{"id":"https://openalex.org/W3090715080","doi":"https://doi.org/10.1109/icra40945.2020.9197324","title":"Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos","display_name":"Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3090715080","doi":"https://doi.org/10.1109/icra40945.2020.9197324","mag":"3090715080"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5088063475","display_name":"Ajay Kumar Tanwani","orcid":"https://orcid.org/0000-0002-6365-8315"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ajay Kumar Tanwani","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544075","display_name":"Pierre Sermanet","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Sermanet","raw_affiliation_strings":["Google Brain, USA"],"affiliations":[{"raw_affiliation_string":"Google Brain, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058240122","display_name":"Andy Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Yan","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101792950","display_name":"Raghav Anand","orcid":"https://orcid.org/0000-0002-6483-0551"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghav Anand","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008537744","display_name":"Mariano Phielipp","orcid":"https://orcid.org/0009-0001-2753-1747"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariano Phielipp","raw_affiliation_strings":["Intel AI Labs, USA"],"affiliations":[{"raw_affiliation_string":"Intel AI Labs, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088063475"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.9442,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.92741441,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2174","last_page":"2181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9962999820709229,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9779999852180481,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7650015354156494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7279400825500488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111451625823975},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6153980493545532},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5906150341033936},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5845797061920166},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5822412371635437},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5520947575569153},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45720013976097107},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4561838209629059},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44915854930877686},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43250808119773865},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4251061677932739},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4193049371242523},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16742005944252014}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7650015354156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7279400825500488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111451625823975},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6153980493545532},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5906150341033936},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5845797061920166},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5822412371635437},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5520947575569153},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45720013976097107},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4561838209629059},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44915854930877686},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43250808119773865},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4251061677932739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4193049371242523},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16742005944252014},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1556824961","https://openalex.org/W1816750950","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W2025468671","https://openalex.org/W2029294400","https://openalex.org/W2054661770","https://openalex.org/W2064675550","https://openalex.org/W2076618452","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2100796029","https://openalex.org/W2121451737","https://openalex.org/W2125838338","https://openalex.org/W2129202194","https://openalex.org/W2129999749","https://openalex.org/W2132579158","https://openalex.org/W2136719407","https://openalex.org/W2142258645","https://openalex.org/W2144499799","https://openalex.org/W2147880316","https://openalex.org/W2153579005","https://openalex.org/W2166851428","https://openalex.org/W2266673418","https://openalex.org/W2285373626","https://openalex.org/W2321739425","https://openalex.org/W2341108136","https://openalex.org/W2415633882","https://openalex.org