{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T22:25:00Z","timestamp":1743373500499,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446420","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3350-3354","source":"Crossref","is-referenced-by-count":2,"title":["Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning for Visual Story Synthesis"],"prefix":"10.1109","author":[{"given":"Tianyi","family":"Song","sequence":"first","affiliation":[{"name":"Southeast University,School of Cyber Science and Engineering,Nanjing,China"}]},{"given":"Jiuxin","family":"Cao","sequence":"additional","affiliation":[{"name":"Southeast University,School of Cyber Science and Engineering,Nanjing,China"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Southeast University,School of Cyber Science and Engineering,Nanjing,China"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.194"},{"key":"ref7","article-title":"Neural discrete representation learning","author":"Oord","year":"2017","journal-title":"Cornell University -arXiv,Cornell University - arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3374587.3374649"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning, International Conference on Machine Learning","author":"Ramesh","key":"ref10"},{"key":"ref11","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"article-title":"Synthesizing coherent story with auto-regressive latent diffusion models","year":"2022","author":"Pan","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref19","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref20"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_2"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446420.pdf?arnumber=10446420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:15:36Z","timestamp":1722575736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446420","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}