"achieve":[78],"superior":[79,203],"localization":[80],"fast":[83],"convergence.":[84],"particular,":[86],"equivalently":[88],"rectangular":[91],"with":[93],"its":[94],"diagonal,":[96],"which":[97,136],"contains":[98],"exclusive":[99],"informative":[101],"geometrical":[102],"factors,":[103],"define":[105],"similarities":[111],"set":[114],"sampled":[116],"point":[117],"pairs":[118],"from":[119],"diagonals.":[125],"Based":[126],"Diag-IoU,":[129],"general":[133],"loss,":[135],"can":[137],"provide":[138],"holistic":[139],"information":[140],"measuring":[142],"two":[143,149,189],"differentiate":[147],"inclusions.":[156],"To":[157],"validate":[158],"effectiveness":[160],"proposed":[163,207],"method,":[164],"apply":[166],"several":[171],"representative":[172],"detectors,":[174],"including":[175],"YOLO":[176],"v5s,":[177],"Faster":[178],"R-CNN,":[179],"FCOS.":[181],"Extensive":[182],"experiments":[183],"synthetic":[186],"data":[187],"challenging":[190],"benchmark":[193],"datasets,":[194],"i.e.,":[195],"MS":[196],"COCO":[197],"PASCAL":[199],"VOC,":[200],"demonstrate":[201],"compared":[210],"previous":[212],"losses":[214],"as":[215,217],"other":[218],"metrics.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":17}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}