{"id":"https://openalex.org/W4312938499","doi":"https://doi.org/10.1109/icpr56361.2022.9956539","title":"Classification-based Multi-task Learning for Efficient Pose Estimation Network","display_name":"Classification-based Multi-task Learning for Efficient Pose Estimation Network","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312938499","doi":"https://doi.org/10.1109/icpr56361.2022.9956539"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956539","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5101758821","display_name":"Dong\u2010oh Kang","orcid":"https://orcid.org/0000-0002-1308-0172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongoh Kang","raw_affiliation_strings":["Kakao Enterprise"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Enterprise","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069653755","display_name":"Myung-Cheol Roh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Myung-Cheol Roh","raw_affiliation_strings":["Kakao Enterprise"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Enterprise","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074151814","display_name":"Hansaem Kim","orcid":"https://orcid.org/0000-0003-1024-4052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansaem Kim","raw_affiliation_strings":["Kakao Enterprise"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Enterprise","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101780915","display_name":"Yonghyun Kim","orcid":"https://orcid.org/0000-0003-0038-7850"},"institutions":[{"id":"https://openalex.org/I26653445","display_name":"Tellabs (Canada)","ror":"https://ror.org/051gaae98","country_code":"CA","type":"company","lineage":["https://openalex.org/I26653445","https://openalex.org/I4210142238"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yonghyun Kim","raw_affiliation_strings":["GaussLabs Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GaussLabs Inc","institution_ids":["https://openalex.org/I26653445"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"3295","last_page":"3302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.8041654229164124},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7512352466583252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6770723462104797},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6348360776901245},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5978853106498718},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5632053017616272},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4821445643901825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45821115374565125},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.447086364030838},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44644901156425476},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43578264117240906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3338346481323242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041654229164124},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7512352466583252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6770723462104797},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6348360776901245},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5978853106498718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5632053017616272},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4821445643901825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45821115374565125},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.447086364030838},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44644901156425476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43578264117240906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3338346481323242},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956539","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":61,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1973181164","https://openalex.org/W1994529670","https://openalex.org/W2097151019","https://openalex.org/W2102605133","https://openalex.org/W2103015390","https://openalex.org/W2128271252","https://openalex.org/W2128990594","https://openalex.org/W2129169401","https://openalex.org/W2131263044","https://openalex.org/W2143478373","https://openalex.org/W2151103935","https://openalex.org/W2161969291","https://openalex.org/W2163352848","https://openalex.org/W2163605009","https://openalex.org/W2172156083","https://openalex.org/W2175012183","https://openalex.org/W2194775991","https://openalex.org/W2382036597","https://openalex.org/W2476270784","https://openalex.org/W2559085405","https://openalex.org/W2565639579","https://openalex.org/W2578797046","https://openalex.org/W2770121394","https://openalex.org/W2798721181","https://openalex.org/W2819476901","https://openalex.org/W2907137919","https://openalex.org/W2916798096","https://openalex.org/W2952819818","https://openalex.org/W2963150697","https://openalex.org/W2963402313","https://openalex.org/W2964105113","https://openalex.org/W2964221239","https://openalex.org/W2965326519","https://openalex.org/W2982772166","https://openalex.org/W3010526057","https://openalex.org/W3020589396","https://openalex.org/W3034399482","https://openalex.org/W3034750257","https://openalex.org/W3034896527","https://openalex.org/W3097096317","https://openalex.org/W3106250896","https://openalex.org/W3108418701","https://openalex.org/W3113950706","https://openalex.org/W3167976421","https://openalex.org/W3205325544","https://openalex.org/W4289047567","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6679090672","https://openalex.org/W6684191040","https://openalex.org/W6709775842","https://openalex.org/W6730410022","https://openalex.org/W6750378959","https://openalex.org/W6757658208","https://openalex.org/W6757733370","https://openalex.org/W6774556237","https://openalex.org/W6785652829","https://openalex.org/W6793094608"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W4387968151","https://openalex.org/W2055243143","https://openalex.org/W4386925306","https://openalex.org/W3132124459","https://openalex.org/W2946083937","https://openalex.org/W2894986065","https://openalex.org/W4299867837"],"abstract_inverted_index":{"Human":[0],"pose":[1],"estimation":[2,79],"is":[3],"an":[4],"interesting":[5],"and":[6,16,34,62,77,99,103,147],"underlying":[7],"topic":[8],"in":[9,32,142],"various":[10],"fields":[11],"such":[12],"as":[13],"action":[14],"recognition":[15],"human-computer":[17],"interaction.":[18],"Although":[19],"many":[20],"methods":[21],"have":[22],"been":[23],"developed":[24],"recently,":[25],"they":[26],"are":[27],"still":[28],"far":[29],"from":[30],"perfect":[31],"accuracy":[33,61],"speed":[35],"at":[36],"a":[37,44],"time.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,117,131],"propose":[43],"Classification-based":[45],"Pose":[46],"Estimation":[47],"Network":[48,93],"with":[49],"Multi-task":[50],"Learning":[51],"(CPENML)":[52],"based":[53,81],"on":[54,82,121,139],"the":[55,90,101,111,114,122,133],"low-resolution":[56],"feature":[57,97],"map":[58],"to":[59,106,129],"improve":[60],"inference":[63,145],"time":[64,146],"simultaneously.":[65],"The":[66],"proposed":[67,75,91,115,126,137],"CPENML":[68],"consists":[69],"of":[70,113,135,144],"two":[71],"ideas.":[72,127],"Firstly,":[73],"novel":[74],"keypoint":[76,102],"offset":[78,104],"tasks":[80,105],"classification":[83],"achieve":[84],"better":[85],"performance":[86],"than":[87],"regression.":[88],"Secondly,":[89],"Multi-Scale":[92],"(MSN)":[94],"makes":[95],"robust":[96],"maps":[98],"balances":[100],"maximize":[107],"performance.":[108],"To":[109],"prove":[110],"effectiveness":[112],"method,":[116],"conduct":[118],"ablation":[119],"studies":[120],"COCO":[123,140],"dataset":[124,141],"for":[125],"Compared":[128],"benchmarks,":[130],"demonstrate":[132],"superiority":[134],"our":[136],"method":[138],"terms":[143],"accuracy.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}