{"id":"https://openalex.org/W4401416102","doi":"https://doi.org/10.1109/icra57147.2024.10611409","title":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","display_name":"RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416102","doi":"https://doi.org/10.1109/icra57147.2024.10611409"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5032877928","display_name":"Mel Vecer\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mel Vecerik","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081047759","display_name":"Carl Doersch","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Carl Doersch","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082626279","display_name":"Todor Davchev","orcid":"https://orcid.org/0000-0002-0584-5163"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Todor Davchev","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056410851","display_name":"Yusuf Aytar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yusuf Aytar","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076644778","display_name":"Guangyao Zhou","orcid":"https://orcid.org/0000-0003-0809-5799"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Guangyao Zhou","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079415139","display_name":"Raia Hadsell","orcid":"https://orcid.org/0000-0002-2390-1771"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Raia Hadsell","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079834126","display_name":"Lourdes Agapito","orcid":"https://orcid.org/0000-0002-6947-1092"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lourdes Agapito","raw_affiliation_strings":["University College London,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014848474","display_name":"Jon Scholz","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jon Scholz","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7806,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97794261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5397","last_page":"5403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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":0.9921000003814697,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7640854120254517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7231401205062866},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7166950106620789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6992114782333374},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6112634539604187},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5708552002906799},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4405581057071686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3236537575721741},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05411478877067566},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.051232993602752686}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7640854120254517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231401205062866},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7166950106620789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6992114782333374},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6112634539604187},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5708552002906799},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4405581057071686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3236537575721741},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05411478877067566},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.051232993602752686},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":46,"referenced_works":["https://openalex.org/W12410007","https://openalex.org/W1903029394","https://openalex.org/W1971662204","https://openalex.org/W2011792403","https://openalex.org/W2043547879","https://openalex.org/W2117228865","https://openalex.org/W2124313187","https://openalex.org/W2124386111","https://openalex.org/W2151103935","https://openalex.org/W2171066085","https://openalex.org/W2810785043","https://openalex.org/W2811406147","https://openalex.org/W2963188159","https://openalex.org/W2963863119","https://openalex.org/W2985205035","https://openalex.org/W3006398608","https://openalex.org/W3012366945","https://openalex.org/W3037784242","https://openalex.org/W3040490156","https://openalex.org/W3090584485","https://openalex.org/W3092822745","https://openalex.org/W3174364619","https://openalex.org/W3203511201","https://openalex.org/W4210700398","https://openalex.org/W4225643926","https://openalex.org/W4250325771","https://openalex.org/W4285102245","https://openalex.org/W4312241108","https://openalex.org/W4312326540","https://openalex.org/W4323640751","https://openalex.org/W4383097638","https://openalex.org/W4385430679","https://openalex.org/W4386066268","https://openalex.org/W4390871749","https://openalex.org/W4390872749","https://openalex.org/W6600496096","https://openalex.org/W6760546089","https://openalex.org/W6779809370","https://openalex.org/W6784173345","https://openalex.org/W6784212503","https://openalex.org/W6793567207","https://openalex.org/W6796242396","https://openalex.org/W6801810553","https://openalex.org/W6803376173","https://openalex.org/W6803891570","https://openalex.org/W6846523392"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2074502265"],"abstract_inverted_index":{"For":[0],"robots":[1],"to":[2,14,27,39,62,77,90],"be":[3,136],"useful":[4,18],"outside":[5],"labs":[6],"and":[7,65,85,118,127],"specialized":[8],"factories":[9],"we":[10,54],"need":[11],"a":[12,59,83,87],"way":[13],"teach":[15],"them":[16],"new":[17,29],"behaviors":[19],"quickly.":[20],"Current":[21],"approaches":[22],"lack":[23,36],"either":[24],"the":[25,37,79,97],"generality":[26],"onboard":[28],"tasks":[30,113,122],"without":[31],"task-specific":[32],"engineering,":[33],"or":[34],"else":[35],"data-efficiency":[38],"do":[40],"so":[41],"in":[42,82,96,104,138],"an":[43],"amount":[44],"of":[45],"time":[46],"that":[47,108,134],"enables":[48],"practical":[49],"use.":[50],"In":[51],"this":[52,92,102],"work":[53],"explore":[55],"dense":[56],"tracking":[57],"as":[58,115,124],"representational":[60],"vehicle":[61],"allow":[63],"faster":[64],"more":[66],"general":[67],"learning":[68],"from":[69,132],"demonstration.":[70],"Our":[71],"approach":[72],"utilizes":[73],"Track-Any-Point":[74],"(TAP)":[75],"models":[76],"isolate":[78],"relevant":[80],"motion":[81,93],"demonstration,":[84],"parameterize":[86],"low-level":[88],"controller":[89],"reproduce":[91],"across":[94],"changes":[95],"scene":[98],"configuration.":[99],"We":[100],"show":[101],"results":[103],"robust":[105],"robot":[106],"policies":[107],"can":[109,135],"solve":[110],"complex":[111],"object-arrangement":[112],"such":[114,123],"shape-matching,":[116],"stacking,":[117],"even":[119],"full":[120],"path-following":[121],"applying":[125],"glue":[126],"sticking":[128],"objects":[129],"together,":[130],"all":[131],"demonstrations":[133],"collected":[137],"minutes.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}