{"id":"https://openalex.org/W3194684992","doi":"https://doi.org/10.23919/mva51890.2021.9511343","title":"Joint Learning of Object Detection and Pose Estimation using Augmented Autoencoder","display_name":"Joint Learning of Object Detection and Pose Estimation using Augmented Autoencoder","publication_year":2021,"publication_date":"2021-07-25","ids":{"openalex":"https://openalex.org/W3194684992","doi":"https://doi.org/10.23919/mva51890.2021.9511343","mag":"3194684992"},"language":"en","primary_location":{"id":"doi:10.23919/mva51890.2021.9511343","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","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/A5110349549","display_name":"Ryota HAYASHI","orcid":null},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryota Hayashi","raw_affiliation_strings":["Toyota Technological Institute, Japan"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Japan","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062346741","display_name":"Asei Shimokura","orcid":null},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asei Shimokura","raw_affiliation_strings":["Toyota Technological Institute, Japan"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Japan","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111571250","display_name":"Takuya Matsumoto","orcid":"https://orcid.org/0000-0002-9286-3115"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Matsumoto","raw_affiliation_strings":["Toyota Technological Institute, Japan"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Japan","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053167635","display_name":"Norimichi Ukita","orcid":"https://orcid.org/0000-0002-0240-1065"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norimichi Ukita","raw_affiliation_strings":["Toyota Technological Institute, Japan"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Japan","institution_ids":["https://openalex.org/I4840577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110349549"],"corresponding_institution_ids":["https://openalex.org/I4840577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10807299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9970999956130981,"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/pose","display_name":"Pose","score":0.8754613995552063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8106721639633179},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.7709243893623352},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7451463937759399},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.7271136045455933},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7143111228942871},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6967705488204956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6601195335388184},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6452081203460693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5427714586257935},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5424926280975342},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5154389142990112},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48774558305740356},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4386652112007141},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2652469575405121},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2478387951850891},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19679662585258484},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08431857824325562}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8754613995552063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8106721639633179},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.7709243893623352},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7451463937759399},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.7271136045455933},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7143111228942871},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6967705488204956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601195335388184},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6452081203460693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5427714586257935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5424926280975342},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5154389142990112},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48774558305740356},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4386652112007141},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2652469575405121},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2478387951850891},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19679662585258484},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08431857824325562},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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:10.23919/mva51890.2021.9511343","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","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":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1909903157","https://openalex.org/W2099606917","https://openalex.org/W2193145675","https://openalex.org/W2574567538","https://openalex.org/W2580726517","https://openalex.org/W2605102758","https://openalex.org/W2613718673","https://openalex.org/W2777195424","https://openalex.org/W2795999188","https://openalex.org/W2797997528","https://openalex.org/W2895439318","https://openalex.org/W2907225497","https://openalex.org/W2909314588","https://openalex.org/W2914868659","https://openalex.org/W2935837427","https://openalex.org/W2949935872","https://openalex.org/W2950921159","https://openalex.org/W2952606116","https://openalex.org/W2953056580","https://openalex.org/W2962783853","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2963927307","https://openalex.org/W2964444661","https://openalex.org/W2981378444","https://openalex.org/W3012573144","https://openalex.org/W3027201070","https://openalex.org/W3034971973","https://openalex.org/W3035217469","https://openalex.org/W3100052745","https://openalex.org/W3103919331","https://openalex.org/W3106250896","https://openalex.org/W3106634005","https://openalex.org/W6620707391","https://openalex.org/W6732350924","https://openalex.org/W6757751764","https://openalex.org/W6760424586","https://openalex.org/W6770600958","https://openalex.org/W6785670581"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W4295519653","https://openalex.org/W4287206000"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,10,19],"method":[4,78,112],"for":[5,98],"estimating":[6],"the":[7,35,49,56,80,84,100,108,118],"pose":[8,16,36,39,73,85,101,120],"of":[9,22,34,110],"rigid":[11],"object.":[12],"While":[13],"an":[14,26],"appearance-based":[15],"estimator":[17,86],"requires":[18],"bounding":[20],"box":[21],"each":[23,96],"target":[24],"object,":[25],"object":[27,50,81],"detector":[28,82],"is":[29,52,62,113],"in":[30],"general":[31],"trained":[32],"independently":[33],"estimator.":[37],"Recent":[38],"estimators":[40],"are":[41],"robust":[42],"to":[43,64,95],"occlusion":[44],"and":[45,68,83,93],"image":[46],"deviation,":[47],"if":[48],"region":[51],"correctly":[53],"located":[54],"by":[55],"detector.":[57],"In":[58],"reality,":[59],"however,":[60],"it":[61],"difficult":[63],"detect":[65],"correct":[66],"bounding-boxes,":[67],"such":[69],"erroneous":[70],"bounding-boxes":[71],"make":[72],"estimation":[74,102,121],"inaccurate.":[75],"Our":[76],"proposed":[77],"integrates":[79],"so":[87],"that":[88,107],"they":[89],"share":[90],"feature":[91],"maps":[92],"support":[94],"other":[97],"improving":[99],"accuracy.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"performance":[109],"our":[111],"7.54":[114],"times":[115],"better":[116],"than":[117],"SoTA":[119],"method.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}