{"id":"https://openalex.org/W4200118469","doi":"https://doi.org/10.1145/3490035.3490286","title":"Translating sign language videos to talking faces","display_name":"Translating sign language videos to talking faces","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4200118469","doi":"https://doi.org/10.1145/3490035.3490286"},"language":"en","primary_location":{"id":"doi:10.1145/3490035.3490286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5061879263","display_name":"Seshadri Mazumder","orcid":null},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Seshadri Mazumder","raw_affiliation_strings":["International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660270","display_name":"Rudrabha Mukhopadhyay","orcid":"https://orcid.org/0009-0000-6628-7065"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rudrabha Mukhopadhyay","raw_affiliation_strings":["International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["University of Bath, Bath, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Bath, Bath, United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Gachibowli, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I188963388"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061879263"],"corresponding_institution_ids":["https://openalex.org/I188963388"],"apc_list":null,"apc_paid":null,"fwci":0.6525,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69957245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.887072741985321},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.7545783519744873},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6742327213287354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5989178419113159},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.513587474822998},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.5055010318756104},{"id":"https://openalex.org/keywords/language-interpretation","display_name":"Language interpretation","score":0.49353229999542236},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49338069558143616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47408926486968994},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4654444456100464},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42526862025260925},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4167099595069885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32099753618240356},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25127020478248596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17580005526542664},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.1537015438079834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887072741985321},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.7545783519744873},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6742327213287354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5989178419113159},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.513587474822998},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.5055010318756104},{"id":"https://openalex.org/C72280650","wikidata":"https://www.wikidata.org/wiki/Q210439","display_name":"Language interpretation","level":3,"score":0.49353229999542236},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49338069558143616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47408926486968994},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4654444456100464},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42526862025260925},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4167099595069885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32099753618240356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25127020478248596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17580005526542664},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.1537015438079834},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490035.3490286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2013148829","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2766531849","https://openalex.org/W2799020610","https://openalex.org/W2896457183","https://openalex.org/W2941870244","https://openalex.org/W2963524571","https://openalex.org/W2970756316","https://openalex.org/W2981767644","https://openalex.org/W3034765865","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3105763085","https://openalex.org/W3161569725","https://openalex.org/W4234518198","https://openalex.org/W4299816210"],"related_works":["https://openalex.org/W2794385750","https://openalex.org/W1498547796","https://openalex.org/W2590273899","https://openalex.org/W220928500","https://openalex.org/W4200549146","https://openalex.org/W2348960846","https://openalex.org/W4248380062","https://openalex.org/W2150892388","https://openalex.org/W2470351710","https://openalex.org/W3176887423"],"abstract_inverted_index":{"Communication":[0],"with":[1,199],"the":[2,8,15,20,46,63,87,117,138,144,153,157,165,211],"deaf":[3],"community":[4],"relies":[5],"profoundly":[6],"on":[7,86,112,143,147],"interpretation":[9],"of":[10,19,156,194],"sign":[11,24,48,94,126,202],"languages":[12,95],"performed":[13],"by":[14,52,132,160,168,183],"signers.":[16],"In":[17,41],"light":[18],"recent":[21],"breakthroughs":[22],"in":[23,81,220],"language":[25,49,58,127,134,203],"translations,":[26],"we":[27,32,44,115],"propose":[28,120],"a":[29,67,72,75,121,133,175,214],"pipeline":[30,182,191],"that":[31,69,90,152],"term":[33],"\"Translating":[34],"Sign":[35],"Language":[36],"Videos":[37],"to":[38,56,65,77,92,96,124,136,178],"Talking":[39],"Faces\".":[40],"this":[42,208],"context,":[43],"improve":[45,57],"existing":[47,187],"translation":[50,88,154,162],"systems":[51,89],"using":[53],"POS":[54],"tags":[55],"modeling.":[59],"We":[60,84,104,119,172],"further":[61],"extend":[62],"challenge":[64],"develop":[66],"system":[68],"can":[70,217],"interpret":[71],"video":[73,216],"from":[74,201],"signer":[76],"an":[78,100],"avatar":[79],"speaking":[80],"spoken":[82],"languages.":[83],"focus":[85],"attempt":[91],"translate":[93,125],"text":[97,130,177],"without":[98],"glosses,":[99],"expensive":[101],"annotation":[102],"form.":[103],"critically":[105],"analyze":[106],"two":[107],"state-of-the-art":[108,166],"architectures,":[109],"and":[110,213],"based":[111],"their":[113],"limitations,":[114],"improvise":[116],"systems.":[118],"two-stage":[122],"approach":[123],"into":[128],"intermediate":[129],"followed":[131],"model":[135,163],"get":[137],"final":[139],"predictions.":[140],"Quantitative":[141],"evaluations":[142],"challenging":[145],"benchmarks":[146],"RWTH-PHOENIX-Weather":[148],"2014":[149],"T":[150],"show":[151],"accuracy":[155],"texts":[158],"generated":[159],"our":[161],"improves":[164],"models":[167],"approximately":[169],"3":[170],"points.":[171],"then":[173],"build":[174],"working":[176],"talking":[179,196],"face":[180,197],"generation":[181],"bringing":[184],"together":[185],"multiple":[186],"modules.":[188],"The":[189],"overall":[190],"is":[192],"capable":[193],"generating":[195],"videos":[198],"speech":[200],"poses.":[204],"Additional":[205],"materials":[206],"about":[207],"project":[209],"including":[210],"codes":[212],"demo":[215],"be":[218],"found":[219],"https://seshadri-c.github.io/SLV2TF/":[221]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
