{"id":"https://openalex.org/W4390872096","doi":"https://doi.org/10.1109/iccv51070.2023.00952","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","display_name":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872096","doi":"https://doi.org/10.1109/iccv51070.2023.00952"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00952","doi":"https://doi.org/10.1109/iccv51070.2023.00952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00952","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.00794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110949634","display_name":"Anshul Shah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshul Shah","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048331057","display_name":"Benjamin Lundell","orcid":"https://orcid.org/0009-0003-8349-5773","observed_orcids":["https://orcid.org/0009-0003-8349-5773"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Lundell","raw_affiliation_strings":["Microsoft Mixed Reality"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Mixed Reality","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091076182","display_name":"Harpreet Sawhney","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harpreet Sawhney","raw_affiliation_strings":["Microsoft Mixed Reality"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Mixed Reality","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650","observed_orcids":["https://orcid.org/0000-0002-7638-1650"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rama Chellappa","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0183,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85744395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10341","last_page":"10353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7275000214576721,"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/T11439","display_name":"Video Analysis and Summarization","score":0.7275000214576721,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.15950000286102295,"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/T10916","display_name":"Surgical Simulation and Training","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/procedural-videos","display_name":"procedural videos","score":0.8650000095367432},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.796999990940094},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7760000228881836},{"id":"https://openalex.org/keywords/optical-flow","display_name":"optical flow","score":0.8270000219345093},{"id":"https://openalex.org/keywords/depth","display_name":"depth","score":0.6100000143051147},{"id":"https://openalex.org/keywords/gaze","display_name":"gaze","score":0.8420000076293945},{"id":"https://openalex.org/keywords/phase-classification","display_name":"phase classification","score":0.6370000243186951},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"augmented reality","score":0.722000002861023},{"id":"https://openalex.org/keywords/job-training","display_name":"job training","score":0.8379999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371046185493469},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8335945010185242},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.8247343301773071},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7337798476219177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6419992446899414},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5966536998748779},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.545856237411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4804063141345978},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4774356782436371},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4509231746196747},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3442285656929016},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51070.2023.00952","doi":"https://doi.org/10.1109/iccv51070.2023.00952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00952","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.00794","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.00794","pdf_url":"https://arxiv.org/pdf/2301.00794","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.00794","doi":"https://doi.org/10.48550/arxiv.2301.00794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.00794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.00794","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.00794","pdf_url":"https://arxiv.org/pdf/2301.00794","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3587679958","display_name":null,"funder_award_id":"N00014-20-1-2787","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G5121974832","display_name":null,"funder_award_id":"N00014-20-1-2787","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8006577219","display_name":null,"funder_award_id":"N00014-20","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390872096.pdf","grobid_xml":"https://content.openalex.org/works/W4390872096.grobid-xml"},"referenced_works_count":93,"referenced_works":["https://openalex.org/W1527883571","https://openalex.org/W1530229763","https://openalex.org/W1963321737","https://openalex.org/W2030452706","https://openalex.org/W2087095333","https://openalex.org/W2102544546","https://openalex.org/W2112838383","https://openalex.org/W2138621090","https://openalex.