{"id":"https://openalex.org/W7167599511","doi":"https://doi.org/10.1016/j.rcim.2026.103371","title":"Video2Knowledge: Extracting temporally consistent task knowledge from monocular video for robot skill learning","display_name":"Video2Knowledge: Extracting temporally consistent task knowledge from monocular video for robot skill learning","publication_year":2026,"publication_date":"2026-07-07","ids":{"openalex":"https://openalex.org/W7167599511","doi":"https://doi.org/10.1016/j.rcim.2026.103371"},"language":"en","primary_location":{"id":"doi:10.1016/j.rcim.2026.103371","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103371","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0736584526001936/pdf","source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S0736584526001936/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140197156","display_name":"Jinyi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jinyi Huang","raw_affiliation_strings":["Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140177669","display_name":"Hao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013195024","display_name":"Yinwang Ren","orcid":"https://orcid.org/0009-0003-0458-7750"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yinwang Ren","raw_affiliation_strings":["Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128026130","display_name":"Wenqing Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Wan","raw_affiliation_strings":["State Key Laboratory for Manufacturing and Systems Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Manufacturing and Systems Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, PR China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451924","display_name":"Xun Xu","orcid":"https://orcid.org/0000-0002-4246-4343"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Xun Xu","raw_affiliation_strings":["Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080995501","display_name":"Jan Polzer","orcid":"https://orcid.org/0000-0001-8513-7302"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Jan Polzer","raw_affiliation_strings":["Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-8513-7302","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Mechatronics Engineering, The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080995501"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":{"value":4240,"currency":"USD","value_usd":4240},"apc_paid":{"value":4240,"currency":"USD","value_usd":4240},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90821848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"103","issue":null,"first_page":"103371","last_page":"103371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.48730000853538513,"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":0.48730000853538513,"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":0.21850000321865082,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05000000074505806,"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/task","display_name":"Task (project management)","score":0.623199999332428},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4788999855518341},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.41589999198913574},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33309999108314514},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.29190000891685486},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.28690001368522644}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6291000247001648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6093000173568726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2816999852657318},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.rcim.2026.103371","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103371","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0736584526001936/pdf","source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.rcim.2026.103371","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103371","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0736584526001936/pdf","source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320801","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167599511.pdf","grobid_xml":"https://content.openalex.org/works/W7167599511.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2768683308","https://openalex.org/W2995983596","https://openalex.org/W3025191362","https://openalex.org/W3150384095","https://openalex.org/W4313453017","https://openalex.org/W4386057769","https://openalex.org/W4388782297","https://openalex.org/W4390874610","https://openalex.org/W4391142622","https://openalex.org/W4392338537","https://openalex.org/W4403510570","https://openalex.org/W4407530753","https://openalex.org/W4411206891","https://openalex.org/W4414038273","https://openalex.org/W4414714021","https://openalex.org/W7115593831","https://openalex.org/W7133189623","https://openalex.org/W7133200073"],"related_works":[],"abstract_inverted_index":{"In":[0,90],"human-centric":[1],"manufacturing,":[2],"collaborative":[3],"robots":[4],"(cobots)":[5],"are":[6],"increasingly":[7],"expected":[8],"to":[9,30,186,237],"continually":[10],"acquire":[11],"knowledge":[12,51,181,211,231],"as":[13,26,132],"products":[14],"and":[15,18,46,110,134,148,174,195,217],"workflows":[16],"evolve,":[17],"learning":[19,123],"from":[20,232],"human":[21],"demonstration":[22,82,235],"videos":[23],"has":[24],"emerged":[25],"a":[27,105,121,127,164,179,233],"flexible":[28],"means":[29],"this":[31,34],"end.":[32],"Realizing":[33],"paradigm":[35],"requires":[36],"perception":[37,109],"that":[38,47,125,183,199],"can":[39],"be":[40],"deployed":[41],"with":[42,170],"minimal":[43],"hardware":[44],"overhead":[45],"generates":[48],"executable":[49,111],"task":[50,112,140,210,230],"for":[52],"robotic":[53],"manipulation.":[54],"Existing":[55],"video-based":[56,122],"methods":[57,93],"rarely":[58,84],"satisfy":[59],"both":[60],"requirements.":[61],"Geometric":[62],"pipelines":[63],"rely":[64],"on":[65,192],"CAD":[66,156],"models":[67,80],"or":[68,98,158],"multi-camera":[69],"rigs,":[70],"hindering":[71],"scalable":[72],"deployment":[73],"across":[74],"diverse":[75],"workpieces,":[76],"while":[77,207],"pre-trained":[78],"vision-language":[79],"require":[81],"corpora":[83],"available":[85],"in":[86,102,245],"high-mix,":[87],"low-volume":[88],"manufacturing.":[89],"addition,":[91],"existing":[92],"recover":[94],"only":[95],"low-level":[96],"geometry":[97],"high-level":[99],"semantic":[100],"labels":[101],"isolation,":[103],"leaving":[104],"gap":[106],"between":[107],"geometric":[108,219],"knowledge.":[113],"To":[114],"address":[115],"these":[116],"limitations,":[117],"we":[118],"propose":[119],"Video2Knowledge,":[120],"framework":[124,162],"takes":[126],"single":[128],"monocular":[129,234],"RGB":[130],"video":[131,236],"input":[133],"distills":[135],"it":[136],"into":[137,178],"temporally":[138],"consistent":[139],"knowledge,":[141],"covering":[142],"action":[143,188,215],"sequences,":[144],"object":[145,167],"state":[146],"transitions,":[147],"spatial":[149],"relations,":[150],"without":[151],"requiring":[152],"additional":[153],"sensors,":[154],"manual":[155],"models,":[157],"task-specific":[159],"retraining.":[160],"The":[161],"couples":[163],"physics-aware":[165,201],"6D":[166],"pose":[168,205],"corrector":[169],"hand\u2013object":[171],"interaction":[172],"analysis,":[173],"consolidates":[175],"the":[176,193,200,208,227,242],"results":[177],"structured":[180],"representation":[182],"maps":[184],"directly":[185],"robot":[187],"sequences.":[189],"Experimental":[190],"evaluation":[191],"HA-ViD":[194],"Assembly101":[196],"datasets":[197],"demonstrates":[198],"correction":[202],"yields":[203],"improved":[204],"coherence,":[206],"extracted":[209],"faithfully":[212],"recovers":[213],"demonstrated":[214],"semantics":[216],"relative":[218],"configurations.":[220],"A":[221],"real-world":[222],"case":[223],"study":[224],"further":[225],"validates":[226],"transfer":[228],"of":[229],"physical":[238],"cobot":[239],"execution,":[240],"confirming":[241],"practical":[243],"deployability":[244],"manufacturing":[246],"scenarios.":[247]},"counts_by_year":[],"updated_date":"2026-07-09T05:49:46.723101","created_date":"2026-07-08T00:00:00"}
