{"id":"https://openalex.org/W4404988225","doi":"https://doi.org/10.1109/iccv51701.2025.01956","title":"Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation","display_name":"Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404988225","doi":"https://doi.org/10.1109/iccv51701.2025.01956"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.16789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453002","display_name":"Jungeun Kim","orcid":"https://orcid.org/0009-0006-9757-7149"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungeun Kim","raw_affiliation_strings":["Yonsei University,Department of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Artificial Intelligence","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072274879","display_name":"Hyung\u2010Bae Jeon","orcid":"https://orcid.org/0000-0001-8650-5154"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongwoo Jeon","raw_affiliation_strings":["Graduate School of Information, Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information, Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771881","display_name":"Jong\u2010Seong Bae","orcid":"https://orcid.org/0000-0003-0039-4030"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongseong Bae","raw_affiliation_strings":["Yonsei University,Department of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Department of Artificial Intelligence","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635330","display_name":"Ha Young Kim","orcid":"https://orcid.org/0000-0001-5115-9984"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha Young Kim","raw_affiliation_strings":["Graduate School of Information, Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information, Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21048","last_page":"21058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9966999888420105,"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":0.9966999888420105,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9908999800682068,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/gloss","display_name":"Gloss (optics)","score":0.8343099355697632},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5712511539459229},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.5458073019981384},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.530917227268219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5275549292564392},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.5027399063110352},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14799928665161133},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12528279423713684},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06411832571029663}],"concepts":[{"id":"https://openalex.org/C143025027","wikidata":"https://www.wikidata.org/wiki/Q900581","display_name":"Gloss (optics)","level":3,"score":0.8343099355697632},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5712511539459229},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.5458073019981384},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.530917227268219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5275549292564392},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5027399063110352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14799928665161133},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12528279423713684},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06411832571029663},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2781448156","wikidata":"https://www.wikidata.org/wiki/Q1570182","display_name":"Coating","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.16789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16789","pdf_url":"https://arxiv.org/pdf/2411.16789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.16789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.16789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2411.16789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16789","pdf_url":"https://arxiv.org/pdf/2411.16789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404988225.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3119463769","https://openalex.org/W2035926194","https://openalex.org/W2514360315","https://openalex.org/W2045489541","https://openalex.org/W2134811186","https://openalex.org/W2160360150","https://openalex.org/W1985904311","https://openalex.org/W4247897165","https://openalex.org/W2358737221","https://openalex.org/W1989687946"],"abstract_inverted_index":{"Sign":[0,57],"language":[1,12,37,70,84],"translation":[2],"(SLT)":[3],"is":[4,133],"a":[5,50],"challenging":[6],"task":[7,23],"that":[8],"involves":[9],"translating":[10],"sign":[11,36,83,99],"images":[13],"into":[14],"spoken":[15,107],"language.":[16],"For":[17],"SLT":[18,53],"models":[19,71],"to":[20,39,77,102,126],"perform":[21],"this":[22],"successfully,":[24],"they":[25],"must":[26],"bridge":[27],"the":[28,63,106,122],"modality":[29],"gap":[30],"and":[31,119],"identify":[32],"subtle":[33],"variations":[34],"in":[35,130],"components":[38],"understand":[40],"their":[41],"meanings":[42],"accurately.":[43],"To":[44],"address":[45],"these":[46,95],"challenges,":[47],"we":[48,74,93],"propose":[49],"novel":[51],"gloss-free":[52],"framework":[54],"called":[55],"Multimodal":[56],"Language":[58],"Translation":[59],"(MMSLT),":[60],"which":[61],"leverages":[62],"representational":[64],"capabilities":[65],"of":[66,82,124],"off-the-shelf":[67],"multimodal":[68],"large":[69],"(MLLMs).":[72],"Specifically,":[73],"use":[75],"MLLMs":[76,125],"generate":[78],"detailed":[79],"textual":[80],"descriptions":[81],"components.":[85],"Then,":[86],"through":[87],"our":[88],"proposed":[89],"multimodal-language":[90],"pre-training":[91],"module,":[92],"integrate":[94],"description":[96],"features":[97,101],"with":[98],"video":[100],"align":[103],"them":[104],"within":[105],"sentence":[108],"space.":[109],"Our":[110],"approach":[111],"achieves":[112],"state-of-the-art":[113],"performance":[114],"on":[115],"benchmark":[116],"datasets":[117],"PHOENIX14T":[118],"CSL-Daily,":[120],"highlighting":[121],"potential":[123],"be":[127],"utilized":[128],"effectively":[129],"SLT.":[131],"Code":[132],"available":[134],"at":[135],"https://github.com/hwjeon98/MMSLT.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}