{"id":"https://openalex.org/W4413156195","doi":"https://doi.org/10.1109/cvpr52734.2025.02578","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","display_name":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413156195","doi":"https://doi.org/10.1109/cvpr52734.2025.02578"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102885390","display_name":"Hongxiang Zhao","orcid":"https://orcid.org/0000-0002-7891-5193"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxiang Zhao","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644714","display_name":"Xingchen Liu","orcid":"https://orcid.org/0000-0002-9704-5728"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Liu","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066673615","display_name":"Mutian Xu","orcid":"https://orcid.org/0000-0001-8123-6493"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mutian Xu","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517009","display_name":"Yiming Hao","orcid":"https://orcid.org/0000-0003-3225-5887"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Hao","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103189918","display_name":"Weikai Chen","orcid":"https://orcid.org/0000-0002-5060-5476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weikai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081098250","display_name":"Xiaoguang Han","orcid":"https://orcid.org/0000-0003-0810-259X"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Han","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3874,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89464469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"27683","last_page":"27693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9937000274658203,"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":0.9937000274658203,"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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9451000094413757,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.6777334213256836},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6509272456169128},{"id":"https://openalex.org/keywords/taste","display_name":"Taste","score":0.6074346303939819},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5727764368057251},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5650676488876343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46351540088653564},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4230974316596985},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3871319890022278},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1586628258228302},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13641253113746643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777334213256836},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6509272456169128},{"id":"https://openalex.org/C8868529","wikidata":"https://www.wikidata.org/wiki/Q124794","display_name":"Taste","level":2,"score":0.6074346303939819},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5727764368057251},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5650676488876343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46351540088653564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4230974316596985},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3871319890022278},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1586628258228302},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13641253113746643},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2106229755","https://openalex.org/W2120645068","https://openalex.org/W2147806277","https://openalex.org/W2165605600","https://openalex.org/W2282481780","https://openalex.org/W2768683308","https://openalex.org/W3034891989","https://openalex.org/W3122520957","https://openalex.org/W3123364653","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4283788863","https://openalex.org/W4313031313","https://openalex.org/W4383108856","https://openalex.org/W4383109144","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4385431288","https://openalex.org/W4387969168","https://openalex.org/W4390873054","https://openalex.org/W4390874627","https://openalex.org/W4393148714","https://openalex.org/W4401416041","https://openalex.org/W4401417162","https://openalex.org/W4402354026","https://openalex.org/W4402354047","https://openalex.org/W4402354080","https://openalex.org/W4402704593","https://openalex.org/W4402753775","https://openalex.org/W4403003238","https://openalex.org/W4403888324","https://openalex.org/W4404525440","https://openalex.org/W4406581187"],"related_works":["https://openalex.org/W4248622074","https://openalex.org/W1977661140","https://openalex.org/W4252618551","https://openalex.org/W2358619800","https://openalex.org/W1590660384","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"We":[0],"address":[1],"key":[2],"limitations":[3],"in":[4,110,128,144,152,162],"existing":[5],"datasets":[6],"and":[7,38,46,80,167],"models":[8],"for":[9,22,50],"task-oriented":[10,147],"hand-object":[11,69,148],"interaction":[12,70,89,149],"video":[13,20,44,73],"generation,":[14],"a":[15,62,83,93,119],"critical":[16],"approach":[17],"of":[18,66],"generating":[19,145],"demonstrations":[21],"robotic":[23,156],"imitation":[24,52],"learning.":[25],"Current":[26],"datasets,":[27],"such":[28],"as":[29],"Ego4D":[30],"[16],":[31],"often":[32],"suffer":[33],"from":[34,82],"inconsistent":[35],"view":[36],"perspectives":[37],"misaligned":[39],"interactions,":[40,104],"leading":[41],"to":[42,87],"reduced":[43],"quality":[45],"limiting":[47],"their":[48],"applicability":[49],"precise":[51],"learning":[53],"tasks.":[54],"Towards":[55],"this":[56],"end,":[57],"we":[58,100,106,117],"introduce":[59,118],"TASTE-Rob":[60,165],"\u2014":[61],"pioneering":[63],"large-scale":[64],"dataset":[65,166],"100,856":[67],"ego-centric":[68],"videos.":[71,130],"Each":[72],"is":[74],"meticulously":[75],"aligned":[76],"with":[77,135],"language":[78],"instructions":[79],"recorded":[81],"consistent":[84],"camera":[85],"viewpoint":[86],"ensure":[88],"clarity.":[90],"By":[91],"fine-tuning":[92],"Video":[94],"Diffusion":[95],"Model":[96],"(VDM)":[97],"on":[98,175],"TASTERob,":[99],"achieve":[101],"realistic":[102],"object":[103],"though":[105],"observed":[107],"occasional":[108],"inconsistencies":[109],"hand":[111,125],"grasping":[112],"postures.":[113],"To":[114,158],"enhance":[115],"realism,":[116],"three-stage":[120],"pose-refinement":[121,138],"pipeline":[122],"that":[123],"improves":[124],"posture":[126],"accuracy":[127],"generated":[129],"Our":[131],"curated":[132],"dataset,":[133],"coupled":[134],"the":[136,163],"specialized":[137],"framework,":[139],"provides":[140],"notable":[141],"performance":[142],"gains":[143],"high-quality,":[146],"videos,":[150],"resulting":[151],"achieving":[153],"superior":[154],"generalizable":[155],"manipulation.":[157],"foster":[159],"further":[160],"advancements":[161],"field,":[164],"source":[168],"code":[169],"will":[170],"be":[171],"made":[172],"publicly":[173],"available":[174],"our":[176],"website":[177],"https://taste-rob.github.io.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}