{"id":"https://openalex.org/W4416136964","doi":"https://doi.org/10.1109/ipta66025.2025.11222046","title":"A Frequency-Augmented CBAM Attention-Aided YOLOv8 for Object Detection","display_name":"A Frequency-Augmented CBAM Attention-Aided YOLOv8 for Object Detection","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4416136964","doi":"https://doi.org/10.1109/ipta66025.2025.11222046"},"language":null,"primary_location":{"id":"doi:10.1109/ipta66025.2025.11222046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","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":"Sayani Dhar","orcid":null},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sayani Dhar","raw_affiliation_strings":["Jadavpur University,Department of CSE,Kolkata,India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University,Department of CSE,Kolkata,India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000595674","display_name":"Sourajit Maity","orcid":"https://orcid.org/0000-0001-5880-0930"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourajit Maity","raw_affiliation_strings":["Jadavpur University,Department of CSE,Kolkata,India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University,Department of CSE,Kolkata,India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004225243","display_name":"Asfak Ali","orcid":"https://orcid.org/0000-0002-4034-1956"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asfak Ali","raw_affiliation_strings":["Jadavpur University,Department of ETCE,Kolkata,India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University,Department of ETCE,Kolkata,India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054967047","display_name":"Dmitrii Kaplun","orcid":"https://orcid.org/0000-0003-2765-4509"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dmitrii Kaplun","raw_affiliation_strings":["China University of Mining and Technology,Artificial Intelligence Research Institute,Xuzhou,China"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,Artificial Intelligence Research Institute,Xuzhou,China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116138941","display_name":"Daria Sidorina","orcid":"https://orcid.org/0009-0005-7625-161X"},"institutions":[{"id":"https://openalex.org/I41518628","display_name":"Saint Petersburg State Electrotechnical University","ror":"https://ror.org/023bq8521","country_code":"RU","type":"education","lineage":["https://openalex.org/I41518628"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Daria Sidorina","raw_affiliation_strings":["Intelligent Devices Institute,Saint Petersburg Electrotechnical University &#x201C;LETI&#x201D;,St. Petersburg,Russia"],"affiliations":[{"raw_affiliation_string":"Intelligent Devices Institute,Saint Petersburg Electrotechnical University &#x201C;LETI&#x201D;,St. Petersburg,Russia","institution_ids":["https://openalex.org/I41518628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082599641","display_name":"Ram Sarkar","orcid":"https://orcid.org/0000-0001-8813-4086"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ram Sarkar","raw_affiliation_strings":["Jadavpur University,Department of CSE,Kolkata,India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University,Department of CSE,Kolkata,India","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170979836"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32894271,"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":0.9322999715805054,"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":0.9322999715805054,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.005100000184029341,"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":0.7504000067710876},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6342999935150146},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.553600013256073},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7504000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656000018119812},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215000152587891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5932999849319458},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipta66025.2025.11222046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2963857746","https://openalex.org/W3042011474","https://openalex.org/W4210598935","https://openalex.org/W4362703401","https://openalex.org/W4381053586","https://openalex.org/W4387824248","https://openalex.org/W4389049926","https://openalex.org/W4390638513","https://openalex.org/W4392425776","https://openalex.org/W4405475687","https://openalex.org/W4405870498","https://openalex.org/W4407277378","https://openalex.org/W4407310382","https://openalex.org/W4408534152","https://openalex.org/W4408594471","https://openalex.org/W4409180546"],"related_works":[],"abstract_inverted_index":{"This":[0],"research":[1],"proposes":[2],"an":[3,51],"improved":[4],"object":[5],"detection":[6,100],"framework":[7],"by":[8],"integrating":[9],"a":[10,59],"Frequency-Augmented":[11],"Convolutional":[12],"Block":[13],"Attention":[14],"Module":[15],"(FCBAM)":[16],"into":[17],"the":[18,41,69,74,109,114],"YOLOv8":[19,111],"(You":[20],"Only":[21],"Look":[22],"Once":[23],"version":[24],"8)":[25],"architecture.":[26],"By":[27],"incorporating":[28],"frequency":[29],"domain":[30],"information,":[31],"FCBAM":[32],"enhances":[33],"both":[34],"spatial":[35],"and":[36,92,96,139],"channel":[37],"attention":[38,54],"mechanisms,":[39],"enabling":[40],"model":[42],"to":[43,64],"focus":[44],"more":[45],"effectively":[46],"on":[47,129,137,141],"informative":[48],"regions":[49],"within":[50],"image.":[52],"The":[53,71],"module":[55],"is":[56,77],"embedded":[57],"in":[58,101],"critical":[60],"component":[61],"of":[62,73,122],"YOLOv8-Head":[63],"analyze":[65],"its":[66],"impact":[67],"across":[68],"network.":[70],"effectiveness":[72],"proposed":[75],"approach":[76],"evaluated":[78],"using":[79],"three":[80],"diverse":[81],"domain-specific":[82],"datasets:":[83],"ADCOS":[84],"for":[85,90,98],"aerial":[86],"aircraft":[87],"detection,":[88],"BRSTD":[89],"traffic":[91],"business":[93],"sign":[94],"recognition,":[95],"IRUVD":[97],"vehicle":[99],"Indian":[102],"road":[103],"conditions.":[104],"Experimental":[105],"results":[106],"demonstrate":[107],"that":[108],"FCBAM-enhanced":[110],"consistently":[112],"outperforms":[113],"baseline,":[115],"achieving":[116],"mean":[117],"Average":[118],"Precision":[119],"(mAP@0.5)":[120],"scores":[121],"<tex":[123,131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{0.":[125,133],"9":[126,127,134],"1}$</tex>":[128],"BRSTD,":[130],"5":[135],"3}$</tex>":[136],"ADCOS,":[138],"0.945":[140],"IRUVD.":[142]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-10T00:00:00"}