{"id":"https://openalex.org/W4416750082","doi":"https://doi.org/10.1109/iros60139.2025.11247201","title":"Temporal-Spatial Representation Fusion for Dexterous Manipulation Learning with Unpaired Visual-Action Data","display_name":"Temporal-Spatial Representation Fusion for Dexterous Manipulation Learning with Unpaired Visual-Action Data","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750082","doi":"https://doi.org/10.1109/iros60139.2025.11247201"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5016523119","display_name":"Guwen Han","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guwen Han","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101039545","display_name":"Zhengnan Sun","orcid":"https://orcid.org/0000-0001-6954-7766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengnan Sun","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166291","display_name":"Qingtao Liu","orcid":"https://orcid.org/0000-0002-6105-2969"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingtao Liu","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103495659","display_name":"Yu Cui","orcid":"https://orcid.org/0009-0001-6203-3022"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Cui","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770129","display_name":"Anjun Chen","orcid":"https://orcid.org/0000-0003-4209-8301"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anjun Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061278083","display_name":"Huajin Chen","orcid":"https://orcid.org/0000-0002-8783-3691"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajin Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528125","display_name":"Rong Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726039","display_name":"Jiming Chen","orcid":"https://orcid.org/0000-0002-7679-0614"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052177334","display_name":"Qi Ye","orcid":"https://orcid.org/0000-0003-0328-5075"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Ye","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5016523119"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44970488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3193","last_page":"3200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6172000169754028,"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":0.6172000169754028,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.11100000143051147,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09179999679327011,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/action","display_name":"Action (physics)","score":0.6717000007629395},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.576200008392334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.490200012922287},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4569999873638153},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3244999945163727},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.301800012588501},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.2856999933719635}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7832000255584717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746399998664856},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5403000116348267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4569999873638153},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4399999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2073408938","https://openalex.org/W2951360122","https://openalex.org/W2963411833","https://openalex.org/W2963669336","https://openalex.org/W3035624836","https://openalex.org/W3091133300","https://openalex.org/W3164862896","https://openalex.org/W3189615635","https://openalex.org/W3202717607","https://openalex.org/W3206200647","https://openalex.org/W4210921444","https://openalex.org/W4313156423","https://openalex.org/W4383066442","https://openalex.org/W4383108491","https://openalex.org/W4383108746","https://openalex.org/W4389665571","https://openalex.org/W4401414409","https://openalex.org/W4401416205","https://openalex.org/W4401417423","https://openalex.org/W4402354112"],"related_works":[],"abstract_inverted_index":{"Supervised":[0],"behavioral":[1],"cloning":[2],"using":[3],"robot":[4,12,156,168],"visual-action":[5,33],"data":[6,42,56,74],"has":[7,44],"been":[8],"widely":[9],"investigated":[10],"in":[11,143,185],"manipulation.":[13],"However,":[14],"these":[15],"methods":[16],"typically":[17],"require":[18],"simultaneous":[19],"acquisition":[20],"of":[21,53,81],"visual":[22,59,174],"and":[23,47,103,146],"action":[24,40,55,73,96,113,133],"data,":[25],"which":[26,43,131],"makes":[27],"them":[28],"difficult":[29],"to":[30,78,92,109,124,138],"utilize":[31],"unpaired":[32],"datasets:":[34],"e.g.":[35],"videos":[36],"on":[37,153],"Internet":[38],"or":[39],"only":[41],"less":[45],"privacy":[46],"security":[48],"concerns.":[49],"To":[50],"take":[51],"advantage":[52],"the":[54,94,100,111,117,126,144],"without":[57,75],"synchronized":[58],"observation,":[60],"we":[61],"propose":[62],"UnVALe,":[63],"a":[64,104,180],"novel":[65],"dexterous":[66,83,155],"robotic":[67],"manipulation":[68,84,157,169],"RL":[69,136],"framework":[70],"that":[71,163],"utilizes":[72],"paired":[76],"images":[77],"learn":[79,93,110],"priors":[80,127],"human":[82],"skills.":[85],"Specifically,":[86],"an":[87],"LSTM-based":[88],"network":[89,106],"is":[90,107],"designed":[91,108],"temporal":[95],"prior":[97,114],"by":[98,115],"reconstructing":[99,116],"input":[101,118],"trajectories,":[102],"VAE":[105,147],"spatial":[112],"action.":[119],"Novel":[120],"rewards":[121],"are":[122],"proposed":[123],"incorporate":[125],"into":[128],"reinforcement":[129],"learning,":[130],"encourages":[132],"output":[134],"from":[135],"polices":[137],"maintain":[139],"low":[140],"reconstruction":[141],"errors":[142],"LSTM":[145],"networks.":[148],"We":[149],"perform":[150],"extensive":[151],"validation":[152],"three":[154],"tasks.":[158],"The":[159],"experimental":[160],"results":[161],"show":[162],"UnVALe":[164],"can":[165],"effectively":[166],"improve":[167],"performance.":[170],"Compared":[171],"with":[172],"existing":[173],"pretraining":[175],"methods,":[176],"our":[177],"method":[178],"achieves":[179],"more":[181],"than":[182],"30%":[183],"increase":[184],"success":[186],"rates.":[187]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}