{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:19Z","timestamp":1774419499529,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018206","name":"Experiment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018206","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889982","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Visual Storytelling through Descriptive Words Distillation and Dynamic Decoding"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Xiong","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Hai","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Lichen","family":"Bai","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Yinghui","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Hai-Tao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua University Pengcheng Laboratory,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Hong-Gee","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01247"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref4","first-page":"12 747","article-title":"Two heads are better than one: Hypergraph-enhanced graph reasoning for visual event ratiocination","volume-title":"ICML","volume":"139","author":"Zheng","year":"2021"},{"key":"ref5","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"ICML, ser. JMLR Workshop and Conference Proceedings","volume":"37","author":"Xu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref13","article-title":"Sequence level training with recurrent neural networks","author":"Ranzato","year":"2016","journal-title":"ICLR (Poster)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199603"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230934"},{"key":"ref19","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126486"},{"key":"ref21","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"NIPS"},{"key":"ref22","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT (1).","author":"Devlin","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490604"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref25","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101169"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"issue":"8","key":"ref28","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref29","article-title":"Zigzag diffusion sampling: Diffusion models can self-improve via self-reflection","author":"Bai","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"IEE-valuation@ACL.","author":"Banerjee","year":"2005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6780"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6455"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16410"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889982.pdf?arnumber=10889982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:11Z","timestamp":1774416191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889982","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}