{"id":"https://openalex.org/W4406495740","doi":"https://doi.org/10.1109/bigdata62323.2024.10825195","title":"Video Content Summarization with Large Language-Vision Models","display_name":"Video Content Summarization with Large Language-Vision Models","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406495740","doi":"https://doi.org/10.1109/bigdata62323.2024.10825195"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5051356545","display_name":"Kelley Lynch","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kelley Lynch","raw_affiliation_strings":["Brandeis University,Department of Computer Science,Waltham,Massachusetts"],"affiliations":[{"raw_affiliation_string":"Brandeis University,Department of Computer Science,Waltham,Massachusetts","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035988035","display_name":"Bohan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Jiang","raw_affiliation_strings":["Brandeis University,Department of Computer Science,Waltham,Massachusetts"],"affiliations":[{"raw_affiliation_string":"Brandeis University,Department of Computer Science,Waltham,Massachusetts","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115913900","display_name":"Ben Lambright","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Lambright","raw_affiliation_strings":["Brandeis University,Department of Computer Science,Waltham,Massachusetts"],"affiliations":[{"raw_affiliation_string":"Brandeis University,Department of Computer Science,Waltham,Massachusetts","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041605161","display_name":"Kyeongmin Rim","orcid":"https://orcid.org/0000-0001-8688-4086"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyeongmin Rim","raw_affiliation_strings":["Brandeis University,Department of Computer Science,Waltham,Massachusetts"],"affiliations":[{"raw_affiliation_string":"Brandeis University,Department of Computer Science,Waltham,Massachusetts","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012141433","display_name":"James Pustejovsky","orcid":"https://orcid.org/0000-0003-2233-9761"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Pustejovsky","raw_affiliation_strings":["Brandeis University,Department of Computer Science,Waltham,Massachusetts"],"affiliations":[{"raw_affiliation_string":"Brandeis University,Department of Computer Science,Waltham,Massachusetts","institution_ids":["https://openalex.org/I6902469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051356545"],"corresponding_institution_ids":["https://openalex.org/I6902469"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70846229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2456","last_page":"2463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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":0.9908999800682068,"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/automatic-summarization","display_name":"Automatic summarization","score":0.949690580368042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749806046485901},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6255632042884827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49935364723205566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4707173705101013},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41553056240081787},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3712158799171448},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32811617851257324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0616915225982666}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.949690580368042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749806046485901},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6255632042884827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49935364723205566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4707173705101013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41553056240081787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3712158799171448},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32811617851257324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0616915225982666},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2061504941","https://openalex.org/W2101105183","https://openalex.org/W2936695845","https://openalex.org/W2954911567","https://openalex.org/W3174544005","https://openalex.org/W4311000453","https://openalex.org/W4322718191","https://openalex.org/W4387076074","https://openalex.org/W4402111785","https://openalex.org/W4402671606","https://openalex.org/W4403791714","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6856656568"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"We":[0,61],"present":[1],"a":[2],"modular":[3],"pipeline":[4,64],"for":[5,19,22,26,31,46,93,104,112],"summarizing":[6],"broadcast":[7],"news":[8],"videos":[9],"using":[10,40],"large":[11],"language":[12],"and":[13,29,54,86,108],"vision":[14],"models,":[15],"specifically":[16],"integrating":[17],"Whisper":[18],"ASR,":[20],"TransNetV2":[21],"shot":[23],"segmentation,":[24],"LLaVA":[25],"image":[27,55],"captioning,":[28],"LLaMA":[30],"generating":[32],"structured":[33],"summaries.":[34],"Implemented":[35],"within":[36],"the":[37,41,88,99,110],"CLAMS":[38],"platform":[39],"Multimedia":[42],"Interchange":[43],"Format":[44],"(MMIF)":[45],"component":[47],"interoperability,":[48],"our":[49,63],"approach":[50],"combines":[51],"ASR":[52],"transcriptions":[53],"captions":[56],"to":[57],"enhance":[58],"metadata":[59,106],"extraction.":[60],"evaluated":[62],"with":[65,83],"automated":[66,84],"metrics":[67,85],"based":[68],"on":[69],"user-generated":[70],"Youtube":[71],"video":[72,105,114],"descriptons":[73],"as":[74,76],"well":[75],"human":[77,91],"assessments.":[78],"Our":[79],"analysis":[80],"highlights":[81],"challenges":[82],"emphasizes":[87],"value":[89],"of":[90,101],"evaluation":[92],"nuanced":[94],"assessment.":[95],"This":[96],"work":[97],"demonstrates":[98],"effectiveness":[100],"multimodal":[102],"summarization":[103],"extraction":[107],"paves":[109],"way":[111],"enhanced":[113],"accessibility.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}