{"id":"https://openalex.org/W4387968214","doi":"https://doi.org/10.1145/3581783.3612179","title":"Text-Only Training for Visual Storytelling","display_name":"Text-Only Training for Visual Storytelling","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968214","doi":"https://doi.org/10.1145/3581783.3612179"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612179","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":"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/A5049116027","display_name":"Yuechen Wang","orcid":"https://orcid.org/0000-0003-0965-584X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechen Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0965-584X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017984888","display_name":"Zhenbo Lu","orcid":"https://orcid.org/0000-0002-0918-7524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenbo Lu","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0918-7524","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3368,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59518691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3686","last_page":"3695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9787999987602234,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.803536593914032},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.7326790690422058},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6228057742118835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6194998025894165},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5232657194137573},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5230094790458679},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.46407178044319153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3391674757003784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803536593914032},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.7326790690422058},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6228057742118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6194998025894165},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5232657194137573},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5230094790458679},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.46407178044319153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3391674757003784},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612179","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5038960961","display_name":null,"funder_award_id":"U20A20183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2100031962","https://openalex.org/W2105103432","https://openalex.org/W2123301721","https://openalex.org/W2466175319","https://openalex.org/W2525579820","https://openalex.org/W2559780844","https://openalex.org/W2938704169","https://openalex.org/W2953486038","https://openalex.org/W2963033554","https://openalex.org/W2963096510","https://openalex.org/W2963187786","https://openalex.org/W2963206148","https://openalex.org/W2963668753","https://openalex.org/W2963785020","https://openalex.org/W2966774251","https://openalex.org/W2981852735","https://openalex.org/W2996941455","https://openalex.org/W2998178282","https://openalex.org/W2998303222","https://openalex.org/W2999905431","https://openalex.org/W3033434706","https://openalex.org/W3034999214","https://openalex.org/W3085190015","https://openalex.org/W3099872554","https://openalex.org/W3100995281","https://openalex.org/W3117704329","https://openalex.org/W3135367836","https://openalex.org/W3138368906","https://openalex.org/W3158172841","https://openalex.org/W3169017236","https://openalex.org/W3170806096","https://openalex.org/W3176565349","https://openalex.org/W3176618728","https://openalex.org/W3205377310","https://openalex.org/W3212560870","https://openalex.org/W3214637961","https://openalex.org/W4206232983","https://openalex.org/W4206749883","https://openalex.org/W4223592162","https://openalex.org/W4226182655","https://openalex.org/W4247924304","https://openalex.org/W4256361765","https://openalex.org/W4285230133","https://openalex.org/W4304092243","https://openalex.org/W4312825258","https://openalex.org/W4312938727","https://openalex.org/W4385567053","https://openalex.org/W6678470764","https://openalex.org/W6731060537","https://openalex.org/W6739901393","https://openalex.org/W6761551260","https://openalex.org/W6778883912","https://openalex.org/W6811009250","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2884441370","https://openalex.org/W1536421369","https://openalex.org/W2086118318","https://openalex.org/W2082193010","https://openalex.org/W4319988281","https://openalex.org/W2993120730","https://openalex.org/W1765898938","https://openalex.org/W2970945984","https://openalex.org/W2552287407","https://openalex.org/W2355818213"],"abstract_inverted_index":{"Visual":[0],"storytelling":[1,47],"aims":[2],"to":[3,35,39,79,131],"generate":[4],"a":[5,9,49,56,84,95],"narrative":[6],"based":[7],"on":[8,26,89,149,167],"sequence":[10,110],"of":[11,64,106,121,142,156,176,181],"images,":[12],"necessitating":[13],"both":[14,160],"vision-language":[15],"alignment":[16,66],"and":[17,37,54,67,114,162,170,183],"coherent":[18],"story":[19,51,68,85,136],"generation.":[20,69],"Most":[21],"existing":[22],"solutions":[23],"predominantly":[24],"depend":[25],"paired":[27],"image-text":[28],"training":[29,58,127],"data,":[30,137],"which":[31],"can":[32],"be":[33],"costly":[34],"collect":[36],"challenging":[38],"scale.":[40],"To":[41],"address":[42],"this,":[43],"we":[44,93],"formulate":[45],"visual":[46,81,97,116,143],"as":[48],"visual-conditioned":[50],"generation":[52],"problem":[53],"propose":[55],"text-only":[57],"method":[59,130,178],"that":[60,100],"separates":[61],"the":[62,74,103,107,139,150,154,174],"learning":[63],"cross-modality":[65,75],"Our":[70],"approach":[71,158],"specifically":[72],"leverages":[73],"pre-trained":[76],"CLIP":[77],"model":[78],"integrate":[80],"control":[82],"into":[83],"generator,":[86],"trained":[87],"exclusively":[88],"text":[90,124,135],"data.":[91],"Moreover,":[92],"devise":[94],"training-free":[96],"condition":[98],"planner":[99],"accounts":[101],"for":[102,126],"temporal":[104],"structure":[105],"input":[108],"image":[109],"while":[111],"balancing":[112],"global":[113],"local":[115],"content.":[117],"The":[118],"distinctive":[119],"advantage":[120],"requiring":[122],"only":[123],"data":[125],"enables":[128],"our":[129,157,177],"learn":[132],"from":[133],"external":[134],"enhancing":[138],"generalization":[140],"capability":[141],"storytelling.":[144],"We":[145],"conduct":[146],"extensive":[147],"experiments":[148],"VIST":[151],"benchmark,":[152],"showcasing":[153],"effectiveness":[155],"in":[159,179],"in-domain":[161],"cross-domain":[163],"settings.":[164],"Further":[165],"evaluations":[166],"expression":[168],"diversity":[169],"human":[171],"assessment":[172],"underscore":[173],"superiority":[175],"terms":[180],"informativeness":[182],"robustness.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}