{"id":"https://openalex.org/W4413018692","doi":"https://doi.org/10.1109/fg61629.2025.11099480","title":"Visual Keyword Spotting with Multi-Encoder for MAVSR 2025","display_name":"Visual Keyword Spotting with Multi-Encoder for MAVSR 2025","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4413018692","doi":"https://doi.org/10.1109/fg61629.2025.11099480"},"language":"en","primary_location":{"id":"doi:10.1109/fg61629.2025.11099480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5064727229","display_name":"Dejun Zhang","orcid":"https://orcid.org/0000-0001-9129-534X"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejun Zhang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046221437","display_name":"Xupeng Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xupeng Jia","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056442083","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0003-4070-075X"},"institutions":[{"id":"https://openalex.org/I340842764","display_name":"Foton Motors (China)","ror":"https://ror.org/05a5w4v67","country_code":"CN","type":"company","lineage":["https://openalex.org/I340842764"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd","institution_ids":["https://openalex.org/I340842764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09073411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9890999794006348,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9810000061988831,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9620000123977661,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.875735878944397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7436093688011169},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6130155324935913},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.601581871509552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4611217677593231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3659953773021698},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34537261724472046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34474629163742065}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.875735878944397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436093688011169},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6130155324935913},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.601581871509552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611217677593231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3659953773021698},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34537261724472046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34474629163742065},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg61629.2025.11099480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1550977693","https://openalex.org/W1897240248","https://openalex.org/W2194775991","https://openalex.org/W2290318471","https://openalex.org/W2479368705","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2886945201","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2919115771","https://openalex.org/W2963608065","https://openalex.org/W2963744813","https://openalex.org/W2964171275","https://openalex.org/W3007075806","https://openalex.org/W3097777922","https://openalex.org/W3128533107","https://openalex.org/W3162293946","https://openalex.org/W4221153068","https://openalex.org/W4282946496","https://openalex.org/W4297841641","https://openalex.org/W4312638101","https://openalex.org/W4385245566","https://openalex.org/W4390874021","https://openalex.org/W4392904484","https://openalex.org/W4401991227","https://openalex.org/W4402775747","https://openalex.org/W4405709212","https://openalex.org/W4406461808","https://openalex.org/W4407774822","https://openalex.org/W4408346039","https://openalex.org/W4411245105","https://openalex.org/W6754420807","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4408353962","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539"],"abstract_inverted_index":{"This":[0],"paper":[1],"systematically":[2],"describes":[3],"the":[4,9,27,84,107,134,148,162],"Fosafer":[5],"system":[6,126],"designed":[7],"for":[8,97],"Mandarin":[10],"Audio-Visual":[11],"Speech":[12],"Recognition":[13],"(MAVSR)":[14],"Challenge":[15],"2025":[16,150],"Track":[17,22,145],"2.":[18],"The":[19,139],"purpose":[20],"of":[21,29,109,123,131,147,158],"2":[23,146],"is":[24],"to":[25,59,81,112,133],"evaluate":[26],"performance":[28],"visual":[30,50,68,91,135],"speech":[31],"analysis":[32],"systems":[33],"in":[34,43,88,144],"identifying":[35],"whether":[36],"a":[37,63,74,128,153],"speaker":[38],"has":[39,127],"pronounced":[40],"specific":[41],"keywords":[42],"silent":[44],"video":[45,64,78,86],"sequences,":[46],"also":[47],"known":[48],"as":[49],"keyword":[51,136],"spotting":[52,137],"(VKWS).":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,71,105],"propose":[58,73],"improve":[60],"VKWS":[61],"with":[62],"augmentation":[65,79],"method":[66,80,141],"and":[67,95],"multi-encoder.":[69],"Specifically,":[70],"first":[72,143],"simple":[75],"but":[76],"effective":[77],"fully":[82],"utilize":[83],"scarce":[85],"data":[87],"VKWS.":[89],"Secondly,":[90],"multi-encoders":[92],"like":[93],"Transformer":[94],"Conformer":[96],"lip":[98],"motion":[99],"feature":[100],"extraction":[101],"are":[102],"implied.":[103],"Finally,":[104],"adopt":[106],"strategy":[108],"model":[110,115],"fusion":[111],"further":[113],"enhance":[114],"performance.":[116],"Ablation":[117],"experiments":[118],"show":[119],"that":[120],"each":[121],"module":[122],"our":[124],"proposed":[125,140],"different":[129],"level":[130],"enhancement":[132],"results.":[138],"ranked":[142],"MAVSR":[149],"Challenge,":[151],"achieving":[152],"Mean":[154],"Average":[155],"Precision":[156],"(mAP)":[157],"$36.226":[159],"\\%$":[160],"on":[161],"test":[163],"dataset.":[164]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}