{"id":"https://openalex.org/W4415401008","doi":"https://doi.org/10.1145/3728424.3760769","title":"An Uncertainty-aware DETR Enhancement Framework for Object Detection","display_name":"An Uncertainty-aware DETR Enhancement Framework for Object Detection","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415401008","doi":"https://doi.org/10.1145/3728424.3760769"},"language":null,"primary_location":{"id":"doi:10.1145/3728424.3760769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728424.3760769","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimedia Computing for Health and Medicine","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3728424.3760769","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089639558","display_name":"X.S. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingshu Chen","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-8200-4909","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104014314","display_name":"Sicheng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sicheng Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-7935-9424","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chong Cheng","orcid":"https://orcid.org/0009-0006-9903-3719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Cheng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-9903-3719","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446112","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3086-3128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3086-3128","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120084661","display_name":"Ting Tian","orcid":"https://orcid.org/0000-0002-7148-5629"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Tian","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7148-5629","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31760933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6998000144958496},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.633400022983551},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6123999953269958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4957999885082245},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3903000056743622},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3898000121116638}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6998000144958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355000138282776},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.633400022983551},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6123999953269958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728424.3760769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728424.3760769","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimedia Computing for Health and Medicine","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3728424.3760769","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728424.3760769","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimedia Computing for Health and Medicine","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1980276039","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2962677013","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2981958729","https://openalex.org/W2990138404","https://openalex.org/W2997747012","https://openalex.org/W3092663126","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3138516171","https://openalex.org/W3176187859","https://openalex.org/W3203003533","https://openalex.org/W4206628887","https://openalex.org/W4214627427","https://openalex.org/W4225570392","https://openalex.org/W4383340328","https://openalex.org/W4386076325","https://openalex.org/W4390629764"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,14,64,68,74,111,142,150],"problem":[4],"of":[5,17,152],"object":[6,52],"detection":[7,94,136,160],"with":[8],"a":[9,84,99],"focus":[10],"on":[11,28,80,110,141],"improving":[12],"both":[13,156],"localization":[15,104],"accuracy":[16],"bounding":[18,30,56],"boxes":[19,57],"and":[20,37,62,76,92,144,158],"explicitly":[21],"modeling":[22],"prediction":[23],"uncertainty.":[24],"Conventional":[25],"detectors":[26],"rely":[27],"deterministic":[29],"box":[31],"regression,":[32],"ignoring":[33],"uncertainty":[34,105],"in":[35],"predictions":[36],"limiting":[38],"model":[39,55],"robustness.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,82],"propose":[45,98],"an":[46],"uncertainty-aware":[47],"enhancement":[48],"framework":[49,133,154],"for":[50],"DETR-based":[51],"detectors.":[53],"We":[54,96,129],"as":[58],"multivariate":[59],"Gaussian":[60],"distributions":[61],"incorporate":[63],"Gromov-Wasserstein":[65],"distance":[66],"into":[67,122],"loss":[69],"function":[70],"to":[71,88,102,134],"better":[72],"align":[73],"predicted":[75],"ground-truth":[77],"distributions.":[78],"Building":[79],"this,":[81],"derive":[83],"Bayes":[85],"Risk":[86],"formulation":[87],"filter":[89],"high-risk":[90],"information":[91],"improve":[93],"reliability.":[95],"also":[97],"simple":[100],"algorithm":[101],"quantify":[103],"via":[106],"confidence":[107],"intervals.":[108],"Experiments":[109],"COCO":[112],"benchmark":[113],"show":[114],"that":[115],"our":[116,132,153],"method":[117],"can":[118],"be":[119],"effectively":[120],"integrated":[121],"existing":[123],"DETR":[124],"variants,":[125],"enhancing":[126],"their":[127],"performance.":[128],"further":[130],"extend":[131],"leukocyte":[135],"tasks,":[137],"achieving":[138],"state-of-the-art":[139],"results":[140,148],"LISC":[143],"WBCDD":[145],"datasets.":[146],"These":[147],"confirm":[149],"scalability":[151],"across":[155],"general":[157],"domain-specific":[159],"tasks.":[161],"Code":[162],"page:":[163],"https://github.com/ParadiseforAndaChen/An-Uncertainty-aware-DETR-Enhancement-Framework-for-Object-Detection.":[164]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-22T00:00:00"}