{"id":"https://openalex.org/W4210731474","doi":"https://doi.org/10.1109/lra.2022.3145488","title":"OSSID: Online Self-Supervised Instance Detection by (And For) Pose Estimation","display_name":"OSSID: Online Self-Supervised Instance Detection by (And For) Pose Estimation","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W4210731474","doi":"https://doi.org/10.1109/lra.2022.3145488"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3145488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3145488","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.07309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068721714","display_name":"Qiao Gu","orcid":"https://orcid.org/0000-0002-1342-3307"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qiao Gu","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, ON, Canada","Computer Science, University of Toronto, Toronto, ON, Canada, M5G0A6 (e-mail: q.gu@mail.utoronto.ca)"],"raw_orcid":"https://orcid.org/0000-0002-1342-3307","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Computer Science, University of Toronto, Toronto, ON, Canada, M5G0A6 (e-mail: q.gu@mail.utoronto.ca)","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021481740","display_name":"Brian Okorn","orcid":"https://orcid.org/0000-0001-8092-1288"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Okorn","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, PITTSBURGH, Pennsylvania, United States of America, 15232 (e-mail: bokorn@andrew.cmu.edu)"],"raw_orcid":"https://orcid.org/0000-0001-8092-1288","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, PITTSBURGH, Pennsylvania, United States of America, 15232 (e-mail: bokorn@andrew.cmu.edu)","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037048516","display_name":"David Held","orcid":"https://orcid.org/0000-0003-0537-1508"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Held","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, United States of America, 15213 (e-mail: davheldwork@gmail.com)"],"raw_orcid":"https://orcid.org/0000-0003-0537-1508","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, United States of America, 15213 (e-mail: davheldwork@gmail.com)","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.405,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53462105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":"2","first_page":"3022","last_page":"3029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T10812","display_name":"Human Pose and Action Recognition","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/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.995199978351593,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6620210409164429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6334375143051147},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5869224071502686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4781668782234192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44111454486846924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34152650833129883}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6620210409164429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6334375143051147},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5869224071502686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781668782234192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44111454486846924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34152650833129883}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2022.3145488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3145488","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2201.07309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.07309","pdf_url":"https://arxiv.org/pdf/2201.07309","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.07309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.07309","pdf_url":"https://arxiv.org/pdf/2201.07309","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320329803","display_name":"LG Electronics","ror":"https://ror.org/03ddh2c27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W132147841","https://openalex.org/W1505952289","https://openalex.org/W1526868886","https://openalex.org/W1969868017","https://openalex.org/W2000760692","https://openalex.org/W2031489346","https://openalex.org/W2058761328","https://openalex.org/W2063849031","https://openalex.org/W2084635560","https://openalex.org/W2104572712","https://openalex.org/W2124386111","https://openalex.org/W2129690990","https://openalex.org/W2139146597","https://openalex.org/W2151103935","https://openalex.org/W2154422044","https://openalex.org/W2157762168","https://openalex.org/W2161168419","https://openalex.org/W2520352517","https://openalex.org/W2604662268","https://openalex.org/W2792470621","https://openalex.org/W2887599887","https://openalex.org/W2888752296","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963227409","https://openalex.org/W2964115968","https://openalex.org/W2964277612","https://openalex.org/W2969177478","https://openalex.org/W2970399728","https://openalex.org/W2981705647","https://openalex.org/W2983156430","https://openalex.org/W2989915422","https://openalex.org/W2990069979","https://openalex.org/W2990740643","https://openalex.org/W3010381534","https://openalex.org/W3034573608","https://openalex.org/W3034712732","https://openalex.org/W3034937575","https://openalex.org/W3034974675","https://openalex.org/W3092774272","https://openalex.org/W3108187451","https://openalex.org/W3120403282","https://openalex.org/W3167453437","https://openalex.org/W3180426564","https://openalex.org/W3207966761","https://openalex.org/W4288333732","https://openalex.org/W4327852039","https://openalex.org/W6749269122","https://openalex.org/W6764306722","https://openalex.org/W6764438438","https://openalex.org/W6774983715"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2058170566","https://openalex.org/W4306674287","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Real-time":[0],"object":[1,15,112],"pose":[2,16,36,63,87,113,131,167,172],"estimation":[3,17,114,132,173],"is":[4],"necessary":[5],"for":[6,14,20,48,130,154],"many":[7],"robot":[8],"manipulation":[9],"algorithms.":[10],"However,":[11],"state-of-the-art":[12],"methods":[13,27,107],"are":[18],"trained":[19],"a":[21,60,70,134,159,165],"specific":[22],"set":[23],"of":[24,37,44,46,69,103,148,158],"objects;":[25],"these":[26],"thus":[28],"need":[29],"to":[30,33,65,81,85,140,143,170],"be":[31,79,186],"retrained":[32],"estimate":[34],"the":[35,56,67,83,86,101,127,141,149],"each":[38],"new":[39],"object,":[40],"often":[41],"requiring":[42,119,178],"tens":[43],"GPU-days":[45],"training":[47,68,99],"optimal":[49],"performance.":[50],"In":[51],"this":[52,97],"letter,":[53],"we":[54,124],"propose":[55],"OSSID":[57],"framework,":[58],"leveraging":[59],"slow":[61,166],"zero-shot":[62,105],"estimator":[64],"self-supervise":[66],"fast":[71,75],"detection":[72,106,116],"algorithm.":[73],"This":[74],"detector":[76,160],"can":[77,185],"then":[78],"used":[80,111],"filter":[82,144],"input":[84],"estimator,":[88],"drastically":[89],"improving":[90],"its":[91],"inference":[92,137],"speed.":[93],"We":[94],"show":[95,125],"that":[96,126],"self-supervised":[98,155],"exceeds":[100],"performance":[102],"existing":[104],"on":[108],"two":[109],"widely":[110],"and":[115,183],"datasets,":[117],"without":[118,177],"any":[120],"human":[121,179],"annotations.":[122,180],"Further,":[123],"resulting":[128],"method":[129,153],"has":[133],"significantly":[135],"faster":[136],"speed,":[138],"due":[139],"ability":[142],"out":[145],"large":[146],"parts":[147],"image.":[150],"Thus,":[151],"our":[152],"online":[156],"learning":[157],"(trained":[161],"using":[162],"pseudo-labels":[163],"from":[164],"estimator)":[168],"leads":[169],"accurate":[171],"at":[174,188],"real-time":[175],"speeds,":[176],"Supplementary":[181],"materials":[182],"code":[184],"found":[187],"<uri>https://georgegu1997.github.io/OSSID/</uri>":[189]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2022-02-08T00:00:00"}