{"id":"https://openalex.org/W3015777237","doi":"https://doi.org/10.1109/icassp40776.2020.9054600","title":"Towards High-Performance Object Detection: Task-Specific Design Considering Classification and Localization Separation","display_name":"Towards High-Performance Object Detection: Task-Specific Design Considering Classification and Localization Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015777237","doi":"https://doi.org/10.1109/icassp40776.2020.9054600","mag":"3015777237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5036936141","display_name":"Jung Uk Kim","orcid":"https://orcid.org/0000-0003-4533-4875"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jung Uk Kim","raw_affiliation_strings":["Image and Video Systems Lab, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646694","display_name":"Seong Tae Kim","orcid":"https://orcid.org/0000-0002-2132-6021"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Seong Tae Kim","raw_affiliation_strings":["Computer Aided Medical Procedures, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Aided Medical Procedures, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691579","display_name":"Eun Sung Kim","orcid":"https://orcid.org/0000-0001-8567-524X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eun Sung Kim","raw_affiliation_strings":["Image and Video Systems Lab, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057349490","display_name":"Sang-Keun Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I198972184","display_name":"Korea Electric Power Corporation (South Korea)","ror":"https://ror.org/04fperw70","country_code":"KR","type":"company","lineage":["https://openalex.org/I198972184"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Keun Moon","raw_affiliation_strings":["Korea Electric Power Corporation (KEPCO) Research Institute"],"affiliations":[{"raw_affiliation_string":"Korea Electric Power Corporation (KEPCO) Research Institute","institution_ids":["https://openalex.org/I198972184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Lab, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036936141"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.7816,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73541373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4317","last_page":"4321"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7499897480010986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7255964279174805},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7208089232444763},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7124082446098328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.62781822681427},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5963686108589172},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5732727646827698},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5037426352500916},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4979972839355469},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.49478787183761597},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4852335453033447},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4482934772968292},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4376218914985657},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43614354729652405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4144648313522339},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4115833342075348},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16185811161994934},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08013451099395752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499897480010986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7255964279174805},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7208089232444763},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7124082446098328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.62781822681427},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5963686108589172},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5732727646827698},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5037426352500916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4979972839355469},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.49478787183761597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4852335453033447},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4482934772968292},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4376218914985657},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43614354729652405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4144648313522339},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4115833342075348},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16185811161994934},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08013451099395752},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1745334888","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2407521645","https://openalex.org/W2565639579","https://openalex.org/W2579985080","https://openalex.org/W2613718673","https://openalex.org/W2789006728","https://openalex.org/W2886904239","https://openalex.org/W2889698616","https://openalex.org/W2896696305","https://openalex.org/W2899771611","https://openalex.org/W2917092108","https://openalex.org/W2938499953","https://openalex.org/W2950800384","https://openalex.org/W2962731685","https://openalex.org/W2963068995","https://openalex.org/W2963351448","https://openalex.org/W2970252859","https://openalex.org/W3106250896","https://openalex.org/W6620707391","https://openalex.org/W6631782140","https://openalex.org/W6637373629","https://openalex.org/W6637573526","https://openalex.org/W6639102338","https://openalex.org/W6714138976","https://openalex.org/W6732243160","https://openalex.org/W6749076073","https://openalex.org/W6749997223","https://openalex.org/W6755621087","https://openalex.org/W6756040250","https://openalex.org/W6761453060","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Object":[0],"detection":[1,118,161],"performs":[2],"two":[3,28,105],"tasks":[4,10,29],"(classification":[5],"and":[6,102,134,154],"localization)":[7],"simultaneously.":[8],"Two":[9],"share":[11],"a":[12,64,70,77,95,139],"similarity:":[13],"they":[14],"need":[15],"robust":[16],"features":[17,38,54],"that":[18],"effectively":[19],"represent":[20],"the":[21,25,47,56,85,100,115,141,144,158],"visual":[22],"appearance":[23],"of":[24,42,87,99,104,114,143,157],"objects.":[26],"However,":[27],"also":[30],"have":[31],"different":[32],"properties.":[33],"First,":[34],"classification":[35,68],"mainly":[36,52],"requires":[37,53],"from":[39,55],"discriminative":[40],"parts":[41,122],"an":[43],"object":[44,48,58,88,117,160],"to":[45,83,93],"determine":[46],"category,":[49],"whereas":[50,74],"localization":[51,75],"entire":[57],"regions":[59],"for":[60],"localizing":[61],"by":[62,123,150],"drawing":[63],"bounding":[65],"box.":[66],"Second,":[67],"has":[69,76],"translation":[71,78],"invariant":[72],"property,":[73],"variant":[79],"property.":[80],"In":[81,107],"order":[82],"increase":[84],"efficiency":[86],"detection,":[89],"it":[90],"is":[91],"necessary":[92],"design":[94],"network":[96],"in":[97],"consideration":[98],"commonalities":[101],"differences":[103],"tasks.":[106],"this":[108],"work,":[109],"we":[110],"simply":[111],"modified":[112],"layers":[113,156],"existing":[116,159],"networks":[119],"into":[120],"three":[121],"considering":[124],"such":[125],"characteristics:":[126],"lower-layer":[127],"feature":[128,135],"sharing":[129],"part,":[130,133],"layer":[131],"separation":[132],"fusion":[136],"part.":[137],"As":[138],"result,":[140],"performance":[142],"proposed":[145],"method":[146],"was":[147],"noticeably":[148],"improved":[149],"properly":[151],"sharing,":[152],"separating,":[153],"fusing":[155],"networks.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}