{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T03:22:42Z","timestamp":1782012162512,"version":"3.54.5"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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","award":["62222209"],"award-info":[{"award-number":["62222209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","award":["BNR2023TD03006"],"award-info":[{"award-number":["BNR2023TD03006"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Lab of Networked Multimedia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557634","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:54:21Z","timestamp":1744134861000},"page":"2875-2885","source":"Crossref","is-referenced-by-count":4,"title":["VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0943-2286","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanning","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0886-8296","authenticated-orcid":false,"given":"Yipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9582-7331","authenticated-orcid":false,"given":"Yuwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7463-2252","authenticated-orcid":false,"given":"Feilin","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Film and TV Technology, Beijing Film Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8474-0027","authenticated-orcid":false,"given":"Yaofei","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref3","first-page":"1","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Hong","year":"2022"},{"key":"ref4","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref5","first-page":"1","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref8","first-page":"26135","article-title":"Free-bloom: Zero-shot text-to-video generator with LLM director and LDM animator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang","year":"2024"},{"key":"ref9","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2023"},{"key":"ref10","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref11","first-page":"1","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref12","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"issue":"PMLR","key":"ref13","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"issue":"PMLR","key":"ref14","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref16","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"key":"ref21","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref23","first-page":"1","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Villegas"},{"key":"ref24","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref27","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023"},{"key":"ref28","article-title":"Controlvideo: Adding conditional control for one shot text-to-video editing","author":"Zhao","year":"2023"},{"key":"ref29","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref33","first-page":"1","article-title":"An image is worth oneword: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gal"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref36","first-page":"1","article-title":"Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref37","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Guet al."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref39","first-page":"30286","article-title":"Subject-driven text-to-image generation via apprenticeship learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref44","article-title":"Videoassembler: Identity-consistent video generation with reference entities using diffusion model","author":"Zhao","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref50","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref51","first-page":"5775","article-title":"DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lu","year":"2022"},{"key":"ref52","first-page":"1","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc 11th Int. Conf. Learn. Representations","author":"Feng","year":"2022"},{"key":"ref53","first-page":"1","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref54","article-title":"Diffusers: State-of-the-art diffusion models","author":"Platen","year":"2022"},{"key":"ref55","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref56","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref57","article-title":"The OpenCV library","author":"Bradski","year":"2000","journal-title":"Dr Dobb\u2019s J. Softw. Tools"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10950092.pdf?arnumber=10950092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:49Z","timestamp":1748539849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10950092\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557634","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}