/W2510642588","https://openalex.org/W2528489519","https://openalex.org/W2555897561","https://openalex.org/W2568518337","https://openalex.org/W2598634450","https://openalex.org/W2601322194","https://openalex.org/W2609990452","https://openalex.org/W2736730521","https://openalex.org/W2750092202","https://openalex.org/W2756475402","https://openalex.org/W2770804203","https://openalex.org/W2785241901","https://openalex.org/W2794908222","https://openalex.org/W2798897443","https://openalex.org/W2887503931","https://openalex.org/W2891273960","https://openalex.org/W2899508538","https://openalex.org/W2902125520","https://openalex.org/W2906270977","https://openalex.org/W2919658942","https://openalex.org/W2949121148","https://openalex.org/W2962787969","https://openalex.org/W2962887033","https://openalex.org/W2962904308","https://openalex.org/W2962957031","https://openalex.org/W2963003918","https://openalex.org/W2963094133","https://openalex.org/W2963277051","https://openalex.org/W2963321993","https://openalex.org/W2963802910","https://openalex.org/W2963863119","https://openalex.org/W2964066956","https://openalex.org/W2964127152","https://openalex.org/W3021888053","https://openalex.org/W3091905774","https://openalex.org/W3099032148","https://openalex.org/W3099206234","https://openalex.org/W3129430660","https://openalex.org/W4211044612","https://openalex.org/W4211191796","https://openalex.org/W4294170691","https://openalex.org/W4320013936","https://openalex.org/W6638229784","https://openalex.org/W6640174482","https://openalex.org/W6682082992","https://openalex.org/W6682691769","https://openalex.org/W6693343427","https://openalex.org/W6693735323","https://openalex.org/W6700718059","https://openalex.org/W6718092244","https://openalex.org/W6721414105","https://openalex.org/W6725336789","https://openalex.org/W6727690138","https://openalex.org/W6730323794","https://openalex.org/W6735531217","https://openalex.org/W6735944222","https://openalex.org/W6740202502","https://openalex.org/W6746798562","https://openalex.org/W6756257017","https://openalex.org/W6756443660","https://openalex.org/W6756908582","https://openalex.org/W6757965624","https://openalex.org/W6783596713","https://openalex.org/W6790562660"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2080152487","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2075445622"],"abstract_inverted_index":{"Learning":[0],"meaningful":[1],"visual":[2],"representations":[3],"in":[4,11,38,63,191],"an":[5,45],"embedding":[6,51,110,131],"space":[7,53,111,132],"can":[8],"facilitate":[9],"generalization":[10],"downstream":[12],"tasks":[13],"such":[14],"as":[15],"action":[16,36,71],"segmentation":[17,172],"and":[18,133,201],"imitation.":[19],"In":[20],"this":[21,153],"paper,":[22],"we":[23],"learn":[24],"a":[25,39,49,59,64,100,105,120],"motion-centric":[26],"representation":[27,154],"of":[28,83,91,108,123,152,165],"surgical":[29,157],"video":[30,55,125],"demonstrations":[31],"by":[32,57,141],"grouping":[33],"them":[34],"into":[35],"segments/subgoals/options":[37],"semi-supervised":[40],"manner.":[41],"We":[42,117,148],"present":[43],"Motion2Vec,":[44],"algorithm":[46],"that":[47],"learns":[48],"deep":[50],"feature":[52],"from":[54,68,79,161],"observations":[56],"minimizing":[58],"metric":[60],"learning":[61],"loss":[62],"Siamese":[65,115],"network:":[66],"images":[67,82],"the":[69,88,92,109,114,130,137,144,150,166,196],"same":[70],"segment":[72],"are":[73,96,203],"pulled":[74],"together":[75],"while":[76,86,183],"pushed":[77],"away":[78],"randomly":[80],"sampled":[81],"other":[84],"segments,":[85],"respecting":[87],"temporal":[89],"ordering":[90],"images.":[93],"The":[94],"embeddings":[95],"iteratively":[97],"segmented":[98],"with":[99],"recurrent":[101],"neural":[102],"network":[103],"for":[104],"given":[106],"parametrization":[107],"after":[112],"pre-training":[113],"network.":[116],"only":[118],"use":[119,151],"small":[121],"set":[122],"labeled":[124],"segments":[126],"to":[127,136,155],"semantically":[128],"align":[129],"assign":[134],"pseudo-labels":[135],"remaining":[138],"unlabeled":[139],"data":[140,202],"inference":[142],"on":[143,174,195],"learned":[145],"model":[146],"parameters.":[147],"demonstrate":[149],"imitate":[156],"suturing":[158],"kinematic":[159,184],"motions":[160],"publicly":[162],"available":[163,204],"videos":[164],"JIGSAWS":[167],"dataset.":[168],"Results":[169],"give":[170],"85.5%":[171],"accuracy":[173],"average":[175],"suggesting":[176],"performance":[177],"improvement":[178],"over":[179],"several":[180],"state-of-the-art":[181],"baselines,":[182],"pose":[185],"imitation":[186],"gives":[187],"0.94":[188],"centimeter":[189],"error":[190],"position":[192],"per":[193],"observation":[194],"test":[197],"set.":[198],"Videos,":[199],"code":[200],"at:":[205],"https://sites.google.com/view/motion2vec.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":16}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}