{"id":"https://openalex.org/W4412876911","doi":"https://doi.org/10.1145/3711896.3737195","title":"Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion","display_name":"Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876911","doi":"https://doi.org/10.1145/3711896.3737195"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/A5101703871","display_name":"Yu Sun","orcid":"https://orcid.org/0009-0009-4419-7611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Sun","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-4419-7611","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100979407","display_name":"Yin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Li","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-4302-0592","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102722648","display_name":"Ruixiao Sun","orcid":"https://orcid.org/0000-0001-6905-1242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruixiao Sun","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6905-1242","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085688294","display_name":"Chunhui Liu","orcid":"https://orcid.org/0000-0001-6707-5187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhui Liu","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6707-5187","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994055","display_name":"Fangming Zhou","orcid":"https://orcid.org/0000-0001-8529-9491"},"institutions":[{"id":"https://openalex.org/I2801787653","display_name":"Beijing Dance Academy","ror":"https://ror.org/02g3wgj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I2801787653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Zhou","raw_affiliation_strings":["ByteDance Inc., Beijing, Beijing, USA"],"raw_orcid":"https://orcid.org/0000-0001-8529-9491","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, Beijing, USA","institution_ids":["https://openalex.org/I2801787653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062939397","display_name":"Ze Jin","orcid":"https://orcid.org/0000-0002-5882-6580"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ze Jin","raw_affiliation_strings":["ByteDance Inc., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5882-6580","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linjie Wang","orcid":"https://orcid.org/0009-0001-1336-2719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Wang","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-1336-2719","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006504972","display_name":"Xiang Shen","orcid":"https://orcid.org/0000-0002-6457-0411"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Shen","raw_affiliation_strings":["ByteDance Inc., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6457-0411","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuolin Hao","orcid":"https://orcid.org/0009-0007-7423-3172"},"institutions":[{"id":"https://openalex.org/I2801787653","display_name":"Beijing Dance Academy","ror":"https://ror.org/02g3wgj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I2801787653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuolin Hao","raw_affiliation_strings":["ByteDance Inc., Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7423-3172","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, Beijing, China","institution_ids":["https://openalex.org/I2801787653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013831155","display_name":"Hongyu Xiong","orcid":"https://orcid.org/0000-0001-6699-5192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Xiong","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6699-5192","affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4872","last_page":"4881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.685468316078186},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5217812657356262},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.498288631439209},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4885936379432678},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4516366124153137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42725926637649536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002893567085266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34341228008270264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32664787769317627},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12983936071395874},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09673875570297241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685468316078186},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5217812657356262},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.498288631439209},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4885936379432678},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4516366124153137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42725926637649536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002893567085266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34341228008270264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32664787769317627},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12983936071395874},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09673875570297241},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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":17,"referenced_works":["https://openalex.org/W1580375566","https://openalex.org/W2027858833","https://openalex.org/W2056707879","https://openalex.org/W2072782484","https://openalex.org/W2117763124","https://openalex.org/W2144452292","https://openalex.org/W2151596305","https://openalex.org/W2167595980","https://openalex.org/W2171671120","https://openalex.org/W2612560781","https://openalex.org/W2956371155","https://openalex.org/W2963341956","https://openalex.org/W2986514296","https://openalex.org/W4385128589","https://openalex.org/W4401863765","https://openalex.org/W4401864059","https://openalex.org/W6682291466"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W2106335228","https://openalex.org/W2105076537","https://openalex.org/W2028371633","https://openalex.org/W2071315630","https://openalex.org/W2038905316","https://openalex.org/W2096375461","https://openalex.org/W4322096525","https://openalex.org/W2183768935"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
