{"id":"https://openalex.org/W2896991173","doi":"https://doi.org/10.1109/tcsvt.2018.2875449","title":"Multi-Scale Attention Deep Neural Network for Fast Accurate Object Detection","display_name":"Multi-Scale Attention Deep Neural Network for Fast Accurate Object Detection","publication_year":2018,"publication_date":"2018-10-11","ids":{"openalex":"https://openalex.org/W2896991173","doi":"https://doi.org/10.1109/tcsvt.2018.2875449","mag":"2896991173"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2018.2875449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2018.2875449","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5018410836","display_name":"Kaiyou Song","orcid":"https://orcid.org/0000-0001-8999-2680"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyou Song","raw_affiliation_strings":["State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8999-2680","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004324946","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0002-5430-5630"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yang","raw_affiliation_strings":["State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-5430-5630","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053892414","display_name":"Zhouping Yin","orcid":"https://orcid.org/0000-0001-5766-2337"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouping Yin","raw_affiliation_strings":["State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6501,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.9298868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"29","issue":"10","first_page":"2972","last_page":"2985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955999851226807,"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":0.9955000281333923,"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/pascal","display_name":"Pascal (unit)","score":0.8477813005447388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8097206950187683},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6766614317893982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6745261549949646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6193235516548157},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48854193091392517},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42653200030326843},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4114637076854706},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4050765931606293}],"concepts":[{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.8477813005447388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097206950187683},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6766614317893982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6745261549949646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6193235516548157},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48854193091392517},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42653200030326843},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4114637076854706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4050765931606293},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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:10.1109/tcsvt.2018.2875449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2018.2875449","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2840902503","display_name":null,"funder_award_id":"51475193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3585931114","display_name":null,"funder_award_id":"51875228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7298260633","display_name":null,"funder_award_id":"51327801","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":61,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1533861849","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1817277359","https://openalex.org/W1861492603","https://openalex.org/W1976977741","https://openalex.org/W1994488211","https://openalex.org/W2029535991","https://openalex.org/W2031031248","https://openalex.org/W2037227137","https://openalex.org/W2088049833","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2161969291","https://openalex.org/W2164598857","https://openalex.org/W2168356304","https://openalex.org/W2194775991","https://openalex.org/W2221625691","https://openalex.org/W2288122362","https://openalex.org/W2295107390","https://openalex.org/W2428342532","https://openalex.org/W2527917904","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2579985080","https://openalex.org/W2600889608","https://openalex.org/W2601564443","https://openalex.org/W2624650145","https://openalex.org/W2737725206","https://openalex.org/W2738982359","https://openalex.org/W2764012408","https://openalex.org/W2765268259","https://openalex.org/W2767566874","https://openalex.org/W2773003563","https://openalex.org/W2791866340","https://openalex.org/W2950800384","https://openalex.org/W2962891704","https://openalex.org/W2962917547","https://openalex.org/W2963016543","https://openalex.org/W2963037989","https://openalex.org/W2963068995","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963446712","https://openalex.org/W2963495494","https://openalex.org/W2963516811","https://openalex.org/W2963604034","https://openalex.org/W2963786238","https://openalex.org/W2963795442","https://openalex.org/W2963813458","https://openalex.org/W2964350391","https://openalex.org/W3106250896","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6694260854","https://openalex.org/W6714138976","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Object":[0],"detection":[1,36,66,143,216,229],"remains":[2],"a":[3,41,45,57,75,88,214,220],"challenging":[4,199],"task":[5],"in":[6,16,52],"computer":[7],"vision":[8],"due":[9],"to":[10,82,103,112,125,158,177,182],"the":[11,17,95,99,105,116,128,133,138,142,146,149,184,189,198,227],"tremendous":[12],"extent":[13],"of":[14,19,98,109,132],"changes":[15],"appearances":[18],"objects":[20,163],"caused":[21],"by":[22,137,153],"clustered":[23],"backgrounds,":[24],"occlusion,":[25],"truncation,":[26],"and":[27,44,160,206],"scale":[28],"change.":[29],"Current":[30],"deep":[31],"neural":[32],"network":[33],"(DNN)-based":[34],"object":[35,65],"methods":[37],"cannot":[38],"simultaneously":[39],"achieve":[40],"high":[42,46,68,221],"accuracy":[43,217],"efficiency.":[47,69,222],"To":[48],"overcome":[49],"this":[50,53],"limitation,":[51],"paper,":[54],"we":[55],"propose":[56],"novel":[58,76,89],"multi-scale":[59,77],"attention":[60],"(MSA)":[61],"DNN":[62],"for":[63],"accurate":[64],"with":[67],"The":[70],"proposed":[71],"MSA-DNN":[72,212,224],"method":[73],"utilizes":[74],"feature":[78,130],"fusion":[79],"module":[80,91],"(MSFFM)":[81],"construct":[83],"high-level":[84],"semantic":[85,107,123,129],"features.":[86],"Subsequently,":[87],"MSA":[90,150],"(MSAM)":[92],"based":[93],"on":[94,197],"fused":[96,134],"layers":[97,135],"MSFFM":[100],"is":[101,175],"introduced":[102,176],"exploit":[104],"global":[106,122],"information":[108,124],"image-level":[110],"labels":[111],"guide":[113],"detection.":[114],"On":[115,145],"one":[117],"hand,":[118,148],"MSAM":[119,154],"can":[120,155],"capture":[121],"further":[126],"enhance":[127],"representation":[131],"constructed":[136],"MSFFM,":[139],"thereby":[140],"improving":[141],"accuracy.":[144,230],"other":[147],"maps":[151],"generated":[152],"be":[156],"employed":[157],"rapidly":[159],"coarsely":[161],"locate":[162],"at":[164],"different":[165],"scales.":[166],"In":[167],"addition,":[168],"an":[169],"attention-based":[170],"hard":[171],"negative":[172,180],"mining":[173],"strategy":[174],"filter":[178],"out":[179],"samples":[181],"reduce":[183],"search":[185],"space,":[186],"dramatically":[187],"alleviating":[188],"severe":[190],"class":[191],"imbalance":[192],"problem.":[193],"Extensive":[194],"experimental":[195],"results":[196],"PASCAL":[200,203],"VOC":[201,204],"2007,":[202],"2012,":[205],"MS":[207],"COCO":[208],"datasets":[209],"demonstrate":[210],"that":[211],"achieves":[213],"state-of-the-art":[215],"while":[218],"maintaining":[219],"Furthermore,":[223],"significantly":[225],"improves":[226],"small-object":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}