{"id":"https://openalex.org/W7160307797","doi":"https://doi.org/10.1109/wacv61042.2026.00134","title":"Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space","display_name":"Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160307797","doi":"https://doi.org/10.1109/wacv61042.2026.00134"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00134","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":"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/A5111343966","display_name":"Aashish Chandra K","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aashish Chandra K","raw_affiliation_strings":["BITS Pilani,Machine Intelligence Group,Department of CS&IS,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Machine Intelligence Group,Department of CS&IS,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135310279","display_name":"Aashutosh A V","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aashutosh A V","raw_affiliation_strings":["BITS Pilani,Machine Intelligence Group,Department of CS&IS,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Machine Intelligence Group,Department of CS&IS,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135357828","display_name":"Abhijit Das","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhijit Das","raw_affiliation_strings":["BITS Pilani,Machine Intelligence Group,Department of CS&IS,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS Pilani,Machine Intelligence Group,Department of CS&IS,India","institution_ids":["https://openalex.org/I74796645"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74796645"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52158783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1314","last_page":"1323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7943000197410583,"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/T11448","display_name":"Face recognition and analysis","score":0.7943000197410583,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13779999315738678,"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/T10860","display_name":"Speech and Audio Processing","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/face","display_name":"Face (sociological concept)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.29989999532699585},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2791000008583069},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.260699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5228999853134155},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24979999661445618},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.24969999492168427},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.24899999797344208}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00134","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2948978827","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2981087920","https://openalex.org/W2981767644","https://openalex.org/W3034192160","https://openalex.org/W3081492798","https://openalex.org/W3187364420","https://openalex.org/W3194357576","https://openalex.org/W3197199219","https://openalex.org/W3197273793","https://openalex.org/W3204680331","https://openalex.org/W3205644108","https://openalex.org/W4247405818","https://openalex.org/W4312933868","https://openalex.org/W4386072021","https://openalex.org/W4390872769","https://openalex.org/W4394597549","https://openalex.org/W4401807241","https://openalex.org/W4402112533","https://openalex.org/W4402727013","https://openalex.org/W4402727776"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,14,21,24,28],"novel":[3],"approach":[4],"for":[5,65,79,100],"generating":[6],"realistic":[7],"speaking":[8],"and":[9,17,27,40,47,63,68,103,108,123],"talking":[10],"faces":[11],"by":[12],"synthesizing":[13],"person\u2019s":[15],"voice":[16,25,42],"facial":[18],"movements":[19],"from":[20],"static":[22],"image,":[23,39],"profile,":[26],"target":[29],"text.":[30],"The":[31,73],"model":[32,120],"encodes":[33],"the":[34,37,41,55,66,81,86,94,114,124],"prompt/driving":[35],"text,":[36],"driving":[38],"profile":[43],"of":[44,97,116],"an":[45],"individual":[46],"then":[48],"combines":[49],"them":[50,53],"to":[51,54,59,93],"pass":[52],"multi-entangled":[56,74],"latent":[57,75],"space":[58,76],"foster":[60],"key-value":[61],"pairs":[62],"queries":[64],"audio":[67,102],"video":[69,104],"modality":[70,99],"generation":[71],"pipeline.":[72],"is":[77],"responsible":[78],"establishing":[80],"spatiotemporal":[82],"person-specific":[83],"features":[84,90],"between":[85],"modalities.":[87],"Further,":[88],"entangled":[89],"are":[91],"passed":[92],"respective":[95],"decoder":[96],"each":[98],"output":[101],"generation.":[105],"Our":[106],"experiments":[107],"analysis":[109],"through":[110],"standard":[111],"metrics":[112],"demonstrate":[113],"effectiveness":[115],"our":[117],"model.":[118],"All":[119],"checkpoints,":[121],"code,":[122],"proposed":[125],"dataset":[126],"can":[127],"be":[128],"found":[129],"at":[130],"https://github.com/narratingForYou/NarratingForYou.":[131]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}