{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T22:37:37Z","timestamp":1773527857117,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00399","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"3831-3836","source":"Crossref","is-referenced-by-count":1,"title":["Generating Visually Consistent Images for Storytelling via Narrative Graph Prompting"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Shin","sequence":"first","affiliation":[{"name":"Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunitake","family":"Kaneko","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"ref3","article-title":"Storydall-e: Adapting pretrained text-toimage transformers for story continuation","volume":"1","author":"Maharana","year":"2022","journal-title":"ArXiv, abs\/2209.06192"},{"key":"ref4","volume-title":"Dall.e 3","volume":"4","year":"2023"},{"key":"ref5","volume-title":"Hello gpt-4o","volume":"4","year":"2024"},{"key":"ref6","volume-title":"Creating video from text","volume":"1","year":"2024"},{"key":"ref7","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ArXiv, abs\/2102.12092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref10","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"1","author":"Saharia","year":"2022","journal-title":"ArXiv, abs\/2205.11487"},{"key":"ref11","article-title":"The lost melody: Empirical observations on text-to-video generation from a storytelling perspective","volume":"1","author":"Shin","year":"2024","journal-title":"ArXiv, abs\/2405.08720"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"issue":"2","key":"ref13","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","volume":"1","author":"Zhou","year":"2024","journal-title":"ArXiv, abs\/2405.01434"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375781.pdf?arnumber=11375781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:17:21Z","timestamp":1771921041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00399","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}