{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:20:06Z","timestamp":1761895206616,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209951","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multi-sentence Video Grounding for Long Video Generation"],"prefix":"10.1109","author":[{"given":"Wei","family":"Feng","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Multi-modal generative ai: Multi-modal llm, diffusion and beyond","year":"2024","author":"Chen","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.73"},{"article-title":"Retrieval-augmented generation for large language models: A survey","year":"2023","author":"Gao","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3532626"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612401"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.530"},{"article-title":"Verified: A video corpus moment retrieval benchmark for fine-grained video understanding","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Chen","key":"ref10"},{"article-title":"Mvmr: Evaluating natural language video localization bias over multiple reliable videos pool","year":"2023","author":"Yang","key":"ref11"},{"article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","key":"ref12"},{"article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4596-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00756"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"article-title":"Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qiu","key":"ref26"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209951.pdf?arnumber=11209951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:45:45Z","timestamp":1761889545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209951","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}