{"id":"https://openalex.org/W4415536811","doi":"https://doi.org/10.1145/3746027.3755045","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","display_name":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536811","doi":"https://doi.org/10.1145/3746027.3755045"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086034520","display_name":"Guiping Cao","orcid":"https://orcid.org/0000-0002-0682-2158"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiping Cao","raw_affiliation_strings":["RITAS, Southern University of Science and Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0682-2158","affiliations":[{"raw_affiliation_string":"RITAS, Southern University of Science and Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055543314","display_name":"Xiangyuan Lan","orcid":"https://orcid.org/0000-0001-8564-0346"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyuan Lan","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China and Pazhou Laboratory (Huangpu), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8564-0346","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China and Pazhou Laboratory (Huangpu), Guangzhou, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060307752","display_name":"Wenjian Huang","orcid":"https://orcid.org/0000-0003-2408-8302"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjian Huang","raw_affiliation_strings":["RITAS, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2408-8302","affiliations":[{"raw_affiliation_string":"RITAS, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461783","display_name":"Jianguo Zhang","orcid":"https://orcid.org/0000-0001-9317-0268"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Zhang","raw_affiliation_strings":["RITAS and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9317-0268","affiliations":[{"raw_affiliation_string":"RITAS and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073082132","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0002-6110-4036"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6110-4036","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9883000254631042,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9686999917030334,"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":0.6205999851226807},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5307000279426575},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5217999815940857},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4185999929904938},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4171999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428000211715698},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6205999851226807},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5217999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903999865055084},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4185999929904938},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C185588885","wikidata":"https://www.wikidata.org/wiki/Q7553811","display_name":"Soft-decision decoder","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.19807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19807","pdf_url":"https://arxiv.org/pdf/2507.19807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19807","pdf_url":"https://arxiv.org/pdf/2507.19807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1470719570","display_name":null,"funder_award_id":"62276121,62402252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2956268511","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W3096609285","https://openalex.org/W3122799380","https://openalex.org/W3138516171","https://openalex.org/W4214627427","https://openalex.org/W4220678948","https://openalex.org/W4302275239","https://openalex.org/W4312312588","https://openalex.org/W4386065740","https://openalex.org/W4390873750"],"related_works":[],"abstract_inverted_index":{"Popular":[0],"transformer":[1],"detectors":[2],"have":[3],"achieved":[4],"promising":[5],"performance":[6],"through":[7,143],"query-based":[8],"learning":[9,48,185],"using":[10],"attention":[11,62,144],"mechanisms.":[12],"However,":[13],"the":[14,47,132,206],"roles":[15],"of":[16,49,109,114,211],"existing":[17],"decoder":[18,71,79,129,141,168],"query":[19,23,184],"types":[20],"(e.g.,":[21],"content":[22],"and":[24,66,86,121,162,166,202,209],"positional":[25],"query)":[26],"are":[27,32,81,216],"still":[28],"underexplored.":[29],"These":[30],"queries":[31],"generally":[33],"predefined":[34],"with":[35,83,149,155],"a":[36,104,111,123,139,173],"fixed":[37],"number":[38,113],"(fixed-query),":[39],"which":[40],"limits":[41],"their":[42],"flexibility.":[43],"We":[44,170],"find":[45],"that":[46,177],"these":[50,99],"fixed-query":[51,133],"is":[52],"impaired":[53],"by":[54],"Recurrent":[55],"Opposing":[56],"in":[57,116],"Teractions":[58],"(ROT)":[59],"between":[60],"two":[61],"operations:":[63],"Self-Attention":[64,156],"(query-to-query)":[65],"Cross-Attention":[67,150],"(query-to-encoder),":[68],"thereby":[69],"degrading":[70],"efficiency.":[72,169],"Furthermore,":[73,136],"\"query":[74],"ambiguity\"":[75],"arises":[76],"when":[77],"shared-weight":[78],"layers":[80],"processed":[82],"both":[84],"one-to-one":[85,94],"one-to-many":[87],"label":[88],"assignments":[89],"during":[90],"training,":[91],"violating":[92],"DETR's":[93],"matching":[95],"principle.":[96],"To":[97],"address":[98],"challenges,":[100],"we":[101,119,137],"propose":[102,138],"DS-Det,":[103],"more":[105],"efficient":[106],"detector":[107],"capable":[108],"detecting":[110],"flexible":[112],"objects":[115],"images.":[117],"Specifically,":[118],"reformulate":[120],"introduce":[122,172],"new":[124],"unified":[125,174],"Single-Query":[126],"paradigm":[127],"for":[128],"modeling,":[130],"transforming":[131],"into":[134],"flexible.":[135],"simplified":[140],"framework":[142],"disentangled":[145],"learning:":[146],"locating":[147],"boxes":[148],"(one-to-many":[151],"process),":[152,158],"deduplicating":[153],"predictions":[154],"(one-to-one":[157],"addressing":[159],"''query":[160],"ambiguity''":[161],"''ROT''":[163],"issues":[164],"directly,":[165],"enhancing":[167],"further":[171],"PoCoo":[175],"loss":[176],"leverages":[178],"box":[179],"size":[180],"priors":[181],"to":[182],"prioritize":[183],"on":[186,200],"hard":[187],"samples":[188],"such":[189],"as":[190],"small":[191],"objects.":[192],"Extensive":[193],"experiments":[194],"across":[195],"five":[196],"different":[197],"backbone":[198],"models":[199],"COCO2017":[201],"WiderPerson":[203],"datasets":[204],"demonstrate":[205],"general":[207],"effectiveness":[208],"superiority":[210],"DS-Det.":[212],"The":[213],"source":[214],"codes":[215],"available":[217],"at":[218],"https://github.com/Med-Process/DS-Det/.":[219]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}