{"id":"https://openalex.org/W4408355843","doi":"https://doi.org/10.1109/icassp49660.2025.10889982","title":"Efficient Visual Storytelling through Descriptive Words Distillation and Dynamic Decoding","display_name":"Efficient Visual Storytelling through Descriptive Words Distillation and Dynamic Decoding","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355843","doi":"https://doi.org/10.1109/icassp49660.2025.10889982"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":null,"display_name":"Zixuan Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixuan Xiong","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107677597","display_name":"Hai Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Lin","raw_affiliation_strings":["Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032096158","display_name":"Lichen Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lichen Bai","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752106","display_name":"Yinghui Li","orcid":"https://orcid.org/0000-0002-7596-9508"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787808","display_name":"Haitao Zheng","orcid":"https://orcid.org/0000-0002-7897-1267"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai-Tao Zheng","raw_affiliation_strings":["Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058110900","display_name":"Hong\u2010Gee Kim","orcid":"https://orcid.org/0000-0002-2610-4321"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Gee Kim","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03351644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9921000003814697,"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":0.9921000003814697,"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":0.9598000049591064,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9126999974250793,"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/storytelling","display_name":"Storytelling","score":0.7815123796463013},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7682306170463562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7140114903450012},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6408244371414185},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.412923127412796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4016857445240021},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3472110629081726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3338938057422638},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15285399556159973},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.14081498980522156},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08649340271949768},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06767991185188293},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06115192174911499}],"concepts":[{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.7815123796463013},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7682306170463562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140114903450012},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6408244371414185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412923127412796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016857445240021},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3472110629081726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3338938057422638},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15285399556159973},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.14081498980522156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08649340271949768},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06767991185188293},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06115192174911499},{"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:10.1109/icassp49660.2025.10889982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320317992","display_name":"Experiment","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2194775991","https://openalex.org/W2463955103","https://openalex.org/W2604178507","https://openalex.org/W2949376505","https://openalex.org/W2962968835","https://openalex.org/W2963033554","https://openalex.org/W2963175879","https://openalex.org/W2964018924","https://openalex.org/W2981851019","https://openalex.org/W2996941455","https://openalex.org/W2998106530","https://openalex.org/W2998303222","https://openalex.org/W3087871082","https://openalex.org/W3109320561","https://openalex.org/W3176313262","https://openalex.org/W3176481196","https://openalex.org/W3176565349","https://openalex.org/W3216765867","https://openalex.org/W4206749883","https://openalex.org/W4285125423","https://openalex.org/W4292263758","https://openalex.org/W4304092243","https://openalex.org/W4312825258","https://openalex.org/W4382073839","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6685322675","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6769627184","https://openalex.org/W6796990549","https://openalex.org/W6851950068"],"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],"a":[2,17,60,107,127],"complex":[3],"task":[4],"in":[5,156],"natural":[6],"language":[7],"generation,":[8],"aims":[9],"to":[10,52,62,73,163],"create":[11],"coherent":[12],"and":[13,24,39,92,100,133,159],"engaging":[14],"narratives":[15],"from":[16,67],"sequence":[18],"of":[19,121],"images,":[20],"requiring":[21],"more":[22],"intricate":[23],"lengthy":[25],"descriptions":[26],"than":[27],"typical":[28],"image":[29,123,131],"captioning.":[30],"Current":[31],"methods":[32,146],"generally":[33],"employ":[34],"sophisticated":[35],"modal":[36],"interaction":[37],"modules":[38,99],"require":[40],"substantial":[41],"additional":[42,97],"data":[43],"for":[44,89,96],"training.":[45],"This":[46,78,125],"paper":[47],"introduces":[48],"two":[49],"innovative":[50],"techniques":[51],"advance":[53],"visual":[54,98],"storytelling":[55],"capabilities.":[56],"First,":[57],"we":[58,105],"propose":[59],"method":[61],"distill":[63],"descriptive":[64,86],"word":[65],"embeddings":[66],"model":[68],"parameters":[69],"as":[70],"an":[71,148],"extension":[72],"the":[74,81,94,113,119,122,134,140],"model\u2019s":[75],"pre-trained":[76],"embeddings.":[77],"approach":[79],"focuses":[80],"training":[82,157],"process":[83,116],"on":[84,118,139],"these":[85,145],"words,":[87],"allowing":[88],"efficient":[90],"fine-tuning":[91],"eliminates":[93],"need":[95],"reduces":[101],"computational":[102],"overhead.":[103],"Second,":[104],"develop":[106],"dynamic":[108],"decoding":[109],"strategy":[110],"that":[111,144],"adapts":[112],"text":[114],"generation":[115],"based":[117],"characteristic":[120],"features.":[124],"ensures":[126],"improved":[128],"alignment":[129],"with":[130],"features":[132],"generated":[135],"stories.":[136],"Our":[137],"experiments":[138],"VIST":[141],"dataset":[142],"demonstrate":[143],"achieve":[147],"impressive":[149],"performance.":[150],"Ablation":[151],"studies":[152],"show":[153],"significant":[154],"improvements":[155],"efficiency":[158],"narrative":[160],"quality":[161],"compared":[162],"existing":[164],"approaches.":[165]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}