{"id":"https://openalex.org/W4403998616","doi":"https://doi.org/10.1007/978-3-031-72684-2_9","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","display_name":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","publication_year":2024,"publication_date":"2024-11-02","ids":{"openalex":"https://openalex.org/W4403998616","doi":"https://doi.org/10.1007/978-3-031-72684-2_9"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-72684-2_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72684-2_9","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":["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/A5005658216","display_name":"Qilang Ye","orcid":"https://orcid.org/0009-0004-6907-702X"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qilang Ye","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103099781","display_name":"Zitong Yu","orcid":"https://orcid.org/0000-0003-0422-6616"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Yu","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037878863","display_name":"Rui Shao","orcid":"https://orcid.org/0000-0003-0090-9604"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Shao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053305389","display_name":"Xinyu Xie","orcid":"https://orcid.org/0000-0001-8582-0857"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Xie","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109615038","display_name":"Philip Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":["University of Oxford, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Cao","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005658216"],"corresponding_institution_ids":["https://openalex.org/I4396570619"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":5.3425,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.97515528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8885728120803833},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5457654595375061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4147518575191498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3946194052696228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36413830518722534},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3542312681674957},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3476179838180542},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26119858026504517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885728120803833},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5457654595375061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147518575191498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3946194052696228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36413830518722534},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3542312681674957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3476179838180542},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26119858026504517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-72684-2_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72684-2_9","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2250539671","https://openalex.org/W2580300496","https://openalex.org/W2765716052","https://openalex.org/W2904452845","https://openalex.org/W2946609015","https://openalex.org/W2952728748","https://openalex.org/W2954199749","https://openalex.org/W2964213933","https://openalex.org/W2964220823","https://openalex.org/W2966683369","https://openalex.org/W2980339970","https://openalex.org/W2989322838","https://openalex.org/W2996908057","https://openalex.org/W2998166190","https://openalex.org/W3015371781","https://openalex.org/W3034730770","https://openalex.org/W3044495139","https://openalex.org/W3083410900","https://openalex.org/W3099388488","https://openalex.org/W3135367836","https://openalex.org/W3204588463","https://openalex.org/W4214604251","https://openalex.org/W4226278401","https://openalex.org/W4304098310","https://openalex.org/W4312256574","https://openalex.org/W4312380001","https://openalex.org/W4361229539","https://openalex.org/W4361864998","https://openalex.org/W4366327919","https://openalex.org/W4367628410","https://openalex.org/W4376312115","https://openalex.org/W4378501696","https://openalex.org/W4378942464","https://openalex.org/W4380559123","https://openalex.org/W4380994269","https://openalex.org/W4384918448","https://openalex.org/W4386071707","https://openalex.org/W4386113246","https://openalex.org/W4388192054","https://openalex.org/W4388684828","https://openalex.org/W4388843160","https://openalex.org/W4389157198","https://openalex.org/W4389519587","https://openalex.org/W4394625659","https://openalex.org/W4402754220","https://openalex.org/W4402754238","https://openalex.org/W4403002096","https://openalex.org/W4403781866","https://openalex.org/W6796581206","https://openalex.org/W6855594702","https://openalex.org/W6856051742","https://openalex.org/W6859474438"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
