{"id":"https://openalex.org/W4387968294","doi":"https://doi.org/10.1145/3581783.3612417","title":"TeViS: Translating Text Synopses to Video Storyboards","display_name":"TeViS: Translating Text Synopses to Video Storyboards","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968294","doi":"https://doi.org/10.1145/3581783.3612417"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5064539132","display_name":"Xu Gu","orcid":"https://orcid.org/0009-0003-4847-6593"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Gu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4847-6593","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062292360","display_name":"Yuchong Sun","orcid":"https://orcid.org/0009-0004-6559-5620"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchong Sun","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6559-5620","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014771799","display_name":"Feiyue Ni","orcid":"https://orcid.org/0009-0001-6062-3459"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyue Ni","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-6062-3459","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["INRIA, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-7313-9703","affiliations":[{"raw_affiliation_string":"INRIA, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560179","display_name":"Xihua Wang","orcid":"https://orcid.org/0009-0002-9454-5775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihua Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9454-5775","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505571","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0002-2163-7401"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2163-7401","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051583322","display_name":"Boyuan Li","orcid":"https://orcid.org/0009-0008-5487-9678"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyuan Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5487-9678","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101964473","display_name":"Xiang Cao","orcid":"https://orcid.org/0000-0002-5142-2292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Cao","raw_affiliation_strings":["Bilibili Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5142-2292","affiliations":[{"raw_affiliation_string":"Bilibili Inc., Beijing, China","institution_ids":[]}]}],"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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4968","last_page":"4979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9919000267982483,"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/storyboard","display_name":"Storyboard","score":0.938969612121582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8693854808807373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5167316794395447},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5146740078926086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5087562203407288},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.47994330525398254},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41835343837738037},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4181169867515564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3904265761375427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3515525758266449},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14636415243148804}],"concepts":[{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.938969612121582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8693854808807373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5167316794395447},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5146740078926086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5087562203407288},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.47994330525398254},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41835343837738037},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4181169867515564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3904265761375427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3515525758266449},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14636415243148804},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6189287592","display_name":null,"funder_award_id":"62276268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1974991592","https://openalex.org/W2076771430","https://openalex.org/W2106791119","https://openalex.org/W2142194269","https://openalex.org/W2146007701","https://openalex.org/W2171186743","https://openalex.org/W2799185021","https://openalex.org/W2914699769","https://openalex.org/W2963047368","https://openalex.org/W2964024144","https://openalex.org/W2964033924","https://openalex.org/W2982260486","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2998106530","https://openalex.org/W3034364644","https://openalex.org/W3107806026","https://openalex.org/W3110420575","https://openalex.org/W3165647589","https://openalex.org/W3168640669","https://openalex.org/W3180355996","https://openalex.org/W3184784418","https://openalex.org/W3204588463","https://openalex.org/W3212610063","https://openalex.org/W3216765867","https://openalex.org/W4220896903","https://openalex.org/W4292779060","https://openalex.org/W4312974539","https://openalex.org/W4385269064","https://openalex.org/W6600547436","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2492710265","https://openalex.org/W4240451687","https://openalex.org/W18668743","https://openalex.org/W1992770539","https://openalex.org/W2763009497","https://openalex.org/W2997546339","https://openalex.org/W20772255","https://openalex.org/W627223050","https://openalex.org/W2134443199","https://openalex.org/W168166288"],"abstract_inverted_index":{"A":[0],"video":[1,7,23,76],"storyboard":[2,77],"is":[3,180],"a":[4,19,55,85,126,138,156,182],"roadmap":[5],"for":[6,161,191],"creation":[8],"which":[9,28,65],"consists":[10],"of":[11,72,158],"shot-by-shot":[12],"images":[13,38,73,136],"to":[14,44,61,67,78,147,186],"visualize":[15,79],"key":[16],"plots":[17],"in":[18],"text":[20,81,98,133],"synopsis.":[21,82],"Creating":[22],"storyboards,":[24],"however,":[25],"remains":[26],"challenging":[27],"not":[29],"only":[30],"requires":[31],"cross-modal":[32],"association":[33],"between":[34],"high-level":[35],"texts":[36],"and":[37,113,125,135,142,163,174,197],"but":[39],"also":[40],"demands":[41],"long-term":[42],"reasoning":[43],"make":[45],"transitions":[46],"smooth":[47],"across":[48],"shots.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,120],"propose":[54],"new":[56],"task":[57],"called":[58],"Text":[59],"synopsis":[60,134],"Video":[62],"Storyboard":[63],"(TeViS)":[64],"aims":[66],"retrieve":[68],"an":[69],"ordered":[70],"sequence":[71,157],"as":[74],"the":[75,80,90,118,149,175],"We":[83],"construct":[84],"MovieNet-TeViS":[86],"dataset":[87,93],"based":[88],"on":[89],"public":[91],"MovieNet":[92],"[17].":[94],"It":[95],"contains":[96],"10K":[97],"synopses":[99],"each":[100],"paired":[101],"with":[102],"keyframes":[103],"manually":[104],"selected":[105],"from":[106],"corresponding":[107],"movies":[108],"by":[109],"considering":[110],"both":[111],"relevance":[112],"cinematic":[114],"coherence.":[115],"To":[116],"benchmark":[117],"task,":[119],"present":[121],"strong":[122],"CLIP-based":[123,176],"baselines":[124],"novel":[127],"VQ-Trans":[128,130,169],"model.":[129],"first":[131],"encodes":[132],"into":[137],"joint":[139],"embedding":[140],"space":[141],"uses":[143],"vector":[144],"quantization":[145],"(VQ)":[146],"improve":[148],"visual":[150,159],"representation.":[151],"Then,":[152],"it":[153],"auto-regressively":[154],"generates":[155],"features":[160],"retrieval":[162],"ordering.":[164],"Experimental":[165],"results":[166],"demonstrate":[167],"that":[168],"significantly":[170],"outperforms":[171],"prior":[172],"methods":[173],"baselines.":[177],"Nevertheless,":[178],"there":[179],"still":[181],"large":[183],"gap":[184],"compared":[185],"human":[187],"performance":[188],"suggesting":[189],"room":[190],"promising":[192],"future":[193],"work.":[194],"The":[195],"code":[196],"data":[198],"are":[199],"available":[200],"at:":[201],"https://ruc-aimind.github.io/projects/TeViS/":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}