{"id":"https://openalex.org/W4415708365","doi":"https://doi.org/10.1109/icme59968.2025.11209405","title":"Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization","display_name":"Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708365","doi":"https://doi.org/10.1109/icme59968.2025.11209405"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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":"Xiaocheng Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaocheng Fang","raw_affiliation_strings":["South China Normal University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075973287","display_name":"Jiali Cai","orcid":"https://orcid.org/0000-0001-8593-8345"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieyi Cai","raw_affiliation_strings":["South China Normal University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101535572","display_name":"Huanyu Liu","orcid":"https://orcid.org/0000-0001-9226-9792"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanyu Liu","raw_affiliation_strings":["South China Normal University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111376387","display_name":"Wenxiu Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiu Cai","raw_affiliation_strings":["South China Normal University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110972704","display_name":"Yishu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yishu Liu","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055183002","display_name":"Bingzhi Chen","orcid":"https://orcid.org/0000-0002-2497-6214"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210165204","display_name":"Zhuhai Institute of Advanced Technology","ror":"https://ror.org/05r1mzq61","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4210165204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingzhi Chen","raw_affiliation_strings":["Beijing Institute of Technology,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Zhuhai,China","institution_ids":["https://openalex.org/I4210165204","https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3035904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.963100016117096,"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":0.963100016117096,"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":0.006300000008195639,"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":0.003700000001117587,"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/object-detection","display_name":"Object detection","score":0.6579999923706055},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6363999843597412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6263999938964844},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5846999883651733},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5295000076293945},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5156999826431274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.3903000056743622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6579999923706055},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5489000082015991},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49729999899864197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4075999855995178},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.31049999594688416},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2565639579","https://openalex.org/W2963351448","https://openalex.org/W2982770724","https://openalex.org/W2985384565","https://openalex.org/W3035396860","https://openalex.org/W3036543015","https://openalex.org/W3096609285","https://openalex.org/W3121020412","https://openalex.org/W3172752666","https://openalex.org/W3177257155","https://openalex.org/W3208645658","https://openalex.org/W4214627427","https://openalex.org/W4283717190","https://openalex.org/W4285131332","https://openalex.org/W4312058704","https://openalex.org/W4312823573","https://openalex.org/W4313172897","https://openalex.org/W4375928714","https://openalex.org/W4382568144","https://openalex.org/W4384519088","https://openalex.org/W4386076400","https://openalex.org/W4390872937","https://openalex.org/W4390873750","https://openalex.org/W4393146361","https://openalex.org/W4402702923"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"advancements":[1],"in":[2,24,33,73],"Transformer-based":[3],"detectors":[4,15],"for":[5,109],"small":[6],"object":[7],"detection":[8],"(SOD),":[9],"recent":[10],"studies":[11],"show":[12],"that":[13],"these":[14],"still":[16],"face":[17],"challenges":[18],"due":[19],"to":[20],"inherent":[21],"noise":[22,69],"sensitivity":[23],"feature":[25,71],"pyramid":[26],"networks":[27],"(FPN)":[28],"and":[29,59,78,103],"diminished":[30],"query":[31],"quality":[32],"existing":[34,83],"label":[35,84],"assignment":[36,85],"strategies.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,89],"novel":[44],"Noise-Resilient":[45],"Query":[46],"Optimization":[47],"(NRQO)":[48],"paradigm,":[49],"which":[50],"innovatively":[51],"incorporates":[52],"the":[53,60,107,119],"Noise-Tolerance":[54],"Feature":[55],"Pyramid":[56],"Network":[57,64],"(NT-FPN)":[58],"Pairwise-Similarity":[61],"Region":[62],"Proposal":[63],"(PS-RPN).":[65],"Specifically,":[66],"NTFPN":[67],"mitigates":[68],"during":[70],"fusion":[72],"FPN":[74],"by":[75,96],"preserving":[76],"spatial":[77],"semantic":[79],"information":[80],"integrity.":[81],"Unlike":[82],"strategies,":[86],"PS-RPN":[87],"generates":[88],"sufficient":[90],"number":[91],"of":[92,121],"high-quality":[93],"positive":[94],"queries":[95],"enhancing":[97],"anchor-ground":[98],"truth":[99],"matching":[100],"through":[101],"position":[102],"shape":[104],"similarities,":[105],"without":[106],"need":[108],"additional":[110],"hyperparameters.":[111],"Extensive":[112],"experiments":[113],"on":[114],"multiple":[115],"benchmarks":[116],"consistently":[117],"demonstrate":[118],"superiority":[120],"NRQO":[122],"over":[123],"state-of-the-art":[124],"baselines.":[125]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-30T00:00:00"}