{"id":"https://openalex.org/W7124837546","doi":"https://doi.org/10.1109/cbmi66578.2025.11339268","title":"SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models","display_name":"SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124837546","doi":"https://doi.org/10.1109/cbmi66578.2025.11339268"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5114230961","display_name":"Zhengxu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengxu Tang","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063627517","display_name":"Z. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizheng Wang","raw_affiliation_strings":["Northeastern University,Department of Mechanical and Industrial Engineering,Boston,United States"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Mechanical and Industrial Engineering,Boston,United States","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647855","display_name":"Luning Wang","orcid":"https://orcid.org/0009-0001-1101-2686"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luning Wang","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104221370","display_name":"Zitao Shuai","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zitao Shuai","raw_affiliation_strings":["University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical and Computer Engineering,Ann Arbor,United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123382684","display_name":"Chenhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100791","display_name":"Paul G. Allen Family Foundation","ror":"https://ror.org/01degd278","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210100791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenhao Zhang","raw_affiliation_strings":["Paul G. Allen School of Computer Science and Engineering, University of Washington,Seattle,United States"],"affiliations":[{"raw_affiliation_string":"Paul G. Allen School of Computer Science and Engineering, University of Washington,Seattle,United States","institution_ids":["https://openalex.org/I4210100791"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyu Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyu Qian","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University,Cambridge,United State"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University,Cambridge,United State","institution_ids":["https://openalex.org/I2801851002","https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121089629","display_name":"Yirui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yirui Wu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050239431","display_name":"Bohao Wang","orcid":"https://orcid.org/0009-0006-8264-3182"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohao Wang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123433785","display_name":"Haosong Rao","orcid":null},"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"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haosong Rao","raw_affiliation_strings":["Georgen Institute for Data Science, University of Rochester,Rochester,United States"],"affiliations":[{"raw_affiliation_string":"Georgen Institute for Data Science, University of Rochester,Rochester,United States","institution_ids":["https://openalex.org/I5388228","https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630915","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0000-0002-9339-332X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Yang","raw_affiliation_strings":["School of Earth Sciences, Zhejiang University,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Earth Sciences, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chenwei Wu","orcid":null},"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"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenwei Wu","raw_affiliation_strings":["Georgen Institute for Data Science, University of Rochester,Rochester,United States"],"affiliations":[{"raw_affiliation_string":"Georgen Institute for Data Science, University of Rochester,Rochester,United States","institution_ids":["https://openalex.org/I5388228","https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5114230961"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68850295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8217999935150146,"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":0.8217999935150146,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09860000014305115,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.014100000262260437,"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/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.7555999755859375},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.6791999936103821},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6710000038146973},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5113999843597412},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.37310001254081726}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.7555999755859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.6791999936103821},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091000199317932},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C63985673","wikidata":"https://www.wikidata.org/wiki/Q6966216","display_name":"Narrative network","level":5,"score":0.2987000048160553},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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":7,"referenced_works":["https://openalex.org/W4387037106","https://openalex.org/W4402727403","https://openalex.org/W4404780711","https://openalex.org/W4409365832","https://openalex.org/W4413145384","https://openalex.org/W4413447807","https://openalex.org/W4417147545"],"related_works":[],"abstract_inverted_index":{"Text-to-video":[0],"(T2V)":[1],"generation":[2,173],"models":[3],"have":[4],"made":[5],"significant":[6],"progress":[7],"in":[8,61,130,146,151,171,183],"creating":[9],"visually":[10],"appealing":[11],"videos.":[12],"However,":[13],"they":[14],"struggle":[15],"with":[16,77,118],"generating":[17],"coherent":[18],"sequential":[19,58,159,180],"narratives":[20],"that":[21],"require":[22],"logical":[23],"progression":[24],"through":[25],"multiple":[26],"events.":[27],"Existing":[28],"T2V":[29,62,85,132,172],"benchmarks":[30],"primarily":[31],"focus":[32],"on":[33],"visual":[34],"quality":[35],"metrics":[36],"but":[37],"fail":[38],"to":[39,135,188],"evaluate":[40],"narrative":[41,59,75,169],"coherence":[42,60,170],"over":[43],"extended":[44],"sequences.":[45],"To":[46],"bridge":[47],"this":[48],"gap,":[49],"we":[50,88,126],"present":[51],"SeqBench,":[52,125],"a":[53,66,90,115],"comprehensive":[54],"benchmark":[55],"for":[56,167,178,190],"evaluating":[57,168],"generation.":[63],"SeqBench":[64,161],"includes":[65],"carefully":[67],"designed":[68],"dataset":[69],"of":[70],"320":[71],"prompts":[72],"spanning":[73],"various":[74],"complexities,":[76],"2,560":[78],"human-annotated":[79],"videos":[80],"generated":[81],"from":[82],"8":[83],"state-of-the-art":[84],"models.":[86,185],"Additionally,":[87],"design":[89],"Dynamic":[91],"Temporal":[92],"Graphs":[93],"(DTG)-based":[94],"automatic":[95],"evaluation":[96,123],"metric,":[97],"which":[98],"can":[99],"efficiently":[100],"capture":[101],"long-range":[102],"dependencies":[103],"and":[104,149,155,174],"temporal":[105],"ordering":[106,156],"while":[107],"maintaining":[108],"computational":[109],"efficiency.":[110],"Our":[111],"DTG-based":[112],"metric":[113],"demonstrates":[114],"strong":[116],"correlation":[117],"human":[119],"annotations.":[120],"Through":[121],"systematic":[122,165],"using":[124],"reveal":[127],"critical":[128],"limitations":[129],"current":[131],"models:":[133],"failure":[134],"maintain":[136],"consistent":[137],"object":[138],"states":[139],"across":[140],"multi-action":[141],"sequences,":[142],"physically":[143],"implausible":[144],"results":[145],"multi-object":[147],"scenarios,":[148],"difficulties":[150],"preserving":[152],"realistic":[153],"timing":[154],"relationships":[157],"between":[158],"actions.":[160],"provides":[162],"the":[163],"first":[164],"framework":[166],"offers":[175],"concrete":[176],"insights":[177],"improving":[179],"reasoning":[181],"capabilities":[182],"future":[184],"Please":[186],"refer":[187],"https://videobench.github.io/SeqBench.github.io/":[189],"more":[191],"details.":[192]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-21T00:00:00"}