{"id":"https://openalex.org/W4403791531","doi":"https://doi.org/10.1145/3664647.3689175","title":"Tutorial: Large Language-Vision Model in Society","display_name":"Tutorial: Large Language-Vision Model in Society","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791531","doi":"https://doi.org/10.1145/3664647.3689175"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3689175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5038563167","display_name":"Kaicheng Yu","orcid":"https://orcid.org/0000-0002-0186-3399"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaicheng Yu","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077948412","display_name":"Zhuang Shao","orcid":"https://orcid.org/0000-0001-7824-0985"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhuang Shao","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, United Kingdom","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043510420","display_name":"Siyuan Qi","orcid":"https://orcid.org/0000-0002-4070-733X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Qi","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101979289","display_name":"Dongfang Liu","orcid":"https://orcid.org/0000-0001-6995-4775"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038563167"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":11.7289,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.98123696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11298","last_page":"11299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12542","display_name":"Second Language Learning and Teaching","score":0.1062999963760376,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12542","display_name":"Second Language Learning and Teaching","score":0.1062999963760376,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6879774928092957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4642760157585144},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32719117403030396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3264450430870056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879774928092957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4642760157585144},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32719117403030396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264450430870056}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3689175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"tutorial":[1,62,124],"\"Large":[2],"Vision-Language":[3],"Model":[4],"in":[5,110,135],"the":[6,65,105,123,128,136],"Society\"":[7],"aims":[8],"to":[9,30,39,83,113],"provide":[10],"a":[11,94],"comprehensive":[12],"overview":[13],"of":[14,19,67],"state-of-the-art":[15,70],"techniques":[16],"and":[17,27,34,51,59,77,86,102,108,120,133],"applications":[18],"large":[20],"vision-language":[21,68],"models":[22],"(LVLMs),":[23],"which":[24],"integrate":[25],"visual":[26],"textual":[28],"data":[29],"transform":[31],"multimedia":[32,129],"research":[33],"applications.":[35],"LVLMs":[36],"are":[37],"poised":[38],"revolutionize":[40],"domains":[41],"such":[42],"as":[43],"content":[44,56],"creation,":[45],"social":[46],"media":[47],"analysis,":[48,57],"education,":[49],"healthcare,":[50],"entertainment":[52],"by":[53],"enabling":[54],"sophisticated":[55],"retrieval,":[58],"generation.":[60],"This":[61],"will":[63,98,125],"cover":[64],"fundamentals":[66],"integration,":[69],"models,":[71],"training":[72],"techniques,":[73],"applications,":[74],"ethical":[75],"considerations,":[76],"future":[78],"directions.":[79],"It":[80],"is":[81],"designed":[82],"be":[84],"educational":[85],"instructive,":[87],"providing":[88],"an":[89],"in-depth":[90],"introduction":[91],"rather":[92],"than":[93],"cursory":[95],"survey.":[96],"Attendees":[97],"gain":[99],"practical":[100],"skills,":[101],"insights":[103],"into":[104],"latest":[106],"research,":[107],"engage":[109],"interactive":[111],"sessions":[112],"reinforce":[114],"learning.":[115],"By":[116],"addressing":[117],"both":[118],"technical":[119],"societal":[121],"aspects,":[122],"significantly":[126],"benefit":[127],"community,":[130],"driving":[131],"innovation":[132],"progress":[134],"field.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}