{"id":"https://openalex.org/W4403331867","doi":"https://doi.org/10.23919/fusion59988.2024.10706514","title":"QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models","display_name":"QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4403331867","doi":"https://doi.org/10.23919/fusion59988.2024.10706514"},"language":"en","primary_location":{"id":"doi:10.23919/fusion59988.2024.10706514","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fusion59988.2024.10706514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Information Fusion (FUSION)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.06566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375425","display_name":"Jiale Wang","orcid":"https://orcid.org/0000-0001-6530-7060"},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiale Wang","raw_affiliation_strings":["Q Team, Home Team Science and Technology Agency,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Q Team, Home Team Science and Technology Agency,Singapore","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111876288","display_name":"Gee Wah Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gee Wah Ng","raw_affiliation_strings":["Q Team, Home Team Science and Technology Agency,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Q Team, Home Team Science and Technology Agency,Singapore","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038114796","display_name":"Lee Onn Mak","orcid":null},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lee Onn Mak","raw_affiliation_strings":["Q Team, Home Team Science and Technology Agency,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Q Team, Home Team Science and Technology Agency,Singapore","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109025413","display_name":"Randall Cher","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Randall Cher","raw_affiliation_strings":["Nanyang Technological University,Department of Computer Science and Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113429980","display_name":"Ng Ding Hei Ryan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ding Hei Ryan Ng","raw_affiliation_strings":["Nanyang Technological University,Department of Computer Science and Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111362433","display_name":"Davis Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Davis Wang","raw_affiliation_strings":["Nanyang Technological University,Department of Computer Science and Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Department of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9966999888420105,"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":0.9288600087165833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642293930053711},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4613696336746216},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4438624382019043},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4358466565608978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35228776931762695},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3314833641052246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32494479417800903},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18728697299957275},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15318188071250916}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9288600087165833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642293930053711},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4613696336746216},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4438624382019043},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4358466565608978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35228776931762695},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3314833641052246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32494479417800903},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18728697299957275},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15318188071250916},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/fusion59988.2024.10706514","is_oa":false,"landing_page_url":"https://doi.org/10.23919/fusion59988.2024.10706514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Information Fusion (FUSION)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.06566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06566","pdf_url":"https://arxiv.org/pdf/2601.06566","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.06566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06566","pdf_url":"https://arxiv.org/pdf/2601.06566","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2142900973","https://openalex.org/W2425121537","https://openalex.org/W2952132648","https://openalex.org/W2964220823","https://openalex.org/W3160460845","https://openalex.org/W3161603460","https://openalex.org/W3166396011","https://openalex.org/W4224308101","https://openalex.org/W4254635861","https://openalex.org/W4292779060","https://openalex.org/W4321497840","https://openalex.org/W4361866031","https://openalex.org/W4362707064","https://openalex.org/W4366999479","https://openalex.org/W4367367040","https://openalex.org/W4382490555","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4387158702","https://openalex.org/W4388894485","https://openalex.org/W4389519587","https://openalex.org/W4390041933","https://openalex.org/W4395091069","https://openalex.org/W4402671548","https://openalex.org/W4404784276","https://openalex.org/W4405812114","https://openalex.org/W6778883912","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"This":[0,39],"paper":[1,111],"introduces":[2],"QCaption,":[3],"a":[4,22,31,132],"novel":[5],"video":[6,13,54,86,116,138],"captioning":[7,55,87,117],"and":[8,30,47,56,79,88,113,123],"Q&A":[9,57,89],"pipeline":[10],"that":[11],"enhances":[12],"analytics":[14],"by":[15],"fusing":[16],"three":[17],"models:":[18],"key":[19],"frame":[20],"extraction,":[21],"Large":[23,32],"Multimodal":[24],"Model":[25,34],"(LMM)":[26],"for":[27,36,65],"image-text":[28],"analysis,":[29],"Language":[33],"(LLM)":[35],"text":[37],"analysis.":[38],"approach":[40,135],"enables":[41],"integrated":[42],"analysis":[43],"of":[44,101,130],"text,":[45],"images,":[46],"video,":[48],"achieving":[49],"performance":[50],"improvements":[51,84],"over":[52],"existing":[53,124],"models;":[58],"all":[59],"while":[60],"remaining":[61],"fully":[62],"self-contained,":[63],"adept":[64],"on-premises":[66],"deployment.":[67],"Experimental":[68],"results":[69],"using":[70],"QCaption":[71,122,126],"demonstrated":[72],"up":[73],"to":[74,97],"$\\mathbf{4":[75,80],"4.":[76],"2":[77],"\\%}$":[78,83],"8.":[81],"9":[82],"in":[85,136],"tasks,":[90],"respectively.":[91],"Ablation":[92],"studies":[93],"were":[94],"also":[95],"performed":[96],"assess":[98],"the":[99,104,107,110,128],"role":[100],"LLM":[102],"on":[103,106],"fusion":[105,134],"results.":[108],"Moreover,":[109],"proposes":[112],"evaluates":[114],"additional":[115],"approaches,":[118],"benchmarking":[119],"them":[120],"against":[121],"methodologies.":[125],"demonstrate":[127],"potential":[129],"adopting":[131],"model":[133],"advancing":[137],"analytics.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}