{"id":"https://openalex.org/W4417073196","doi":"https://doi.org/10.1145/3743093.3770993","title":"Can Multimodal Large Language Models Understand Human Values in Videos?","display_name":"Can Multimodal Large Language Models Understand Human Values in Videos?","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073196","doi":"https://doi.org/10.1145/3743093.3770993"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Yuchen Wang","orcid":"https://orcid.org/0009-0002-0778-2183"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Wang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0778-2183","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Qiu","orcid":"https://orcid.org/0009-0000-3803-2030"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Qiu","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3803-2030","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076422515","display_name":"He Chang","orcid":"https://orcid.org/0000-0002-7203-0677"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Chang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7203-0677","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195"},"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":false,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5573-6195","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019100110","display_name":"Zhulin Tao","orcid":"https://orcid.org/0000-0001-9011-8464"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhulin Tao","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9011-8464","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047161111","display_name":"Libiao Jin","orcid":"https://orcid.org/0000-0003-4530-2996"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libiao Jin","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4530-2996","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":2,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.51419997215271,"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":0.51419997215271,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.05000000074505806,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.043699998408555984,"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/value","display_name":"Value (mathematics)","score":0.5353999733924866},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4909999966621399},{"id":"https://openalex.org/keywords/human-language","display_name":"Human language","score":0.4291999936103821},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.392300009727478},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395999789237976},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4189999997615814},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C2988948121","wikidata":"https://www.wikidata.org/wiki/Q194112","display_name":"Human values","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C3019207227","wikidata":"https://www.wikidata.org/wiki/Q10883614","display_name":"Human life","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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":8,"referenced_works":["https://openalex.org/W1986829999","https://openalex.org/W4402727885","https://openalex.org/W4404780769","https://openalex.org/W4407049645","https://openalex.org/W4409253869","https://openalex.org/W4413147124","https://openalex.org/W4415798317","https://openalex.org/W4416037051"],"related_works":[],"abstract_inverted_index":{"Human":[0],"values":[1,65,87],"are":[2],"core":[3],"principles":[4],"to":[5,83,107],"determine":[6],"what":[7],"is":[8,38],"right,":[9],"desirable,":[10],"and":[11,15,116,120,148],"important":[12],"for":[13,54,61,152],"individuals":[14],"societies.":[16],"The":[17,43],"deep":[18],"integration":[19],"of":[20,45,146],"large":[21,47],"language":[22,48],"models":[23,49],"(LLMs)":[24],"into":[25,142],"human":[26,64,86,114],"life":[27],"has":[28],"facilitated":[29],"their":[30,81,118],"remarkable":[31],"performance":[32],"in":[33,40,66,89,155],"value":[34,56,144],"understanding.":[35,57],"Multimodal":[36],"content":[37],"rich":[39],"value-laden":[41],"information.":[42],"development":[44],"multimodal":[46,55],"(MLLMs)":[50],"provides":[51],"new":[52],"perspectives":[53],"However,":[58],"MLLMs\u2019":[59],"capacity":[60],"understanding":[62,145],"basic":[63],"the":[67,98,124,128,143],"video":[68,100],"domain":[69],"remains":[70],"underexplored.":[71],"To":[72],"bridge":[73],"this":[74,156],"gap,":[75],"our":[76],"work":[77],"focuses":[78],"on":[79,97,127],"evaluating":[80],"ability":[82],"understand":[84,113],"specific":[85],"embedded":[88],"videos.":[90],"We":[91],"assess":[92],"11":[93],"advanced":[94],"MLLMs":[95,112,147],"based":[96],"VVALUES":[99],"dataset,":[101],"using":[102],"a":[103],"four-module":[104],"strategy":[105],"designed":[106],"answer":[108],"two":[109],"questions:":[110],"Do":[111,117],"values,":[115],"design":[119],"training":[121],"elements":[122],"impact":[123],"performance?":[125],"Based":[126],"evaluation":[129],"results,":[130],"we":[131],"derive":[132],"valuable":[133],"findings":[134],"across":[135],"eight":[136],"aspects":[137],"that":[138],"provide":[139],"deeper":[140],"insights":[141],"offer":[149],"useful":[150],"guides":[151],"future":[153],"research":[154],"field.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}