{"id":"https://openalex.org/W4206749883","doi":"https://doi.org/10.1145/3469877.3490604","title":"Visual Storytelling with Hierarchical BERT Semantic Guidance","display_name":"Visual Storytelling with Hierarchical BERT Semantic Guidance","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4206749883","doi":"https://doi.org/10.1145/3469877.3490604"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3490604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","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/A5061965819","display_name":"Ruichao Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichao Fan","raw_affiliation_strings":["Tongji University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Tongji University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057852825","display_name":"Jinjing Gu","orcid":"https://orcid.org/0000-0002-7669-8201"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjing Gu","raw_affiliation_strings":["Tongji University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114310406","display_name":"Xianhui Liu","orcid":"https://orcid.org/0009-0008-7048-7148"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhui Liu","raw_affiliation_strings":["Tongji University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, CN","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"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":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":0.9958999752998352,"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":0.9835000038146973,"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/computer-science","display_name":"Computer science","score":0.8176409006118774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6021322011947632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5605648756027222},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5272741913795471},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.5191816091537476},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.4740181565284729},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4623834490776062},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41916656494140625},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.29956763982772827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1858292520046234},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14880886673927307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176409006118774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6021322011947632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605648756027222},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5272741913795471},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.5191816091537476},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.4740181565284729},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4623834490776062},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41916656494140625},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.29956763982772827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1858292520046234},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14880886673927307},{"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:10.1145/3469877.3490604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5501368935","display_name":null,"funder_award_id":"61976159","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1984899418","https://openalex.org/W2108325777","https://openalex.org/W2335943242","https://openalex.org/W2897098357","https://openalex.org/W2953486038","https://openalex.org/W2962686197","https://openalex.org/W2963033554","https://openalex.org/W2963084599","https://openalex.org/W2963187786","https://openalex.org/W2963668753","https://openalex.org/W2963829244","https://openalex.org/W2964173634","https://openalex.org/W2966774251","https://openalex.org/W2987862245","https://openalex.org/W2996941455","https://openalex.org/W2998178282","https://openalex.org/W3087871082","https://openalex.org/W3100995281","https://openalex.org/W3113632293","https://openalex.org/W3166368118"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W4200355488","https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W2052919063","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280"],"abstract_inverted_index":{"Visual":[0],"storytelling,":[1],"which":[2,222],"aims":[3,94],"at":[4],"automatically":[5],"producing":[6],"a":[7,32,54,110,133],"narrative":[8],"paragraph":[9],"for":[10,147],"photo":[11,23,29,49],"album,":[12],"remains":[13],"quite":[14],"challenging":[15],"due":[16],"to":[17,47,68,95,123,132,153,171,176,184,202,215],"the":[18,70,97,101,127,139,156,162,173,207,217,224,229],"complexity":[19,158],"and":[20,37,44,87,118,167],"diversity":[21],"of":[22,35,78,100,219],"album":[24],"content.":[25],"In":[26,51,138],"addition,":[27],"open-domain":[28],"albums":[30],"cover":[31],"broad":[33],"range":[34],"topics":[36,175],"this":[38,52],"results":[39],"in":[40],"highly":[41],"variable":[42],"vocabularies":[43],"expression":[45],"styles":[46],"describe":[48],"albums.":[50],"work,":[53],"novel":[55],"teacher-student":[56],"visual":[57,116],"storytelling":[58],"framework":[59],"with":[60,165],"hierarchical":[61],"BERT":[62,112],"semantic":[63,168,187],"guidance":[64],"(HBSG)":[65],"is":[66,105,121,130,145,152,169,183,200],"proposed":[67,74],"address":[69],"above-mentioned":[71],"challenges.":[72],"The":[73,91,150,181],"teacher":[75,194],"module":[76],"consists":[77],"two":[79,148],"joint":[80],"tasks,":[81],"namely,":[82],"word-level":[83],"latent":[84,98,174],"topic":[85,99,108,128],"generation":[86,142,209],"semantic-guided":[88,140],"sentence":[89,141,186],"generation.":[90],"first":[92,151],"task":[93],"predict":[96],"story.":[102],"As":[103],"there":[104],"no":[106],"ground-truth":[107],"information,":[109],"pre-trained":[111],"model":[113],"based":[114],"on":[115,228],"contents":[117],"annotated":[119],"stories":[120],"utilized":[122],"mine":[124],"topics.":[125],"Then":[126],"vector":[129],"distilled":[131],"designed":[134,170],"image-topic":[135],"prediction":[136],"model.":[137,210],"task,":[143],"HBSG":[144,220],"introduced":[146],"purposes.":[149],"narrow":[154],"down":[155],"language":[157,179,208],"across":[159],"topics,":[160],"where":[161],"co-attention":[163],"decoder":[164],"vision":[166],"leverage":[172],"induce":[177],"topic-related":[178],"models.":[180],"second":[182],"employ":[185],"as":[188],"an":[189,197],"online":[190],"external":[191],"linguistic":[192,204],"knowledge":[193,205],"module.":[195],"Finally,":[196],"auxiliary":[198],"loss":[199],"devised":[201],"transform":[203],"into":[206],"Extensive":[211],"experiments":[212],"are":[213],"performed":[214],"demonstrate":[216],"effectiveness":[218],"framework,":[221],"surpasses":[223],"state-of-the-art":[225],"approaches":[226],"evaluated":[227],"VIST":[230],"test":[231],"set.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}