{"id":"https://openalex.org/W4388196844","doi":"https://doi.org/10.1145/3607827.3616847","title":"Large Generative Models Meet Multimodal Video Intelligence","display_name":"Large Generative Models Meet Multimodal Video Intelligence","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388196844","doi":"https://doi.org/10.1145/3607827.3616847"},"language":"en","primary_location":{"id":"doi:10.1145/3607827.3616847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607827.3616847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","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/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068937750"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.2456,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53809959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9603999853134155,"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":0.9603999853134155,"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":0.9003999829292297,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.830222487449646},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7556508779525757},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6100272536277771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439335107803345},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4389289319515228},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3729386627674103},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06725254654884338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830222487449646},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7556508779525757},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6100272536277771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439335107803345},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4389289319515228},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3729386627674103},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06725254654884338}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3607827.3616847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607827.3616847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"In":[0],"this":[1],"talk,":[2],"I":[3,22,48,71],"would":[4],"like":[5],"to":[6,37,45,61,84],"share":[7],"my":[8],"recent":[9],"research":[10],"around":[11],"multimodal":[12],"video":[13],"intelligence":[14],"in":[15],"the":[16,75],"era":[17],"of":[18,55],"large":[19,58],"generative":[20],"models.":[21],"will":[23,49,72],"first":[24],"talk":[25],"about":[26],"video-language":[27],"pretraining":[28],"techniques":[29],"(All-in-one,":[30],"EgoVLP)":[31],"that":[32],"use":[33],"one":[34],"single":[35],"model":[36],"power":[38],"various":[39],"understanding":[40],"tasks":[41],"ranging":[42],"from":[43],"retrieval":[44],"QA.":[46],"Then":[47],"introduce":[50],"challenges":[51],"and":[52],"our":[53],"efforts":[54],"adapting":[56],"these":[57],"pretrained":[59],"models":[60,89],"AI":[62],"Assistant,":[63],"such":[64],"a":[65],"real-world":[66],"application":[67],"(AssistQ,":[68],"AssistGPT).":[69],"Finally":[70],"delve":[73],"into":[74],"reverse":[76],"problem":[77],"i.e.":[78],"given":[79],"open-world":[80],"textual":[81],"description,":[82],"how":[83],"generate":[85],"videos":[86],"with":[87],"diffusion":[88],"(Tune-A-Video,":[90],"Show-1).":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
