{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:22Z","timestamp":1778048302014,"version":"3.51.4"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00010","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"12-21","source":"Crossref","is-referenced-by-count":0,"title":["ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Sibo","family":"Dong","sequence":"first","affiliation":[{"name":"Georgetown University,Department of Computer Science,Washington, D.C.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismail","family":"Shaheen","sequence":"additional","affiliation":[{"name":"Georgetown University,Department of Computer Science,Washington, D.C.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maggie","family":"Shen","sequence":"additional","affiliation":[{"name":"Georgetown University,Department of Computer Science,Washington, D.C.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rupayan","family":"Mallick","sequence":"additional","affiliation":[{"name":"Georgetown University,Department of Computer Science,Washington, D.C.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah Adel","family":"Bargal","sequence":"additional","affiliation":[{"name":"Georgetown University,Department of Computer Science,Washington, D.C.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657430"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3600149"},{"key":"ref7","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel","year":"2017"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref10","author":"Jeong","year":"2023","journal-title":"Zero-shot generation of coherent storybook from plain text story using diffusion models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.537"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"ref14","article-title":"One-prompt-one-story: Free-lunch consistent text-to-image generation using a single prompt","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu"},{"key":"ref15","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32644"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"ref18","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Nichol"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00290"},{"key":"ref20","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00246"},{"key":"ref23","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01239"},{"key":"ref28","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref29","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446420"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref33","author":"Tian","year":"2024","journal-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer"},{"key":"ref34","author":"Wang","year":"2024","journal-title":"Oneactor: Consistent character generation via cluster-conditioned guidance"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00197"},{"key":"ref36","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models"},{"key":"ref37","author":"Zheng","year":"2024","journal-title":"Temporalstory: Enhancing consistency in story visualization using spatial-temporal attention"},{"key":"ref38","author":"Zhou","year":"2024","journal-title":"Story-diffusion: Consistent self-attention for long-range image and video generation"},{"key":"ref39","author":"Zhou","year":"2024","journal-title":"Storymaker: Towards holistic consistent characters in text-to-image generation"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02267-5"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492010.pdf?arnumber=11492010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:36Z","timestamp":1778046816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00010","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}