{"id":"https://openalex.org/W4415087506","doi":"https://doi.org/10.48550/arxiv.2509.10952","title":"ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation","display_name":"ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation","publication_year":2025,"publication_date":"2025-09-13","ids":{"openalex":"https://openalex.org/W4415087506","doi":"https://doi.org/10.48550/arxiv.2509.10952"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.10952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.10952","pdf_url":"https://arxiv.org/pdf/2509.10952","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.10952","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104285914","display_name":"Yangcen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yangcen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119950766","display_name":"Woo Chul Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Woo Chul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500088","display_name":"Yunhai Han","orcid":"https://orcid.org/0000-0003-3119-0129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Yunhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108033016","display_name":"Zhenyang Chen","orcid":"https://orcid.org/0000-0002-1459-3498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087370510","display_name":"Harish Ravichandar","orcid":"https://orcid.org/0000-0002-6635-2637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravichandar, Harish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028834865","display_name":"Danfei Xu","orcid":"https://orcid.org/0000-0002-8744-3861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Danfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9987000226974487,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9970999956130981,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9944999814033508,"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/robot","display_name":"Robot","score":0.6366000175476074},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5985000133514404},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4830999970436096},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.415800005197525},{"id":"https://openalex.org/keywords/teleoperation","display_name":"Teleoperation","score":0.39809998869895935},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.3961000144481659},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6924999952316284},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6155999898910522},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5985000133514404},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.32249999046325684},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2687000036239624},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.10952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.10952","pdf_url":"https://arxiv.org/pdf/2509.10952","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,"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.2509.10952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.10952","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.10952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.10952","pdf_url":"https://arxiv.org/pdf/2509.10952","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,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"robot":[1,52,73,83,156],"manipulation":[2,119],"from":[3],"abundant":[4],"human":[5,44,69,81,91],"videos":[6,45],"offers":[7],"a":[8,47],"scalable":[9],"alternative":[10],"to":[11,66,72,149],"costly":[12],"robot-specific":[13],"data":[14,104],"collection.":[15],"However,":[16],"domain":[17,32,111,152],"gaps":[18],"across":[19,127],"visual,":[20],"morphological,":[21],"and":[22,46,82,98,122,143],"physical":[23],"aspects":[24],"hinder":[25],"direct":[26],"imitation.":[27],"To":[28],"effectively":[29],"bridge":[30,150],"the":[31,102,151],"gap,":[33],"we":[34],"propose":[35],"ImMimic,":[36],"an":[37],"embodiment-agnostic":[38],"co-training":[39],"framework":[40],"that":[41,108,137],"leverages":[42],"both":[43],"small":[48],"amount":[49],"of":[50],"teleoperated":[51],"demonstrations.":[53],"ImMimic":[54,138],"uses":[55],"Dynamic":[56],"Time":[57],"Warping":[58],"(DTW)":[59],"with":[60],"either":[61],"action-":[62],"or":[63],"visual-based":[64],"mapping":[65],"map":[67],"retargeted":[68,90],"hand":[70,92],"poses":[71],"joints,":[74],"followed":[75],"by":[76],"MixUp":[77],"interpolation":[78,100],"between":[79],"paired":[80],"trajectories.":[84],"Our":[85],"key":[86],"insights":[87],"are":[88],"(1)":[89],"trajectories":[93],"provide":[94],"informative":[95],"action":[96],"labels,":[97],"(2)":[99],"over":[101],"mapped":[103],"creates":[105],"intermediate":[106],"domains":[107],"facilitate":[109],"smooth":[110],"adaptation":[112],"during":[113],"co-training.":[114],"Evaluations":[115],"on":[116],"four":[117,128],"real-world":[118],"tasks":[120],"(Pick":[121],"Place,":[123],"Push,":[124],"Hammer,":[125],"Flip)":[126],"robotic":[129],"embodiments":[130],"(Robotiq,":[131],"Fin":[132],"Ray,":[133],"Allegro,":[134],"Ability)":[135],"show":[136],"improves":[139],"task":[140],"success":[141],"rates":[142],"execution":[144],"smoothness,":[145],"highlighting":[146],"its":[147],"efficacy":[148],"gap":[153],"for":[154],"robust":[155],"manipulation.":[157],"The":[158],"project":[159],"website":[160],"can":[161],"be":[162],"found":[163],"at":[164],"https://sites.google.com/view/immimic.":[165]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-12T00:00:00"}
