{"id":"https://openalex.org/W4392911142","doi":"https://doi.org/10.1109/icassp48485.2024.10446420","title":"Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning for Visual Story Synthesis","display_name":"Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning for Visual Story Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392911142","doi":"https://doi.org/10.1109/icassp48485.2024.10446420"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5003896988","display_name":"Tianyi Song","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyi Song","raw_affiliation_strings":["Southeast University,School of Cyber Science and Engineering,Nanjing,China","School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Cyber Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012384188","display_name":"Jiuxin Cao","orcid":"https://orcid.org/0000-0002-2448-6717"},"institutions":[{"id":"https://openalex.org/I209549992","display_name":"Sanjiang University","ror":"https://ror.org/02q1hyx43","country_code":"CN","type":"education","lineage":["https://openalex.org/I209549992"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["Southeast University,School of Cyber Science and Engineering,Nanjing,China","School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Computer Science and Engineering, Sanjiang University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Cyber Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sanjiang University, Nanjing, China","institution_ids":["https://openalex.org/I209549992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366662","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-4794-2359"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Southeast University,School of Cyber Science and Engineering,Nanjing,China","School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Cyber Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461621","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-0894-1054"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China","School of Computer Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455665","display_name":"Xiaofeng Zhang","orcid":"https://orcid.org/0000-0002-7185-4682"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003896988"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61556762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3350","last_page":"3354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9876999855041504,"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/T12290","display_name":"Human Motion and Animation","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6474780440330505},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.43615198135375977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37038394808769226},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3429739475250244},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1990627646446228},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07139420509338379}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474780440330505},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.43615198135375977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37038394808769226},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3429739475250244},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1990627646446228},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07139420509338379},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":26,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2752796333","https://openalex.org/W2962931774","https://openalex.org/W2963047368","https://openalex.org/W2963799213","https://openalex.org/W3010564927","https://openalex.org/W3036167779","https://openalex.org/W3096831136","https://openalex.org/W3104780697","https://openalex.org/W3169749700","https://openalex.org/W3205612999","https://openalex.org/W4288099666","https://openalex.org/W4312697499","https://openalex.org/W4312721788","https://openalex.org/W4312933868","https://openalex.org/W4320561770","https://openalex.org/W4385573943","https://openalex.org/W6640963894","https://openalex.org/W6779823529","https://openalex.org/W6788990321","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6811013733","https://openalex.org/W6840815571","https://openalex.org/W6850276463"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0,16],"excellent":[1],"text-to-image":[2],"synthesis":[3],"capability":[4],"of":[5,23,71,119],"diffusion":[6],"models":[7],"has":[8],"driven":[9],"progress":[10],"in":[11,55,145],"synthesizing":[12],"coherent":[13],"visual":[14],"stories.":[15],"current":[17,30,37,73,100,112],"state-of-the-art":[18,134],"method":[19,41],"combines":[20],"the":[21,29,36,49,69,72,92,111,116,127,138],"features":[22],"historical":[24,26,44,64],"captions,":[25,97],"frames,":[27,98],"and":[28,46,99,129,132,137],"captions":[31],"as":[32,48],"conditions":[33,65],"for":[34],"generating":[35],"frame.":[38,74],"However,":[39],"this":[40,77,107],"treats":[42],"each":[43],"frame":[45],"caption":[47],"same":[50],"contribution.":[51],"It":[52],"connects":[53],"them":[54],"order":[56],"with":[57,68],"equal":[58],"weights,":[59],"ignoring":[60],"that":[61,90],"not":[62],"all":[63],"are":[66],"associated":[67],"generation":[70],"To":[75],"address":[76],"issue,":[78],"we":[79],"propose":[80],"Causal-Story.":[81],"This":[82],"model":[83,125],"incorporates":[84],"a":[85],"local":[86],"causal":[87,93],"attention":[88],"mechanism":[89],"considers":[91],"relationship":[94],"between":[95],"previous":[96],"captions.":[101],"By":[102],"assigning":[103],"weights":[104],"based":[105],"on":[106,126],"relationship,":[108],"Causal-Story":[109],"generates":[110],"frame,":[113],"thereby":[114],"improving":[115],"global":[117],"consistency":[118],"story":[120],"generation.":[121],"We":[122],"evaluated":[123],"our":[124],"PororoSV":[128],"FlintstonesSV":[130],"datasets":[131],"obtained":[133],"FID":[135],"scores,":[136],"generated":[139],"frames":[140],"also":[141],"demonstrate":[142],"better":[143],"storytelling":[144],"visuals.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}