{"id":"https://openalex.org/W4413917052","doi":"https://doi.org/10.1109/icra55743.2025.11128780","title":"This&That: Language-Gesture Controlled Video Generation for Robot Planning","display_name":"This&That: Language-Gesture Controlled Video Generation for Robot Planning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917052","doi":"https://doi.org/10.1109/icra55743.2025.11128780"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100725035","display_name":"Boyang Wang","orcid":"https://orcid.org/0000-0001-8973-2328"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boyang Wang","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102703567","display_name":"Nikhil Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Sridhar","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089069072","display_name":"Chao Feng","orcid":"https://orcid.org/0000-0002-6102-6832"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Feng","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042652043","display_name":"Mark Van der Merwe","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark van der Merwe","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073162537","display_name":"Adam Fishman","orcid":"https://orcid.org/0000-0002-8807-3102"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Fishman","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031338070","display_name":"Nima Fazeli","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Fazeli","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109413502","display_name":"Jeong Joon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeong Joon Park","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100725035"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.9571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94407273,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12842","last_page":"12849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.984499990940094,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.984499990940094,"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/T12290","display_name":"Human Motion and Animation","score":0.9546999931335449,"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":0.95169997215271,"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/gesture","display_name":"Gesture","score":0.7569541931152344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134473919868469},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4974236786365509},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41666916012763977},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3629147410392761},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33903968334198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3348744511604309}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7569541931152344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134473919868469},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4974236786365509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41666916012763977},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3629147410392761},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33903968334198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3348744511604309}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":19,"referenced_works":["https://openalex.org/W1986014385","https://openalex.org/W2760103357","https://openalex.org/W2918333121","https://openalex.org/W2962785568","https://openalex.org/W3038245394","https://openalex.org/W3176484337","https://openalex.org/W3204665606","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4385431288","https://openalex.org/W4390873054","https://openalex.org/W4391759936","https://openalex.org/W4402713100","https://openalex.org/W4403021266","https://openalex.org/W4404199654","https://openalex.org/W4404719810","https://openalex.org/W4413157524"],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650","https://openalex.org/W2954779189"],"abstract_inverted_index":{"Clear,":[0],"interpretable":[1],"instructions":[2],"are":[3,123],"invaluable":[4],"for":[5,25],"complex":[6,116],"tasks,":[7,34],"helping":[8],"to":[9,100,110,134],"clarify":[10],"goals":[11],"and":[12,28,55,85,107,117,143],"anticipate":[13],"necessary":[14],"steps.":[15],"In":[16],"this":[17,59],"work,":[18,60],"we":[19,61],"propose":[20],"a":[21,30,105,127],"robot":[22,91],"learning":[23],"framework":[24],"communicating,":[26],"planning,":[27],"executing":[29],"wide":[31],"range":[32],"of":[33],"dubbed":[35,131],"This&That.":[36],"This&That":[37],"solves":[38],"general":[39],"tasks":[40],"by":[41,147],"leveraging":[42],"video":[43,79,102,121],"generative":[44],"models,":[45],"which,":[46],"through":[47],"training":[48],"on":[49],"internet-scale":[50],"data,":[51],"contain":[52],"rich":[53],"physical":[54],"semantic":[56],"context.":[57],"Through":[58],"tackle":[62],"three":[63],"fundamental":[64],"challenges":[65],"in":[66,115],"video-based":[67,144],"planning:":[68],"1)":[69],"unambiguous":[70,108],"task":[71],"communication":[72],"with":[73],"simple":[74],"human":[75],"instructions,":[76],"2)":[77],"controllable":[78],"gen-eration":[80],"that":[81],"respects":[82],"user":[83],"intent,":[84],"3)":[86],"translating":[87],"visual":[88],"plans":[89],"into":[90,126],"actions.":[92],"This&":[93],"That":[94],"adds":[95],"gesture":[96],"conditioning":[97],"alongside":[98],"language":[99],"generate":[101],"predictions":[103,122],"as":[104],"suc-cinct":[106],"alternative":[109],"existing":[111],"language-only":[112],"methods,":[113],"especially":[114],"uncertain":[118],"environments.":[119],"These":[120],"then":[124],"fed":[125],"behavior":[128,141],"cloning":[129,142],"architecture":[130],"Diffusion":[132],"Video":[133],"Action":[135],"(DiVA),":[136],"which":[137],"outperforms":[138],"prior":[139],"state-of-the-art":[140],"planning":[145],"methods":[146],"substantial":[148],"margins.":[149],"Project":[150],"web-site:":[151],"https://this-and-that-vid.github.io/this-and-thatl.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}