{"id":"https://openalex.org/W7131669378","doi":"https://doi.org/10.1007/s44443-026-00481-4","title":"VSMatch-Lip: a visual-semantic matching framework for zero-shot lip reading","display_name":"VSMatch-Lip: a visual-semantic matching framework for zero-shot lip reading","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131669378","doi":"https://doi.org/10.1007/s44443-026-00481-4"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00481-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00481-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00481-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126856859","display_name":"Jixia Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Jixia Shen","raw_affiliation_strings":["School of Mechanical Engineering, Tianjin University, 300354, Tianjin, China","Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0005-5475-7759","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tianjin University, 300354, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126861562","display_name":"Hao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","School of Advanced Manufacturing and Robotics, Peking University, 100871, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3038-4679","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"School of Advanced Manufacturing and Robotics, Peking University, 100871, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126863708","display_name":"Xingyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":true,"raw_author_name":"Xingyu Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-684X","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126933041","display_name":"Yakun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Yakun Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5829-1371","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086000146","display_name":"Changyan Zheng","orcid":"https://orcid.org/0000-0002-2088-9308"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyan Zheng","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","High-tech Institute, 261000, Weifang, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-2088-9308","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"High-tech Institute, 261000, Weifang, Shandong, China","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126925819","display_name":"Liang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Liang Xie","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8286-6785","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126856903","display_name":"Zhibin Song","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Song","raw_affiliation_strings":["School of Mechanical Engineering, Tianjin University, 300354, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-3715-2003","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tianjin University, 300354, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126904012","display_name":"Erwei Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Erwei Yin","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2147-9888","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences, 100071, Beijing, China","institution_ids":["https://openalex.org/I2802541053"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, 300450, Tianjin, China","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126863708"],"corresponding_institution_ids":["https://openalex.org/I2802541053","https://openalex.org/I4210164862"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19249012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9833999872207642,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9833999872207642,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.0066999997943639755,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7469000220298767},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6148999929428101},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46549999713897705},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43709999322891235}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7469000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312999725341797},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6148999929428101},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.49570000171661377},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46549999713897705},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43709999322891235},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00481-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00481-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c1c6b18c45404addafc7031857aa5125","is_oa":true,"landing_page_url":"https://doaj.org/article/c1c6b18c45404addafc7031857aa5125","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 4 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00481-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00481-4","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.575128972530365}],"awards":[{"id":"https://openalex.org/G5931773243","display_name":null,"funder_award_id":"62332019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6231997530","display_name":null,"funder_award_id":"20240484513","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2098411764","https://openalex.org/W2128532956","https://openalex.org/W2171061940","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2398118205","https://openalex.org/W2400717490","https://openalex.org/W2552383788","https://openalex.org/W2802223794","https://openalex.org/W2890952074","https://openalex.org/W2893950723","https://openalex.org/W2897492880","https://openalex.org/W2924476266","https://openalex.org/W2963270153","https://openalex.org/W2963283377","https://openalex.org/W2963446712","https://openalex.org/W2963499153","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2996952156","https://openalex.org/W3003241499","https://openalex.org/W3016011581","https://openalex.org/W3119418740","https://openalex.org/W3171007011","https://openalex.org/W3197875592","https://openalex.org/W3213454282","https://openalex.org/W4225299282","https://openalex.org/W4295138011","https://openalex.org/W4390685975","https://openalex.org/W4399541983","https://openalex.org/W4402176064","https://openalex.org/W4402696041","https://openalex.org/W4402917184","https://openalex.org/W4408743015"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Lip":[1],"reading":[2,247],"interprets":[3],"speech":[4],"from":[5],"visual":[6,67,122],"lip":[7,63,246],"movements,":[8],"offering":[9],"a":[10,49,66,72,97,132,148,167,203,237],"vital":[11],"complement":[12],"to":[13,30,86,117,157],"audio-based":[14],"recognition":[15],"in":[16,58,95,121,218],"challenging":[17],"acoustic":[18],"environments.":[19],"However,":[20],"existing":[21],"models":[22],"rely":[23],"on":[24,80,178,184,207,243],"supervised,":[25],"closed-set":[26],"classification":[27],"and":[28,135,163,233],"fail":[29],"recognize":[31],"out-of-vocabulary":[32],"words,":[33],"severely":[34],"limiting":[35],"their":[36],"practical":[37],"application.":[38],"To":[39,140,222],"address":[40],"this":[41,81,143,185,228],"zero-shot":[42],"learning":[43,151],"(ZSL)":[44],"challenge,":[45],"we":[46,146,170],"propose":[47],"VSMatch-Lip,":[48],"non-generative":[50],"visual-semantic":[51],"matching":[52,144,240],"framework.":[53],"Our":[54],"approach":[55],"is":[56,83,229],"grounded":[57],"the":[59,114,119,125,159,173,211,223,230],"insight":[60],"that":[61,102,188],"while":[62,124],"movements":[64],"represent":[65],"manifestation":[68],"of":[69,225,236],"phonetics,":[70],"providing":[71],"strong":[73],"physical":[74],"correlation":[75,82],"for":[76,138],"generalization,":[77],"relying":[78],"solely":[79],"insufficient":[84],"due":[85],"ambiguities":[87],"like":[88],"homophones.":[89],"Therefore,":[90],"our":[91,226],"core":[92],"innovation":[93],"lies":[94],"introducing":[96],"multi-source":[98],"fused":[99],"semantic":[100,126],"representation":[101],"synergistically":[103],"integrates":[104],"lexical":[105],"meaning":[106],"with":[107,153],"powerful":[108],"phonetic":[109,115],"cues.":[110],"This":[111],"design":[112,147],"allows":[113],"component":[116,127],"ground":[118],"alignment":[120],"articulation,":[123],"provides":[128],"crucial":[129],"disambiguation,":[130],"creating":[131],"more":[133],"robust":[134],"discriminative":[136],"target":[137],"matching.":[139],"effectively":[141],"optimize":[142],"process,":[145],"tailored":[149],"contrastive":[150],"framework":[152,242],"specialized":[154],"optimization":[155],"strategies":[156],"tackle":[158],"large":[160],"intra-class":[161],"variance":[162],"training":[164],"instability.":[165],"As":[166],"key":[168],"contribution,":[169],"also":[171],"establish":[172],"first":[174,231],"comprehensive":[175],"ZSL":[176,241],"benchmark":[177,186],"large-scale,":[179,244],"in-the-wild":[180,245],"datasets.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[187],"VSMatch-Lip":[189],"achieves":[190],"state-of-the-art":[191],"performance,":[192],"consistently":[193],"outperforming":[194],"all":[195],"baselines,":[196],"including":[197],"contemporary":[198],"generative":[199,213],"models.":[200],"Notably,":[201],"under":[202],"19:1":[204],"seen-to-unseen":[205],"ratio":[206],"LRW,":[208],"it":[209],"surpasses":[210],"strongest":[212],"baseline":[214],"by":[215],"nearly":[216],"9%":[217],"Top-1":[219],"unseen":[220],"accuracy.":[221],"best":[224],"knowledge,":[227],"successful":[232],"rigorous":[234],"validation":[235],"non-generative,":[238],"direct":[239],"benchmarks.":[248]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-27T00:00:00"}