{"id":"https://openalex.org/W4415316197","doi":"https://doi.org/10.1007/978-981-95-7251-9_21","title":"MAGIC-Enhanced Keyword Prompting for\u00a0Zero-Shot Audio Captioning with\u00a0CLIP Models","display_name":"MAGIC-Enhanced Keyword Prompting for\u00a0Zero-Shot Audio Captioning with\u00a0CLIP Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415316197","doi":"https://doi.org/10.1007/978-981-95-7251-9_21"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-7251-9_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-7251-9_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018194367","display_name":"Vijay Govindarajan","orcid":"https://orcid.org/0000-0001-6046-5262"},"institutions":[{"id":"https://openalex.org/I4210106647","display_name":"Expedia Group (United States)","ror":"https://ror.org/01sh85g09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106647"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Govindarajan","raw_affiliation_strings":["Expedia Group, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Expedia Group, Seattle, USA","institution_ids":["https://openalex.org/I4210106647","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103881379","display_name":"Pratik Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100621","display_name":"University of Fairfax","ror":"https://ror.org/00v23bh67","country_code":"US","type":"education","lineage":["https://openalex.org/I4210100621"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Patel","raw_affiliation_strings":["California Universities of Management and Sciences, Fairfax, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Universities of Management and Sciences, Fairfax, USA","institution_ids":["https://openalex.org/I4210100621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024415135","display_name":"Sahil Tripathi","orcid":null},"institutions":[{"id":"https://openalex.org/I19716509","display_name":"Jamia Hamdard","ror":"https://ror.org/03dwxvb85","country_code":"IN","type":"education","lineage":["https://openalex.org/I19716509"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sahil Tripathi","raw_affiliation_strings":["Jamia Hamdard, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jamia Hamdard, New Delhi, India","institution_ids":["https://openalex.org/I19716509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777464","display_name":"Md Azizul Hoque","orcid":"https://orcid.org/0000-0002-7778-9009"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Md Azizul Hoque","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076626481","display_name":"Gautam Siddharth Kashyap","orcid":"https://orcid.org/0000-0003-2140-9617"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Gautam Siddharth Kashyap","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076626481"],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02053915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9739999771118164,"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":0.9718999862670898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9056000113487244},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5787000060081482},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.4611999988555908},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.3474999964237213}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9056000113487244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373000025749207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.59579998254776},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.3474999964237213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-981-95-7251-9_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-7251-9_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2509.12591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12591","pdf_url":"https://arxiv.org/pdf/2509.12591","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12591","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12591","pdf_url":"https://arxiv.org/pdf/2509.12591","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-18T00:00:00"}
