{"id":"https://openalex.org/W4417449962","doi":"https://doi.org/10.1109/wacv61042.2026.00146","title":"InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation","display_name":"InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417449962","doi":"https://doi.org/10.1109/wacv61042.2026.00146"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.12664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030246373","display_name":"Sreehari Rajan","orcid":"https://orcid.org/0000-0001-7941-5337"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sreehari Rajan","raw_affiliation_strings":["IIIT Hyderabad,Machine Learning Lab,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Machine Learning Lab,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120840755","display_name":"Kunal Bhosikar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kunal Bhosikar","raw_affiliation_strings":["IIIT Hyderabad,Machine Learning Lab,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Machine Learning Lab,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101841889","display_name":"Charu Sharma","orcid":"https://orcid.org/0000-0003-2518-5008"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Charu Sharma","raw_affiliation_strings":["IIIT Hyderabad,Machine Learning Lab,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Machine Learning Lab,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01712549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1438","last_page":"1447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5419999957084656,"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/T12290","display_name":"Human Motion and Animation","score":0.5419999957084656,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.08730000257492065,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07890000194311142,"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":0.8931999802589417},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.636900007724762},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.619700014591217},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.525600016117096},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8931999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930999994277954},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40849998593330383},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3262999951839447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2718999981880188}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.12664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12664","pdf_url":"https://arxiv.org/pdf/2512.12664","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.2512.12664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.12664","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:2512.12664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12664","pdf_url":"https://arxiv.org/pdf/2512.12664","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"realistic":[1],"human":[2],"motions":[3,176],"that":[4,50,109],"naturally":[5],"respond":[6],"to":[7,34,69,114],"both":[8,160],"spoken":[9],"language":[10],"and":[11,75,164,181],"physical":[12],"objects":[13],"is":[14,120],"crucial":[15],"for":[16],"interactive":[17],"digital":[18],"experiences.":[19],"Current":[20],"methods,":[21,170],"however,":[22],"address":[23,127],"speech-driven":[24],"gestures":[25],"or":[26],"object":[27,98],"interactions":[28,55],"independently,":[29],"limiting":[30],"real-world":[31],"applicability":[32],"due":[33],"a":[35,47,65,71,84,104],"lack":[36],"of":[37],"integrated,":[38],"comprehensive":[39],"datasets.":[40],"To":[41,79,126],"overcome":[42],"this,":[43,81],"we":[44,82,134],"introduce":[45],"InteracTalker,":[46],"novel":[48],"framework":[49,102],"seamlessly":[51],"integrates":[52],"prompt-based":[53],"object-aware":[54,174],"with":[56,96,177],"co-speech":[57,161],"gesture":[58,162],"generation.":[59],"We":[60],"achieve":[61],"this":[62],"by":[63,90],"employing":[64],"multi-stage":[66],"training":[67],"process":[68],"learn":[70],"unified":[72],"motion,":[73],"speech,":[74],"prompt":[76],"embedding":[77],"space.":[78],"support":[80],"curate":[83],"rich":[85],"human-object":[86],"interaction":[87,99],"dataset,":[88],"formed":[89],"augmenting":[91],"an":[92,136],"existing":[93],"text-to-motion":[94],"dataset":[95],"detailed":[97],"annotations.":[100],"Our":[101],"utilizes":[103],"Generalized":[105],"Motion":[106],"Adaptation":[107],"Module":[108],"enables":[110],"independent":[111],"training,":[112],"adapting":[113],"the":[115,128,143],"corresponding":[116],"motion":[117],"condition,":[118],"which":[119,140],"then":[121],"dynamically":[122,141],"combined":[123],"during":[124,146],"inference.":[125],"imbalance":[129],"between":[130],"heterogeneous":[131],"conditioning":[132,144],"signals,":[133],"propose":[135],"adaptive":[137],"fusion":[138],"strategy,":[139],"reweights":[142],"signals":[145],"diffusion":[147,169],"sampling.":[148],"InteracTalker":[149],"successfully":[150],"unifies":[151],"these":[152],"previously":[153],"separate":[154],"tasks,":[155],"outperforming":[156,167],"prior":[157],"methods":[158],"in":[159],"generation":[163],"object-interaction":[165],"synthesis,":[166],"gesture-focused":[168],"yielding":[171],"highly":[172],"realistic,":[173],"full-body":[175],"enhanced":[178],"realism,":[179],"flexibility,":[180],"control.":[182],"(https://sreeharirajan.github.io/projects/InteracTalker/)":[183]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-12-17T00:00:00"}