{"id":"https://openalex.org/W4410830113","doi":"https://doi.org/10.1145/3736759","title":"Open-ended Autoregressive Visual Storytelling via Parameter Efficient Instruction Tuning","display_name":"Open-ended Autoregressive Visual Storytelling via Parameter Efficient Instruction Tuning","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4410830113","doi":"https://doi.org/10.1145/3736759"},"language":"en","primary_location":{"id":"doi:10.1145/3736759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736759","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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":null,"display_name":"Lixin Liu","orcid":"https://orcid.org/0009-0000-2281-9939"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Liu","raw_affiliation_strings":["School of Digital Industry, Jiangxi Normal University","School of Digital Industry, Jiangxi Normal University, Shangrao, China"],"raw_orcid":"https://orcid.org/0009-0000-2281-9939","affiliations":[{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University, Shangrao, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034126758","display_name":"Aiwen Jiang","orcid":"https://orcid.org/0000-0002-5979-7590"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiwen Jiang","raw_affiliation_strings":["School of Digital Industry, Jiangxi Normal University","School of Digital Industry, Jiangxi Normal University, Shangrao, China"],"raw_orcid":"https://orcid.org/0000-0002-5979-7590","affiliations":[{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University, Shangrao, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yinuo Chen","orcid":"https://orcid.org/0009-0007-9217-1817"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinuo Chen","raw_affiliation_strings":["School of Digital Industry, Jiangxi Normal University","School of Digital Industry, Jiangxi Normal University, Shangrao, China"],"raw_orcid":"https://orcid.org/0009-0007-9217-1817","affiliations":[{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University, Shangrao, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859009","display_name":"Changhong Liu","orcid":"https://orcid.org/0000-0003-4673-5806"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Liu","raw_affiliation_strings":["School of Computer and Infomation Engineering, Jiangxi Normal University","School of Computer and Infomation Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0003-4673-5806","affiliations":[{"raw_affiliation_string":"School of Computer and Infomation Engineering, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Infomation Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112378738","display_name":"Qi Huang","orcid":"https://orcid.org/0000-0002-3603-1875"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Huang","raw_affiliation_strings":["School of Computer and Information Engineering, Jiangxi Normal University","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":"https://orcid.org/0000-0002-3603-1875","affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033849258","display_name":"Mingwen Wang","orcid":"https://orcid.org/0000-0002-8118-9612"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwen Wang","raw_affiliation_strings":["School of Digital Industry, Jiangxi Normal University","School of Digital Industry, Jiangxi Normal University, Shangrao, China"],"raw_orcid":"https://orcid.org/0000-0002-8118-9612","affiliations":[{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Digital Industry, Jiangxi Normal University, Shangrao, China","institution_ids":["https://openalex.org/I53592917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I53592917"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0891007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"6","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7524880170822144},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.5984762907028198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57594233751297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3453083336353302},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3262251317501068},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.27504852414131165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19121497869491577},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06525152921676636},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.05818125605583191}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7524880170822144},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.5984762907028198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57594233751297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3453083336353302},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3262251317501068},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27504852414131165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19121497869491577},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06525152921676636},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.05818125605583191},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3736759","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1026333626","display_name":null,"funder_award_id":"62366021","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2183386595","https://openalex.org/W2466175319","https://openalex.org/W2613718673","https://openalex.org/W2963033554","https://openalex.org/W2963047368","https://openalex.org/W2966715458","https://openalex.org/W2966774251","https://openalex.org/W2976119386","https://openalex.org/W2998178282","https://openalex.org/W2998303222","https://openalex.org/W3037111525","https://openalex.org/W3087871082","https://openalex.org/W3174202502","https://openalex.org/W3176565349","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4214614183","https://openalex.org/W4221152653","https://openalex.org/W4280534475","https://openalex.org/W4280652277","https://openalex.org/W4312651322","https://openalex.org/W4312825258","https://openalex.org/W4381611941","https://openalex.org/W4387436689","https://openalex.org/W4400601342","https://openalex.org/W4402667011","https://openalex.org/W4402727764"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Visual":[0],"storytelling":[1,25],"(VIST)":[2],"involves":[3],"generating":[4],"coherent,":[5],"creative,":[6],"and":[7,73,87,99,104,174,182,201],"vivid":[8,88,125],"narrative":[9],"for":[10,127,139],"a":[11,118],"collection":[12],"of":[13,162,178],"images.":[14],"It":[15,155],"remains":[16],"an":[17,147,166],"immense":[18],"challenge":[19],"within":[20],"cross-modal":[21,45],"domain.":[22],"Traditional":[23],"mainstream":[24],"work":[26],"were":[27,51],"less":[28],"proficient":[29],"in":[30,65,91,165,176],"handling":[31,56],"long":[32],"sequential":[33],"relationships.":[34],"Though":[35],"large-scale":[36],"visual-language":[37],"pre-training":[38],"(VLP)":[39],"models":[40,81,202],"demonstrated":[41,189],"promising":[42],"prospect":[43],"on":[44,135,205],"tasks.":[46],"So":[47],"far":[48],"they":[49],"still":[50],"not":[52],"particularly":[53],"adept":[54],"at":[55],"tasks":[57],"involving":[58],"image":[59,129,160],"sequences.":[60,130],"Moreover,":[61],"the":[62,66],"reference":[63],"descriptions":[64],"available":[67],"VIST":[68],"benchmark":[69],"dataset":[70,103,120,132],"are":[71,203],"short":[72],"simplistic,":[74],"which":[75,122],"constrains":[76],"model\u2019s":[77],"potential":[78,134],"capabilities.":[79],"Current":[80],"struggle":[82],"to":[83,159],"produce":[84],"truly":[85],"rich":[86],"narratives.":[89],"Therefore,":[90],"this":[92],"article,":[93],"we":[94,115,144],"will":[95],"address":[96],"these":[97],"deficiencies,":[98],"contribute":[100],"from":[101],"both":[102],"innovative":[105,148],"model":[106,113,141,152],"aspects.":[107],"Firstly,":[108],"by":[109],"leveraging":[110],"large":[111],"language":[112],"(LLM),":[114],"have":[116,145,170,187],"constructed":[117],"new":[119],"VIST++":[121],"can":[123,156],"enrich":[124],"narratives":[126],"open-ended":[128,167],"The":[131,184],"has":[133],"providing":[136],"beneficial":[137],"support":[138],"future":[140],"learning.":[142],"Secondly,":[143],"proposed":[146],"auto-regressive":[149],"story":[150],"generation":[151],"named":[153],"ReStoryGen.":[154],"be":[157],"applied":[158],"sequences":[161],"varying":[163],"lengths":[164],"way.":[168],"We":[169],"performed":[171],"extensive":[172],"experiments":[173],"evaluations":[175],"terms":[177],"visual":[179],"grounding,":[180],"coherence":[181],"non-redundancy.":[183],"experiment":[185],"results":[186],"convincingly":[188],"ReStoryGen":[190],"achieves":[191],"impressive":[192],"outcomes":[193],"through":[194],"utilizing":[195],"parameter-efficient":[196],"instruction-tuning.":[197],"Related":[198],"source":[199],"codes":[200],"distributed":[204],"Github":[206],"https://github.com/lixinliu1995/story_gen":[207],".":[208]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}