{"id":"https://openalex.org/W4375868910","doi":"https://doi.org/10.1109/icassp49357.2023.10097155","title":"Yolo-Based Lightweight Object Detection With Structure Simplification And Attention Enhancement","display_name":"Yolo-Based Lightweight Object Detection With Structure Simplification And Attention Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868910","doi":"https://doi.org/10.1109/icassp49357.2023.10097155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111952364","display_name":"Shuqi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqi Sun","raw_affiliation_strings":["University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","School of Information Science and Engineering, University of Jinan, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","institution_ids":["https://openalex.org/I34949971"]},{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054830929","display_name":"Xiaohui Yang","orcid":"https://orcid.org/0000-0001-9677-979X"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Yang","raw_affiliation_strings":["University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","School of Information Science and Engineering, University of Jinan, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","institution_ids":["https://openalex.org/I34949971"]},{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060447663","display_name":"Jingliang Peng","orcid":"https://orcid.org/0000-0001-5131-7743"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Peng","raw_affiliation_strings":["University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","School of Information Science and Engineering, University of Jinan, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jinan,Shandong Provincial Key Laboratory of Network Based Intelligent Computing,Jinan,China,250022","institution_ids":["https://openalex.org/I34949971"]},{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I34949971"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9979000091552734,"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":0.9950000047683716,"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/convolution","display_name":"Convolution (computer science)","score":0.8058411478996277},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7906222343444824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216861248016357},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6709675788879395},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6077518463134766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5353124141693115},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49016913771629333},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4792494773864746},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.4714302122592926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4583233594894409},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4503338932991028},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41084933280944824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31166985630989075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11506563425064087},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10835680365562439},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06906566023826599}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.8058411478996277},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7906222343444824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216861248016357},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6709675788879395},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6077518463134766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353124141693115},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49016913771629333},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4792494773864746},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.4714302122592926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4583233594894409},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4503338932991028},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41084933280944824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31166985630989075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11506563425064087},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10835680365562439},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06906566023826599},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2129987527","https://openalex.org/W2179352600","https://openalex.org/W2531409750","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2963163009","https://openalex.org/W2964241181","https://openalex.org/W2982083293","https://openalex.org/W2982220924","https://openalex.org/W2982770724","https://openalex.org/W3012573144","https://openalex.org/W3018757597","https://openalex.org/W3042011474","https://openalex.org/W3102701618","https://openalex.org/W3175148838","https://openalex.org/W3180134609","https://openalex.org/W3184439416","https://openalex.org/W3209766476","https://openalex.org/W4293584584","https://openalex.org/W6679461745","https://openalex.org/W6728184133","https://openalex.org/W6750227808","https://openalex.org/W6753412334","https://openalex.org/W6753494528","https://openalex.org/W6777046832","https://openalex.org/W6782793182","https://openalex.org/W6798838024","https://openalex.org/W6803865744"],"related_works":["https://openalex.org/W3158431807","https://openalex.org/W2530952058","https://openalex.org/W2582836483","https://openalex.org/W4299366318","https://openalex.org/W2964954556","https://openalex.org/W4297580547","https://openalex.org/W2951583185","https://openalex.org/W3019910406","https://openalex.org/W4308155352","https://openalex.org/W2969228573"],"abstract_inverted_index":{"In":[0,114],"this":[1],"paper":[2],"we":[3,42,83],"propose":[4],"a":[5,65,73,95],"lightweight":[6,27],"object":[7],"detector":[8,135],"by":[9,26,61],"optimizing":[10],"the":[11,23,31,36,40,44,56,62,80,85,89,93,101,110,123,133],"structure":[12],"of":[13,64,88],"YOLOv3.":[14],"The":[15],"optimization":[16],"is":[17],"conducted":[18],"in":[19,55,141],"two":[20],"aspects:":[21],"simplifying":[22],"structural":[24],"components":[25],"substitutes":[28],"and":[29,50,59,72,75,104],"introducing":[30],"attention":[32,81,107],"mechanism":[33],"to":[34,92,100,109,122],"increase":[35],"detection":[37,57,112],"accuracy.":[38],"For":[39],"simplification,":[41],"remodel":[43],"backbone":[45,103,125],"based":[46],"on":[47],"MobileNet":[48],"v2":[49],"replace":[51],"every":[52],"3\u00d73":[53,117],"convolution":[54,71,118],"neck":[58],"head":[60],"fusion":[63],"3":[66,68],"\u00d7":[67],"depthwise":[69],"separable":[70],"squeeze":[74],"excitation":[76],"block":[77,99,106],"(DSConv+SE);":[78],"for":[79,126],"enhancement,":[82],"introduce":[84],"high-frequency":[86],"wavelets":[87],"original":[90],"image":[91],"input,":[94],"simplified":[96,102,111,124],"non-":[97],"local":[98,116],"convolutional":[105],"modules":[108],"neck.":[113],"addition,":[115],"branches":[119],"are":[120],"introduced":[121],"enhanced":[127],"learning":[128],"capability.":[129],"Experiments":[130],"demonstrate":[131],"that":[132],"proposed":[134],"outperforms":[136],"each":[137],"compared":[138],"state-of-the-art":[139],"work":[140],"one":[142],"or":[143],"more":[144],"aspects.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}