{"id":"https://openalex.org/W4392255648","doi":"https://doi.org/10.1145/3633637.3633663","title":"Small Object Detection with YOLOv8 Algorithm Enhanced by MobileViTv3 and Wise-IoU","display_name":"Small Object Detection with YOLOv8 Algorithm Enhanced by MobileViTv3 and Wise-IoU","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4392255648","doi":"https://doi.org/10.1145/3633637.3633663"},"language":"en","primary_location":{"id":"doi:10.1145/3633637.3633663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3633637.3633663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Computing and Pattern Recognition","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/A5061421715","display_name":"W. J. Wang","orcid":"https://orcid.org/0009-0001-8008-7825"},"institutions":[{"id":"https://openalex.org/I74485261","display_name":"Shandong Agricultural University","ror":"https://ror.org/02ke8fw32","country_code":"CN","type":"education","lineage":["https://openalex.org/I74485261"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wencheng Wang","raw_affiliation_strings":["Shandong Agricultural University, China"],"raw_orcid":"https://orcid.org/0009-0001-8008-7825","affiliations":[{"raw_affiliation_string":"Shandong Agricultural University, China","institution_ids":["https://openalex.org/I74485261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047336800","display_name":"Wenxin Liu","orcid":"https://orcid.org/0009-0004-7194-4436"},"institutions":[{"id":"https://openalex.org/I74485261","display_name":"Shandong Agricultural University","ror":"https://ror.org/02ke8fw32","country_code":"CN","type":"education","lineage":["https://openalex.org/I74485261"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Liu","raw_affiliation_strings":["Shandong Agricultural University, China"],"raw_orcid":"https://orcid.org/0009-0004-7194-4436","affiliations":[{"raw_affiliation_string":"Shandong Agricultural University, China","institution_ids":["https://openalex.org/I74485261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74485261"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"180"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9922999739646912,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728182673454285},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.72523432970047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6088691353797913},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5392635464668274},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5304645299911499},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4714542329311371},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46245265007019043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4276387691497803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4129159450531006},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34735506772994995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728182673454285},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.72523432970047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6088691353797913},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5392635464668274},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5304645299911499},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4714542329311371},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46245265007019043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4276387691497803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4129159450531006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34735506772994995},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3633637.3633663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3633637.3633663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Computing and Pattern Recognition","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":9,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2193145675","https://openalex.org/W2962749812","https://openalex.org/W3106250896","https://openalex.org/W3209586559","https://openalex.org/W4210904973","https://openalex.org/W4396222384","https://openalex.org/W6600503824","https://openalex.org/W6696711281"],"related_works":["https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2969228573","https://openalex.org/W2963690996","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Small":[0],"object":[1,46,166],"detection":[2,47,82,167,176],"is":[3,76],"an":[4,72,126],"important":[5],"and":[6,23,35,68,100,112,115,131,136,146,149],"challenging":[7],"task":[8],"in":[9,15,133,168],"computer":[10],"vision,":[11],"with":[12],"widespread":[13],"applications":[14],"fields":[16],"such":[17,29,59],"as":[18,30,60],"remote":[19,142],"sensing,":[20],"autonomous":[21],"driving,":[22],"security.":[24],"However,":[25],"due":[26],"to":[27,51,154],"factors":[28],"small":[31,39,54,85,165],"size,":[32],"indistinct":[33],"features,":[34],"complex":[36,169],"backgrounds":[37],"of":[38,84,110,128,164],"objects,":[40],"traditional":[41],"convolutional":[42],"neural":[43],"network":[44],"(CNN)-based":[45],"algorithms":[48],"often":[49],"struggle":[50],"effectively":[52,160],"detect":[53],"objects.":[55],"To":[56],"address":[57],"issues":[58],"insufficient":[61],"feature":[62,97],"extraction,":[63],"suboptimal":[64],"anchor":[65],"box":[66],"matching,":[67],"unbalanced":[69],"loss":[70,103],"functions,":[71],"improved":[73,122],"YOLOv8":[74,123],"algorithm":[75,79,124],"proposed.":[77],"This":[78],"enhances":[80],"the":[81,108,121,140,155,162,173],"accuracy":[83,163],"objects":[86],"by":[87],"adding":[88],"a":[89,101],"lightweight":[90],"visual":[91],"transformer,":[92],"MobileViTv3,":[93],"which":[94],"can":[95,159],"enhance":[96],"representation":[98],"capabilities,":[99],"Wise-IoU":[102],"function":[104],"that":[105,120],"adaptively":[106],"adjusts":[107],"ratio":[109],"positive":[111],"negative":[113],"samples":[114],"regression":[116],"coefficients.":[117],"Results":[118],"show":[119],"achieves":[125],"increase":[127],"2.5%,":[129],"2.1%,":[130],"2.9%":[132],"precision,":[134],"recall,":[135],"mAP":[137],"respectively":[138],"on":[139,151],"public":[141],"sensing":[143],"dataset":[144],"VisDrone2019":[145],"2.4%,":[147],"2.7%,":[148],"3.5%":[150],"DOTA":[152],"compared":[153],"original":[156],"algorithm.":[157],"It":[158],"improve":[161],"scenarios":[170],"while":[171],"meeting":[172],"requirements":[174],"for":[175],"speed.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}