{"id":"https://openalex.org/W4414360022","doi":"https://doi.org/10.24963/ijcai.2025/255","title":"SCVBench: A Benchmark with Multi-turn Dialogues for Story-Centric Video Understanding","display_name":"SCVBench: A Benchmark with Multi-turn Dialogues for Story-Centric Video Understanding","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360022","doi":"https://doi.org/10.24963/ijcai.2025/255"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/255","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":"https://openalex.org/A5101970691","display_name":"Sisi You","orcid":"https://orcid.org/0009-0004-2173-1694"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I4210159812","display_name":"Tibetan Traditional Medical College","ror":"https://ror.org/05hk7qq56","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210159812"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sisi You","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications","State Key Laboratory of Tibetan Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"State Key Laboratory of Tibetan Intelligence","institution_ids":["https://openalex.org/I4210159812"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740413","display_name":"Bowen Yuan","orcid":"https://orcid.org/0000-0002-8051-3070"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Yuan","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044697325","display_name":"Bing-Kun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications","Pengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2287","last_page":"2295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12461","display_name":"Narrative Theory and Analysis","score":0.9404000043869019,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9362000226974487,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8398000001907349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7372999787330627},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.6952999830245972},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6337000131607056},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39329999685287476}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8398000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651000022888184},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7372999787330627},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601999759674072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/255","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":[],"abstract_inverted_index":{"Video":[0],"understanding":[1],"seeks":[2],"to":[3,6,24,31,73,128],"enable":[4],"machines":[5],"interpret":[7],"visual":[8],"content":[9],"across":[10],"three":[11],"levels:":[12],"action,":[13],"event,":[14],"and":[15,39,87,137],"story.":[16],"Existing":[17],"models":[18],"are":[19],"limited":[20],"in":[21],"their":[22],"ability":[23],"perform":[25],"high-level":[26],"long-term":[27],"story":[28],"understanding,":[29],"due":[30],"(1)":[32],"the":[33,41],"oversimplified":[34],"treatment":[35],"of":[36],"temporal":[37,135],"information":[38],"(2)":[40],"training":[42],"bias":[43],"introduced":[44],"by":[45,131],"action/event-centric":[46],"datasets.":[47],"To":[48],"address":[49],"this,":[50],"we":[51],"introduce":[52],"SCVBench,":[53],"a":[54,74],"novel":[55],"benchmark":[56],"for":[57],"story-centric":[58,113],"video":[59,114],"understanding.":[60,115],"SCVBench":[61,126],"evaluates":[62],"LVLMs":[63,110,123],"through":[64],"an":[65],"event":[66],"ordering":[67],"task":[68],"decomposed":[69],"into":[70],"sub-questions":[71],"leading":[72],"final":[75,85],"question,":[76],"quantitatively":[77],"measuring":[78],"historical":[79],"dialogue":[80],"exploration.":[81],"We":[82],"collected":[83],"1,253":[84],"questions":[86],"6,027":[88],"sub-question":[89],"pairs":[90],"from":[91],"925":[92],"videos,":[93],"constructing":[94],"continuous":[95],"multi-turn":[96],"dialogues.":[97],"Experimental":[98],"results":[99],"show":[100],"that":[101],"while":[102],"closed-source":[103],"GPT-4o":[104],"outperforms":[105],"other":[106],"models,":[107],"most":[108],"open-source":[109,122],"struggle":[111],"with":[112],"Additionally,":[116],"our":[117],"StoryCoT":[118],"model":[119],"significantly":[120],"surpasses":[121],"on":[124],"SCVBench.":[125],"aims":[127],"advance":[129],"research":[130],"comprehensively":[132],"analyzing":[133],"LVLMs'":[134],"reasoning":[136],"comprehension":[138],"capabilities.":[139],"Code":[140],"can":[141],"be":[142],"accessed":[143],"at":[144],"https://github.com/yuanrr/SCVBench.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}