{"id":"https://openalex.org/W4414144354","doi":"https://doi.org/10.1631/fitee.2400960","title":"End-to-end object detection using a query-selection encoder with hierarchical feature-aware attention","display_name":"End-to-end object detection using a query-selection encoder with hierarchical feature-aware attention","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414144354","doi":"https://doi.org/10.1631/fitee.2400960"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2400960","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400960","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5020535366","display_name":"Zuyi Wang","orcid":"https://orcid.org/0000-0001-7652-268X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zuyi Wang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7652-268X","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111335270","display_name":"Zhimeng Zheng","orcid":"https://orcid.org/0000-0002-9644-1219"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimeng Zheng","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670647","display_name":"Jun Meng","orcid":"https://orcid.org/0000-0003-0920-0968"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Meng","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Zhejiang University Robotics Institute, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University Robotics Institute, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112316572","display_name":"Li Xu","orcid":"https://orcid.org/0009-0008-9363-7575"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xu","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Zhejiang University Robotics Institute, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University Robotics Institute, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020535366"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2209421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"8","first_page":"1324","last_page":"1340"},"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":0.9997000098228455,"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":0.9973000288009644,"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/object-detection","display_name":"Object detection","score":0.7839999794960022},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7178999781608582},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6299999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.545799970626831},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5383999943733215},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5131000280380249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870000004768372},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7839999794960022},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7178999781608582},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628600001335144},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28439998626708984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2400960","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400960","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2982770724","https://openalex.org/W3012573144","https://openalex.org/W3035396860","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3108849448","https://openalex.org/W3167088971","https://openalex.org/W3171162369","https://openalex.org/W3172752666","https://openalex.org/W3199093552","https://openalex.org/W3203003533","https://openalex.org/W4312312588","https://openalex.org/W4386065740","https://openalex.org/W4386075868","https://openalex.org/W4386076079","https://openalex.org/W4386076325","https://openalex.org/W4386083115","https://openalex.org/W4388460549","https://openalex.org/W4390871882","https://openalex.org/W4390872804","https://openalex.org/W4390873750","https://openalex.org/W4403943254"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W4386564352","https://openalex.org/W4413042444","https://openalex.org/W2952668426","https://openalex.org/W3173456895"],"abstract_inverted_index":{"End-to-end":[0],"object":[1,66],"detection":[2,21,33,75],"methods":[3,25],"have":[4],"attracted":[5],"extensive":[6],"interest":[7],"recently":[8],"since":[9],"they":[10],"alleviate":[11],"the":[12,20,70,88,136,156,177,189],"need":[13],"for":[14,64,112],"complicated":[15],"human-designed":[16],"components":[17],"and":[18,31,43,74,130,150,169,184,199],"simplify":[19],"pipeline.":[22],"However,":[23],"these":[24],"suffer":[26],"from":[27,140],"slower":[28],"training":[29,71,211],"convergence":[30,72],"inferior":[32],"performance":[34,208],"compared":[35],"to":[36,68,100,134,187],"conventional":[37],"detectors,":[38],"as":[39],"their":[40],"feature":[41,132,148,157],"fusion":[42],"selection":[44,158],"processes":[45],"are":[46],"constrained":[47],"by":[48],"insufficient":[49],"positive":[50,110],"supervision.":[51],"To":[52],"address":[53],"this":[54],"issue,":[55],"we":[56],"introduce":[57],"a":[58,105,116],"novel":[59],"query-selection":[60],"encoder":[61,82,98,126],"(QSE)":[62],"designed":[63],"end-to-end":[65,207],"detectors":[67,201],"improve":[69],"speed":[73],"accuracy.":[76],"QSE":[77,203],"is":[78,94,122,162],"composed":[79],"of":[80,87,191],"multiple":[81],"layers":[83],"stacked":[84],"on":[85,176],"top":[86],"backbone.":[89],"A":[90],"lightweight":[91],"head":[92],"network":[93],"added":[95],"after":[96],"each":[97,125],"layer":[99],"continuously":[101],"optimize":[102],"features":[103,139],"in":[104,124,165],"cascading":[106],"manner,":[107],"providing":[108],"more":[109],"supervision":[111],"efficient":[113],"training.":[114],"Additionally,":[115],"hierarchical":[117],"feature-aware":[118],"attention":[119],"(HFA)":[120],"mechanism":[121],"incorporated":[123],"layer,":[127],"including":[128],"in-":[129],"cross-level":[131],"attention,":[133],"enhance":[135],"interaction":[137],"between":[138],"different":[141],"levels.":[142],"HFA":[143],"can":[144,204],"effectively":[145],"suppress":[146],"similar":[147],"representations":[149],"highlight":[151],"discriminative":[152],"ones,":[153],"thereby":[154],"accelerating":[155],"process.":[159],"Our":[160],"method":[161],"highly":[163],"versatile":[164],"accommodating":[166],"both":[167],"CNN-":[168,198],"Transformer-based":[170,200],"detectors.":[171],"Extensive":[172],"experiments":[173],"were":[174],"conducted":[175],"popular":[178],"benchmark":[179],"datasets":[180],"MS":[181],"COCO,":[182],"CrowdHuman,":[183],"PASCAL":[185],"VOC":[186],"demonstrate":[188],"effectiveness":[190],"our":[192],"method.":[193],"The":[194],"results":[195],"showed":[196],"that":[197],"using":[202],"achieve":[205],"better":[206],"within":[209],"fewer":[210],"epochs.":[212]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}