{"id":"https://openalex.org/W4415708434","doi":"https://doi.org/10.1109/icme59968.2025.11208976","title":"DCGNet: Detail and Context Guided Small Object Detection Network with Decoupled Detection Head","display_name":"DCGNet: Detail and Context Guided Small Object Detection Network with Decoupled Detection Head","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708434","doi":"https://doi.org/10.1109/icme59968.2025.11208976"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208976","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":"https://openalex.org/A5063170090","display_name":"Yixin Qiao","orcid":"https://orcid.org/0000-0001-6387-3130"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yixin Qiao","raw_affiliation_strings":["Sichuan University,College of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032662894","display_name":"Shiyong Lan","orcid":"https://orcid.org/0000-0002-7109-9170"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyong Lan","raw_affiliation_strings":["Sichuan University,College of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Center for Vision Speech and Signal Processing,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Center for Vision Speech and Signal Processing,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019550571","display_name":"Haohan Chen","orcid":"https://orcid.org/0009-0008-5658-4507"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohan Chen","raw_affiliation_strings":["Sichuan University,College of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083870206","display_name":"Y Li","orcid":"https://orcid.org/0009-0004-8157-7019"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Li","raw_affiliation_strings":["Sichuan University,College of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guonan Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guonan Deng","raw_affiliation_strings":["Sichuan University,College of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063170090"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30376238,"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":0.8823000192642212,"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":0.8823000192642212,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.043299999088048935,"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":0.02070000022649765,"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":0.7483999729156494},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6567000150680542},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6241999864578247},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6114000082015991},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5609999895095825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5044999718666077},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48260000348091125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4616999924182892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7483999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6920999884605408},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5612999796867371},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48260000348091125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.26919999718666077},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.267300009727478}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208976","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"},{"id":"https://openalex.org/F4320322990","display_name":"Sichuan University","ror":"https://ror.org/011ashp19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2017745767","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2952122856","https://openalex.org/W2982220924","https://openalex.org/W2982770724","https://openalex.org/W2989676862","https://openalex.org/W2996735448","https://openalex.org/W2997408160","https://openalex.org/W3035396860","https://openalex.org/W3117876421","https://openalex.org/W3160733999","https://openalex.org/W3175630421","https://openalex.org/W3177257155","https://openalex.org/W3185980597","https://openalex.org/W3208645658","https://openalex.org/W4283717190","https://openalex.org/W4289752563","https://openalex.org/W4303982397","https://openalex.org/W4308119868","https://openalex.org/W4313172897","https://openalex.org/W4372260606","https://openalex.org/W4386065740","https://openalex.org/W4386596831","https://openalex.org/W4396605538","https://openalex.org/W4402177704","https://openalex.org/W4402402063","https://openalex.org/W4404582922"],"related_works":[],"abstract_inverted_index":{"Small":[0,48],"object":[1,165],"detection":[2,154,166],"plays":[3],"a":[4,40,57,117],"significant":[5],"role":[6],"in":[7,156,178],"many":[8],"fields,":[9],"yet":[10],"it":[11],"still":[12],"faces":[13],"numerous":[14],"challenges.":[15],"These":[16],"include":[17],"the":[18,68,71,75,87,112,126,145,148,162],"lack":[19],"of":[20,90,144,147],"key":[21],"features":[22,128,146],"due":[23],"to":[24,31,85,101,106],"its":[25,29],"tiny":[26],"size,":[27],"and":[28,45,59,93,132,142,169,183],"sensitivity":[30],"environmental":[32],"noise.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"we":[38,55],"introduce":[39],"novel":[41],"network":[42],"termed":[43],"Detail":[44,58],"Context":[46,60],"Guided":[47],"Object":[49],"Detection":[50],"Network":[51,64],"(DCGNet).":[52],"Specifically,":[53],"1)":[54],"design":[56],"Enhanced":[61,118],"Feature":[62],"Pyramid":[63],"(DCE-FPN),":[65],"which":[66],"transforms":[67],"feature":[69,136],"from":[70,111],"temporal":[72],"domain":[73],"into":[74],"frequency":[76],"domain,":[77],"followed":[78],"by":[79],"noise":[80],"reduction":[81],"on":[82,161],"high-frequency":[83],"components":[84],"accentuate":[86],"detailed":[88],"information":[89,105],"small":[91,109,149,164,187],"objects":[92,110,150,188],"leverages":[94],"multiple":[95],"branches":[96],"with":[97,152],"different":[98],"receptive":[99],"fields":[100],"capture":[102],"multi-scale":[103],"contextual":[104],"further":[107],"differentiate":[108],"background.":[113],"2)":[114],"We":[115],"propose":[116],"Decoupled":[119],"Interaction":[120],"RCNN":[121],"(EDI-RCNN)":[122],"that":[123,172],"independently":[124],"enhances":[125],"specific":[127],"for":[129,186],"each":[130],"task":[131],"subsequently":[133],"facilitates":[134],"comprehensive":[135],"interaction.":[137],"This":[138],"helps":[139],"avoid":[140],"ambiguity":[141],"sparsity":[143],"extracted":[151],"coupled":[153],"head":[155],"existing":[157],"methods.":[158],"The":[159],"results":[160],"well-known":[163],"datasets":[167],"(VisDrone2019":[168],"AI-TODv2)":[170],"show":[171],"our":[173],"proposed":[174],"method":[175],"achieves":[176],"SOTA":[177],"both":[179],"Average":[180,184],"Precision":[181,185],"(AP)":[182],"(APs)":[189],"metrics.":[190]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-30T00:00:00"}