org/W2152668594","https://openalex.org/W2152790380","https://openalex.org/W2154214162","https://openalex.org/W2171680637","https://openalex.org/W2185243164","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2487442924","https://openalex.org/W2737677090","https://openalex.org/W2769112066","https://openalex.org/W2781922022","https://openalex.org/W2795187948","https://openalex.org/W2799087757","https://openalex.org/W2883451034","https://openalex.org/W2895299763","https://openalex.org/W2909895379","https://openalex.org/W2930595145","https://openalex.org/W2937170809","https://openalex.org/W2948242301","https://openalex.org/W2948859046","https://openalex.org/W2962771625","https://openalex.org/W2963814513","https://openalex.org/W2964037671","https://openalex.org/W2967038491","https://openalex.org/W2971672253","https://openalex.org/W2979331346","https://openalex.org/W2982673782","https://openalex.org/W2987425933","https://openalex.org/W2990616379","https://openalex.org/W2990720095","https://openalex.org/W2997333136","https://openalex.org/W3003076898","https://openalex.org/W3003339562","https://openalex.org/W3005680577","https://openalex.org/W3017094594","https://openalex.org/W3020933450","https://openalex.org/W3022061250","https://openalex.org/W3024811055","https://openalex.org/W3034381931","https://openalex.org/W3035218028","https://openalex.org/W3035467150","https://openalex.org/W3035524453","https://openalex.org/W3040046528","https://openalex.org/W3044365806","https://openalex.org/W3047573812","https://openalex.org/W3080919758","https://openalex.org/W3083405884","https://openalex.org/W3087792975","https://openalex.org/W3091940082","https://openalex.org/W3092157723","https://openalex.org/W3092639633","https://openalex.org/W3092689724","https://openalex.org/W3099156605","https://openalex.org/W3103215803","https://openalex.org/W3103717557","https://openalex.org/W3108225446","https://openalex.org/W3108655343","https://openalex.org/W3109908659","https://openalex.org/W3117320425","https://openalex.org/W3147426949","https://openalex.org/W3147788509","https://openalex.org/W3151935374","https://openalex.org/W3158922870","https://openalex.org/W3168531333","https://openalex.org/W3174461105","https://openalex.org/W3177173029","https://openalex.org/W3188030217","https://openalex.org/W3201942032","https://openalex.org/W3204659849","https://openalex.org/W3208431284","https://openalex.org/W3214328324","https://openalex.org/W4214514833","https://openalex.org/W4226195309","https://openalex.org/W4283819635","https://openalex.org/W4297808394","https://openalex.org/W4304701298","https://openalex.org/W4312245820","https://openalex.org/W4312422429","https://openalex.org/W4319299787","https://openalex.org/W4319300928","https://openalex.org/W4386075592","https://openalex.org/W4390873954","https://openalex.org/W4411244992","https://openalex.org/W6940864310","https://openalex.org/W7133231027"],"related_works":["https://openalex.org/W4386075592","https://openalex.org/W3103717557","https://openalex.org/W4386076369","https://openalex.org/W4386065873","https://openalex.org/W2990720095","https://openalex.org/W4416233037","https://openalex.org/W4394596554","https://openalex.org/W7148951347","https://openalex.org/W4221153256","https://openalex.org/W4305007506"],"abstract_inverted_index":{"We":[0,27,40,107,122],"address":[1],"the":[2,14,29,118,130,143,155],"problem":[3,30],"of":[4,16,132,154],"extracting":[5],"key":[6,37,110,133,145],"steps":[7,38,56,111,146,153],"from":[8,61,86],"un-labeled":[9],"procedural":[10,156],"videos,":[11],"motivated":[12],"by":[13],"potential":[15],"Augmented":[17],"Reality":[18],"(AR)":[19],"headsets":[20],"to":[21,50,67,95],"revolutionize":[22],"job":[23],"training":[24,43],"and":[25,36,120,136,149],"performance.":[26],"decompose":[28],"into":[31],"two":[32],"steps:":[33],"representation":[34],"learning":[35],"extraction.":[39],"propose":[41],"a":[42,69,113],"objective,":[44],"Bootstrapped":[45],"Multi-Cue":[46],"Contrastive":[47],"(BMC2)":[48],"loss":[49],"learn":[51,96],"discriminative":[52,97],"representations":[53,119],"for":[54,77,99,104,129],"various":[55,152],"without":[57],"any":[58],"labels.":[59],"Different":[60],"prior":[62,127],"works,":[63],"we":[64],"develop":[65],"techniques":[66],"train":[68],"light-weight":[70],"temporal":[71],"module":[72],"which":[73],"uses":[74],"off-the-shelf":[75],"features":[76,98],"self":[78],"supervision.":[79],"Our":[80,158],"approach":[81],"can":[82,160],"seamlessly":[83],"leverage":[84],"information":[85],"multiple":[87],"cues":[88],"like":[89],"optical":[90],"flow,":[91],"depth":[92],"or":[93],"gaze":[94],"key-steps,":[100],"making":[101],"it":[102],"amenable":[103],"AR":[105],"applications.":[106],"finally":[108],"extract":[109],"via":[112],"tunable":[114],"algorithm":[115],"that":[116,142],"clusters":[117],"samples.":[121],"show":[123],"significant":[124],"improvements":[125],"over":[126],"works":[128],"task":[131],"step":[134],"localization":[135],"phase":[137],"classification.":[138],"Qualitative":[139],"results":[140],"demonstrate":[141],"extracted":[144],"are":[147],"meaningful":[148],"succinctly":[150],"represent":[151],"tasks.":[157],"code":[159],"be":[161],"found":[162],"at":[163],"https://github.com/anshulbshah/STEPs.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-01-16T00:00:00"}