{"id":"https://openalex.org/W3174214845","doi":"https://doi.org/10.1109/tro.2022.3204509","title":"Multimodal Learning of Keypoint Predictive Models for Visual Object Manipulation","display_name":"Multimodal Learning of Keypoint Predictive Models for Visual Object Manipulation","publication_year":2023,"publication_date":"2023-01-20","ids":{"openalex":"https://openalex.org/W3174214845","doi":"https://doi.org/10.1109/tro.2022.3204509","mag":"3174214845"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2022.3204509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2022.3204509","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Robotics","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/A5090921029","display_name":"Sarah Bechtle","orcid":"https://orcid.org/0000-0002-1705-3147"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sarah Bechtle","raw_affiliation_strings":["DeepMind, London, U.K"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045156654","display_name":"Neha Das","orcid":"https://orcid.org/0000-0001-7819-0383"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neha Das","raw_affiliation_strings":["Meta AI Research, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI Research, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071976030","display_name":"Franziska Meier","orcid":"https://orcid.org/0000-0003-1640-4619"},"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":"Franziska Meier","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090921029"],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":0.9391,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73045569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"39","issue":"2","first_page":"1212","last_page":"1224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9984999895095825,"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":0.9970999956130981,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7952083945274353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011846303939819},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6980699896812439},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6497313976287842},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6493417024612427},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6050834655761719},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5165637731552124},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4360523223876953},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4150831401348114},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4148164391517639},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4126434028148651},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24337100982666016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0795462429523468}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7952083945274353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011846303939819},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6980699896812439},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6497313976287842},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6493417024612427},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6050834655761719},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5165637731552124},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4360523223876953},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4150831401348114},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4148164391517639},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4126434028148651},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24337100982666016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0795462429523468},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2022.3204509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2022.3204509","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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 Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W155952036","https://openalex.org/W1932061758","https://openalex.org/W1964359788","https://openalex.org/W1977687214","https://openalex.org/W1978224777","https://openalex.org/W1992687061","https://openalex.org/W2000314002","https://openalex.org/W2032121142","https://openalex.org/W2039278485","https://openalex.org/W2066691972","https://openalex.org/W2070338807","https://openalex.org/W2082761562","https://openalex.org/W2082971343","https://openalex.org/W2089098644","https://openalex.org/W2102727145","https://openalex.org/W2113010946","https://openalex.org/W2114474661","https://openalex.org/W2131044714","https://openalex.org/W2131708731","https://openalex.org/W2144913215","https://openalex.org/W2148217105","https://openalex.org/W2155007355","https://openalex.org/W2165033984","https://openalex.org/W2184188583","https://openalex.org/W2213273183","https://openalex.org/W2285644164","https://openalex.org/W2337977475","https://openalex.org/W2537677623","https://openalex.org/W2604698059","https://openalex.org/W2613677041","https://openalex.org/W2639200898","https://openalex.org/W2773276919","https://openalex.org/W2804941773","https://openalex.org/W2888082890","https://openalex.org/W2890290306","https://openalex.org/W2902125520","https://openalex.org/W2913107198","https://openalex.org/W2925241625","https://openalex.org/W2934031659","https://openalex.org/W2957394706","https://openalex.org/W2962960500","https://openalex.org/W2963430173","https://openalex.org/W2963654998","https://openalex.org/W2964067046","https://openalex.org/W2964345931","https://openalex.org/W2967578475","https://openalex.org/W2968095426","https://openalex.org/W2970415880","https://openalex.org/W2971202257","https://openalex.org/W2980999634","https://openalex.org/W2991276239","https://openalex.org/W3008303301","https://openalex.org/W3009343398","https://openalex.org/W3009928773","https://openalex.org/W3011466691","https://openalex.org/W3022259169","https://openalex.org/W3086412568","https://openalex.org/W3098436915","https://openalex.org/W3100818121","https://openalex.org/W3105287169","https://openalex.org/W3106384096","https://openalex.org/W3119978101","https://openalex.org/W3210246279","https://openalex.org/W3210274826","https://openalex.org/W4206297508","https://openalex.org/W4253187718","https://openalex.org/W4297810738","https://openalex.org/W6623316541","https://openalex.org/W6682849425","https://openalex.org/W6686207219","https://openalex.org/W6756908582","https://openalex.org/W6764529735","https://openalex.org/W6765456200","https://openalex.org/W6774494813","https://openalex.org/W6783068448","https://openalex.org/W6784212503"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4387272257"],"abstract_inverted_index":{"Humans":[0],"have":[1],"impressive":[2],"generalization":[3],"capabilities":[4,18],"when":[5],"it":[6],"comes":[7],"to":[8,38,95,140,161],"manipulating":[9],"objects":[10,146],"and":[11,33,91,196,201],"tools":[12],"in":[13,147,166,199],"completely":[14],"novel":[15],"environments.":[16],"These":[17],"are,":[19],"at":[20],"least":[21],"partially,":[22],"a":[23,54,60,170,193],"result":[24],"of":[25,30,112,116,173],"humans":[26],"having":[27],"internal":[28],"models":[29],"their":[31],"bodies":[32],"any":[34],"grasped":[35,165,194],"object.":[36],"How":[37],"learn":[39,109],"such":[40,190],"body":[41],"representations":[42],"for":[43,64,186],"robots":[44],"remains":[45],"an":[46,101,110,157],"open":[47],"problem.":[48],"In":[49],"this":[50,180],"work,":[51],"we":[52,77,104,107,177],"present":[53,78,197],"self-supervised":[55],"learning":[56,94,156],"approach":[57,138],"that":[58,88,136,179],"extends":[59],"robot's":[61],"kinematic":[62,114,159,182],"model":[63],"object":[65,164,187,195],"manipulation":[66,188],"from":[67,123,169],"visual":[68,97,125,143,174],"latent":[69],"representations.":[70],"Our":[71,133],"framework":[72],"comprises":[73],"two":[74],"components:":[75],"First,":[76],"our":[79,129,137],"multimodal":[80,130],"keypoint":[81,131],"detector:":[82],"A":[83],"neural":[84],"network":[85],"autoencoder":[86],"architecture":[87],"fuses":[89],"proprioception":[90],"vision":[92],"during":[93],"predict":[96,142],"key":[98],"points":[99],"on":[100,145,202],"object;":[102],"second,":[103],"show":[105,178],"how":[106],"can":[108,153],"extension":[111],"the":[113,117,124,148,163],"chain":[115,160,183],"robot":[118],"by":[119,128],"regressing":[120],"virtual":[121],"joints":[122],"keypoints":[126,144],"predicted":[127],"detector.":[132],"evaluation":[134],"shows":[135],"learns":[139],"consistently":[141],"manipulator's":[149],"hand":[150],"and,":[151],"thus,":[152],"easily":[154],"facilitate":[155],"extended":[158,181],"include":[162],"various":[167],"configurations,":[168],"few":[171],"seconds":[172],"data.":[175],"Finally,":[176],"lends":[184],"itself":[185],"tasks":[189],"as":[191],"placing":[192],"experiments":[198],"simulation":[200],"hardware.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}