{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:38:45Z","timestamp":1771922325713,"version":"3.50.1"},"reference-count":39,"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\/iccvw69036.2025.00371","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"3554-3563","source":"Crossref","is-referenced-by-count":0,"title":["MG-Gen: Single Image to Motion Graphics Generation"],"prefix":"10.1109","author":[{"given":"Takahiro","family":"Shirakawa","sequence":"first","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoyuki","family":"Suzuki","sequence":"additional","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuto","family":"Narumoto","sequence":"additional","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daichi","family":"Haraguchi","sequence":"additional","affiliation":[{"name":"CyberAgent"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/642675.642677"},{"key":"ref4","volume-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","year":"2025"},{"key":"ref5","volume-title":"DocumentAI","year":"2025"},{"key":"ref6","volume-title":"Gemini","year":"2025"},{"key":"ref7","volume-title":"Veo","year":"2025"},{"key":"ref8","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref11","article-title":"Free-Bloom: Zero-shot text-to-video generator with LLM director and LDM animator","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref13","article-title":"TextAI-ive: Integrated design environment for kinetic typography","volume-title":"CHI","author":"Kato","year":"2015"},{"key":"ref14","article-title":"YOLOv11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","volume-title":"KlingAI","year":"2025"},{"key":"ref17","article-title":"LLM-grounded video diffusion models","volume-title":"ICLR","author":"Lian","year":"2024"},{"key":"ref18","article-title":"VideoDirectorGPT: Consistent multi-scene video generation via llm-guided planning","volume-title":"COLM","author":"Lin","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714155"},{"key":"ref20","volume-title":"Ray2","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref23","volume-title":"GPT-4o","year":"2025"},{"key":"ref24","volume-title":"o3","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_10"},{"key":"ref26","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"ConsistI2V: Enhancing visual consistency for image-to-video generation","volume-title":"Transactions on Machine Learning Research","author":"Ren","year":"2024"},{"key":"ref28","volume-title":"Gen-3 Alpha","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref30","article-title":"Generating animated layouts as structured text representations","author":"Shin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_12"},{"key":"ref34","article-title":"Keyframer: Empowering animation design using large language models","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"VideoComposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3286392"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606813"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3495831"}],"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\/11375216.pdf?arnumber=11375216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:33:55Z","timestamp":1771918435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00371","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}