{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:40Z","timestamp":1777865380613,"version":"3.51.4"},"reference-count":61,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3807600"],"award-info":[{"award-number":["2023YFC3807600"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01023","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10995-11005","source":"Crossref","is-referenced-by-count":0,"title":["Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer"],"prefix":"10.1109","author":[{"given":"Qingyu","family":"Shi","sequence":"first","affiliation":[{"name":"PKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wu","sequence":"additional","affiliation":[{"name":"PKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinbin","family":"Bai","sequence":"additional","affiliation":[{"name":"NUS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"UC Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[{"name":"PKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"NTU"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Integrating view conditions for image synthesis","author":"Bai","year":"2023","journal-title":"arXiv"},{"key":"ref2","article-title":"Humanedit: A highquality human-rewarded dataset for instruction-based image editing","author":"Bai","year":"2024","journal-title":"arXiv"},{"key":"ref3","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","author":"Bai","year":"2024","journal-title":"arXiv"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Pixart- \u03b1 : Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2023"},{"key":"ref9","article-title":"\u03b4-dit: A training-free acceleration method tailored for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01265","article-title":"Panda-70m: Captioning 70 m videos with multiple cross-modality teachers","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-1209-4_1"},{"key":"ref12","article-title":"Computing discrete fr\u00e9chet distance","volume-title":"Christian Doppler Laboratory for Expert Systems","author":"Eiter","year":"1994"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33819"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00674"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"ref17","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","volume-title":"ICLR","author":"Geyer","year":"2024"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref19","article-title":"Photorealistic video generation with diffusion models","author":"Gupta","year":"2023","journal-title":"arXiv"},{"key":"ref20","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref23","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv"},{"key":"ref32","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3532719.3543228"},{"key":"ref37","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2022"},{"key":"ref38","volume-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32685"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02133"},{"key":"ref43","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2018","journal-title":"arXiv"},{"key":"ref44","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref45","article-title":"Customize-a-video: One-shot motion customization of text-to-video diffusion models","volume-title":"ECCV","author":"Ren","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref50","article-title":"Motion inversion for video customization","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref54","volume-title":"Cvpr 2023 text guided video editing competition","author":"Wu","year":"2023"},{"key":"ref55","article-title":"Video diffusion models are training-free motion interpreter and controller","volume-title":"NeurIPS","author":"Xiao","year":"2024"},{"key":"ref56","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv"},{"key":"ref57","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref58","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","volume-title":"ICLR","author":"Yang","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref60","article-title":"Motiondirector: Motion customization of text-tovideo diffusion models","volume-title":"ECCV","author":"Zhao","year":"2024"},{"key":"ref61","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv"}],"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\/11444833.pdf?arnumber=11444833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:31Z","timestamp":1777530151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01023","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}