{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:44Z","timestamp":1777865324472,"version":"3.51.4"},"reference-count":59,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212,623B2094"],"award-info":[{"award-number":["62222212,623B2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01538","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16565-16575","source":"Crossref","is-referenced-by-count":1,"title":["DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization"],"prefix":"10.1109","author":[{"given":"Wenchuan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijing","family":"Tu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"An","year":"2023","journal-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755462"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"issue":"4","key":"ref6","volume":"3","author":"Chen","year":"2023","journal-title":"Disenbooth: Disentangled parameter-efficient tuning for subject-driven text-to-image generation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32210"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref10","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion"},{"key":"ref11","author":"Geyer","year":"2023","journal-title":"Tokenflow: Consistent diffusion features for consistent video editing"},{"key":"ref12","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref14","author":"He","year":"2024","journal-title":"Id-animator: Zero-shot identity-preserving human video generation"},{"key":"ref15","author":"Hendrycks","year":"2016","journal-title":"Gaussian error linear units (gelus)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref17","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"issue":"2","key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547881"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref23","author":"Jabri","year":"2022","journal-title":"Scalable adaptive computation for iterative generation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref25","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref27","volume-title":"Cones 2: Customizable image synthesis with multiple subjects","author":"Liu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3623025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref31","author":"Molad","year":"2023","journal-title":"Dreamix: Video diffusion models are general video editors"},{"key":"ref32","article-title":"OpenAI","year":"2024","journal-title":"Sora"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref40","volume-title":"1st place solution in google universal image embedding challenge","author":"Shao","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref42","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref43","author":"Seale Smith","year":"2023","journal-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09396-3_9"},{"key":"ref45","author":"Soomro","year":"2012","journal-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild"},{"key":"ref46","author":"Tan","year":"2024","journal-title":"Animate-x: Universal character image animation with enhanced motion representation"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref48","author":"Wang","year":"2023","journal-title":"Modelscope text-to-video technical report"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3668653"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref53","author":"Wu","year":"2024","journal-title":"Motionbooth: Motion-aware customized text-to-video generation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"ref56","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref59","author":"Zhou","year":"2022","journal-title":"Magicvideo: Efficient video generation with latent diffusion models"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445687.pdf?arnumber=11445687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:36Z","timestamp":1777529736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01538","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}