{"id":"https://openalex.org/W4416062460","doi":"https://doi.org/10.1109/iccv51701.2025.01112","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","display_name":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416062460","doi":"https://doi.org/10.1109/iccv51701.2025.01112"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.06224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087953918","display_name":"Yixiang Chen","orcid":"https://orcid.org/0000-0002-3795-7530"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiang Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867544","display_name":"Peiyan Li","orcid":"https://orcid.org/0000-0001-8440-0674"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyan Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090159795","display_name":"Jiabing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabing Yang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057018921","display_name":"Kehan Chen","orcid":"https://orcid.org/0009-0004-3938-6542"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehan Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11958","last_page":"11968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7213000059127808,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7213000059127808,"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":0.06430000066757202,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.04690000042319298,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6610999703407288},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6276000142097473},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6201000213623047},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5913000106811523},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5259000062942505},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46230000257492065},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.4239000082015991},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4237000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309999823570251},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5893999934196472},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.3779999911785126},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.37790000438690186},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.06224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06224","pdf_url":"https://arxiv.org/pdf/2507.06224","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"},{"id":"doi:10.48550/arxiv.2507.06224","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.06224","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.06224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06224","pdf_url":"https://arxiv.org/pdf/2507.06224","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"language-guided":[1],"robotic":[2],"manipulation":[3,48,71,159],"systems":[4],"often":[5],"require":[6],"low-level":[7],"action-labeled":[8],"datasets":[9],"for":[10],"imitation":[11],"learning.":[12],"While":[13],"object-centric":[14,170],"flow":[15,171],"prediction":[16],"methods":[17],"mitigate":[18],"this":[19,36],"issue,":[20],"they":[21],"remain":[22],"limited":[23],"to":[24,69,108,123,133],"scenarios":[25],"involving":[26],"rigid":[27],"objects":[28],"with":[29,85],"clear":[30],"displacement":[31],"and":[32,78,88,102,144,162],"minimal":[33],"occlusion.":[34],"In":[35],"work,":[37],"we":[38,91],"present":[39],"Embodiment-Centric":[40],"Flow":[41],"(EC-Flow),":[42],"a":[43,94,114],"framework":[44],"that":[45,60],"directly":[46],"learns":[47],"from":[49],"action-unlabeled":[50],"videos":[51],"by":[52,97],"predicting":[53],"embodiment-centric":[54],"flow.":[55],"Our":[56],"key":[57],"insight":[58],"is":[59],"incorporating":[61],"the":[62,83],"embodiment's":[63],"inherent":[64],"kinematics":[65],"significantly":[66],"enhances":[67],"generalization":[68],"versatile":[70],"scenarios,":[72],"including":[73],"deformable":[74,157],"object":[75,89,153,158],"handling,":[76],"occlusions,":[77],"non-object-displacement":[79,163],"tasks.":[80],"To":[81],"connect":[82],"EC-Flow":[84,107,139],"language":[86],"instructions":[87],"interactions,":[90],"further":[92],"introduce":[93],"goal-alignment":[95],"module":[96],"jointly":[98],"optimizing":[99],"movement":[100],"consistency":[101],"goal-image":[103],"prediction.":[104],"Moreover,":[105],"translating":[106],"executable":[109],"robot":[110,116],"actions":[111],"only":[112],"requires":[113],"standard":[115],"URDF":[117],"(Unified":[118],"Robot":[119],"Description":[120],"Format)":[121],"file":[122],"specify":[124],"kinematic":[125],"constraints":[126],"across":[127],"joints,":[128],"which":[129],"makes":[130],"it":[131],"easy":[132],"use":[134],"in":[135,151],"practice.":[136],"We":[137],"validate":[138],"on":[140],"both":[141],"simulation":[142],"(Meta-World)":[143],"real-world":[145],"tasks,":[146],"demonstrating":[147],"its":[148],"state-of-the-art":[149,169],"performance":[150],"occluded":[152],"handling":[154],"(62%":[155],"improvement),":[156,161],"(45%":[160],"tasks":[164],"(80%":[165],"improvement)":[166],"than":[167],"prior":[168],"methods.":[172],"For":[173],"more":[174],"information,":[175],"see":[176],"our":[177],"project":[178],"website":[179],"at":[180],"https://ec-flow1.github.io":[181],".":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
