{"id":"https://openalex.org/W4407129623","doi":"https://doi.org/10.1109/cbmi62980.2024.10859201","title":"Elevating Video Retrieval Capabilities: A Cross-Modal Approach Utilizing Text and Image Generative Models","display_name":"Elevating Video Retrieval Capabilities: A Cross-Modal Approach Utilizing Text and Image Generative Models","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4407129623","doi":"https://doi.org/10.1109/cbmi62980.2024.10859201"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi62980.2024.10859201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5011544913","display_name":"Kazuya Ueki","orcid":"https://orcid.org/0009-0005-1691-1858"},"institutions":[{"id":"https://openalex.org/I63030401","display_name":"Meisei University","ror":"https://ror.org/022yhjq53","country_code":"JP","type":"education","lineage":["https://openalex.org/I63030401"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuya Ueki","raw_affiliation_strings":["Meisei University,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Meisei University,Tokyo,Japan","institution_ids":["https://openalex.org/I63030401"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101753127","display_name":"Yuma Suzuki","orcid":"https://orcid.org/0000-0003-4542-6243"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Suzuki","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028567449","display_name":"Haruki Sato","orcid":"https://orcid.org/0000-0001-7143-2781"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Sato","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005023805","display_name":"Takayuki Hori","orcid":"https://orcid.org/0000-0001-8232-5922"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Hori","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109678052","display_name":"T. Takada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Takada","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042033475","display_name":"Hiroki Takushima","orcid":"https://orcid.org/0009-0006-2041-8713"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Takushima","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392251","display_name":"Hayato Tanoue","orcid":"https://orcid.org/0009-0007-7050-035X"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Tanoue","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102610106","display_name":"Aiswariya Manoj Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aiswariya Manoj Kumar","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009185928","display_name":"Hiroki Nishihara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Nishihara","raw_affiliation_strings":["SoftBank Corp.,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SoftBank Corp.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210120159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5011544913"],"corresponding_institution_ids":["https://openalex.org/I63030401"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27676692,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9650999903678894,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9650999903678894,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9575999975204468,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9265000224113464,"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":0.7889499068260193},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7263416051864624},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6915478110313416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5638135075569153},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4627893269062042},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45302245020866394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3624928593635559},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.328612744808197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3248494267463684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889499068260193},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7263416051864624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6915478110313416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638135075569153},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4627893269062042},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45302245020866394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3624928593635559},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.328612744808197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3248494267463684},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi62980.2024.10859201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325763","display_name":"Telecommunications Advancement Foundation","ror":"https://ror.org/05y77zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2914699769","https://openalex.org/W2963017553","https://openalex.org/W2989322838","https://openalex.org/W4312933868","https://openalex.org/W6775142626","https://openalex.org/W6809140504","https://openalex.org/W6810452849","https://openalex.org/W6846007759","https://openalex.org/W6846700717"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3211753092","https://openalex.org/W2386000789"],"abstract_inverted_index":{"In":[0,67],"this":[1],"study,":[2],"we":[3,70],"propose":[4],"a":[5,35,72],"new":[6],"methodology":[7],"to":[8,30,64,91,118],"enhance":[9],"the":[10,77,83,93,101],"accuracy":[11],"of":[12,26,39,95,100,107,113],"video":[13,58,74],"retrieval":[14],"by":[15],"integrating":[16],"rapidly":[17],"developing":[18],"text":[19],"and":[20,44,89,109],"image":[21,110],"generation":[22,111],"technologies.":[23],"The":[24,98],"core":[25],"our":[27,68,96],"study":[28],"is":[29,61,81],"transform":[31],"search":[32,40,65,123],"queries":[33],"into":[34,47],"more":[36,48],"diverse":[37],"range":[38],"requirements":[41],"using":[42,52],"ChatGPT,":[43],"convert":[45],"them":[46],"specific":[49],"visual":[50],"features":[51],"stable":[53,114],"diffusion,":[54],"thereby":[55],"accurately":[56],"retrieving":[57],"content":[59],"that":[60],"highly":[62,121],"relevant":[63,122],"queries.":[66,128],"experiments,":[69],"used":[71],"large-scale":[73],"dataset":[75],"from":[76],"TRECVID":[78],"benchmark,":[79],"which":[80],"considered":[82],"industry":[84],"standard":[85],"as":[86],"concerns":[87],"diversity":[88],"inclusiveness,":[90],"validate":[92],"effectiveness":[94],"method.":[97],"combination":[99],"advanced":[102],"natural":[103],"language":[104],"understanding":[105],"capabilities":[106],"ChatGPT":[108],"prowess":[112],"diffusion":[115],"enabled":[116],"us":[117],"successfully":[119],"retrieve":[120],"results,":[124],"even":[125],"for":[126],"complicated":[127]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}