{"id":"https://openalex.org/W4410394497","doi":"https://doi.org/10.1109/tcsvt.2025.3570504","title":"Generalized Concordant Vision Transformer With Masked Image Tokens for Object Detection","display_name":"Generalized Concordant Vision Transformer With Masked Image Tokens for Object Detection","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410394497","doi":"https://doi.org/10.1109/tcsvt.2025.3570504"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3570504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3570504","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":null,"display_name":"Yu Quan","orcid":"https://orcid.org/0000-0002-5884-6039"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Quan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5884-6039","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101818657","display_name":"Dong Zhang","orcid":"https://orcid.org/0000-0002-4543-2179"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4543-2179","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8204,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90436842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"11","first_page":"10616","last_page":"10631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9480999708175659,"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"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9480999708175659,"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"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9322999715805054,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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-vision","display_name":"Computer vision","score":0.708898663520813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6776094436645508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.639855146408081},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5076879262924194},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46158841252326965},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.43472540378570557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37376534938812256},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3674218952655792}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.708898663520813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6776094436645508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639855146408081},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5076879262924194},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46158841252326965},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.43472540378570557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37376534938812256},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3674218952655792}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3570504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3570504","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:repository.hkust.edu.hk:1783.1-170204","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6671792466","display_name":null,"funder_award_id":"BG2024042","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2565639579","https://openalex.org/W2948672349","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963466847","https://openalex.org/W2963925437","https://openalex.org/W2966434031","https://openalex.org/W2983943451","https://openalex.org/W3034522582","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106728613","https://openalex.org/W3138516171","https://openalex.org/W3153273997","https://openalex.org/W3160412534","https://openalex.org/W3165745140","https://openalex.org/W3165924482","https://openalex.org/W3168825659","https://openalex.org/W3169575272","https://openalex.org/W3176659256","https://openalex.org/W3180134609","https://openalex.org/W3212032174","https://openalex.org/W4206118545","https://openalex.org/W4214588794","https://openalex.org/W4214614183","https://openalex.org/W4225531230","https://openalex.org/W4226512186","https://openalex.org/W4312446817","https://openalex.org/W4312612915","https://openalex.org/W4312685069","https://openalex.org/W4312769131","https://openalex.org/W4313032837","https://openalex.org/W4313156423","https://openalex.org/W4315705623","https://openalex.org/W4366463717","https://openalex.org/W4376872192","https://openalex.org/W4385245566","https://openalex.org/W4386076325","https://openalex.org/W4386076493","https://openalex.org/W4386320382","https://openalex.org/W4388976132","https://openalex.org/W4389961109","https://openalex.org/W4390618600","https://openalex.org/W4390706284","https://openalex.org/W4390873661","https://openalex.org/W4390873750","https://openalex.org/W4390874177","https://openalex.org/W4390874319","https://openalex.org/W4392940036","https://openalex.org/W4393404507","https://openalex.org/W4400409506","https://openalex.org/W4400721967","https://openalex.org/W4400975112","https://openalex.org/W4402436199","https://openalex.org/W4402716047","https://openalex.org/W4402978296","https://openalex.org/W4403390316","https://openalex.org/W4403943254","https://openalex.org/W4405784843","https://openalex.org/W4406163664","https://openalex.org/W4407555696","https://openalex.org/W4412381848"],"related_works":["https://openalex.org/W4308080241","https://openalex.org/W4391382592","https://openalex.org/W4387253492","https://openalex.org/W2921271497","https://openalex.org/W4205668735","https://openalex.org/W4360585155","https://openalex.org/W1921169094","https://openalex.org/W2570343428","https://openalex.org/W4200612475","https://openalex.org/W366410996"],"abstract_inverted_index":{"The":[0],"vision":[1],"transformer":[2],"(ViT)":[3],"architecture":[4],"offers":[5],"significant":[6],"advantages":[7],"in":[8,41],"object":[9,64,221],"detection":[10,65,222],"tasks.":[11],"However,":[12],"some":[13],"limitations":[14],"affect":[15],"improving":[16],"task":[17],"performance.":[18],"Firstly,":[19],"the":[20,77,84,91,129,139,160,173,202,208],"ViT":[21,61],"relies":[22],"heavily":[23],"on":[24,207],"inflexible":[25],"position":[26,87,108],"embedding,":[27],"which":[28,80],"causes":[29],"poor":[30],"performance":[31,218],"when":[32],"processing":[33],"images":[34],"with":[35,184],"complex":[36,146],"semantic":[37,134],"dependencies.Secondly,":[38],"class":[39,161],"imbalance":[40,162],"large-scale":[42],"datasets":[43],"can":[44,188,215],"easily":[45],"cause":[46],"training":[47,165],"instability":[48],"and":[49,97,111,177,196],"inference":[50],"bias.":[51],"To":[52],"overcome":[53],"these":[54],"limitations,":[55],"we":[56,68,150],"propose":[57,151],"a":[58,71,98,115,123,152,168],"generalized":[59],"concordant":[60],"scheme":[62,137],"for":[63],"(GCViTDet).":[66],"Specifically,":[67],"first":[69],"introduce":[70],"relevance":[72],"enhancement":[73],"strategy":[74,102],"(RES)":[75],"into":[76],"encoder-decoder":[78],"structure,":[79],"is":[81,120],"composed":[82],"of":[83,141,180],"spatial":[85],"enhanced":[86,107],"embeddings":[88],"(SEPE)":[89],"component,":[90,96],"cross":[92,124],"multipooling":[93],"attention":[94,126],"(CMPA)":[95],"global-local":[99],"path.":[100],"This":[101,136],"establishes":[103],"semantic-rich":[104,197],"dependencies":[105,198],"through":[106],"embedding":[109],"information":[110],"omni-feature":[112],"representations.":[113],"Subsequently,":[114],"bottom-up":[116],"feature":[117],"aggregation":[118],"pathway":[119],"employed,":[121],"utilizing":[122],"multi-pooling":[125],"to":[127,132,158,171],"improve":[128,217],"model\u2019s":[130],"capacity":[131],"capture":[133,191],"dependencies.":[135],"enables":[138],"extraction":[140],"high-dimensional":[142],"features":[143],"that":[144,213],"exhibit":[145],"positional":[147,194],"relationships.":[148],"Besides,":[149],"focal":[153],"unified":[154],"cross-entropy":[155],"(FUCE)":[156],"loss":[157],"solve":[159],"problem":[163],"during":[164],"by":[166],"introducing":[167],"uniform":[169],"threshold":[170],"regulate":[172],"similarity":[174],"between":[175],"positive":[176],"negative":[178],"samples":[179],"different":[181],"classes.":[182],"Compared":[183],"existing":[185],"methods,":[186],"GCViTDet":[187,214],"not":[189],"only":[190],"more":[192],"intricate":[193],"relationships":[195],"but":[199],"also":[200],"alleviate":[201],"class-imbalance":[203],"problem.":[204],"Experimental":[205],"results":[206],"challenging":[209],"MS-COCO":[210],"dataset":[211],"validate":[212],"consistently":[216],"over":[219],"state-of-the-art":[220],"baseline":[223],"models.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}