{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:25:19Z","timestamp":1782318319844,"version":"3.54.5"},"reference-count":94,"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\/501100001666","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006,62472098"],"award-info":[{"award-number":["62032006,62472098"]}],"id":[{"id":"10.13039\/501100001666","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\/iccv51701.2025.01126","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12112-12123","source":"Crossref","is-referenced-by-count":5,"title":["MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance"],"prefix":"10.1109","author":[{"given":"Quanhao","family":"Li","sequence":"first","affiliation":[{"name":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Xing","sequence":"additional","affiliation":[{"name":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dai","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of CS, Fudan University,Shanghai Key Lab of Intell. Info. Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","author":"Bhat","year":"2025","journal-title":"Simgen: A diffusion-based framework for simultaneous surgical image and segmentation mask generation"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref6","author":"Chen","year":"2023","journal-title":"Videocrafter1: Open diffusion models for high-quality video generation"},{"key":"ref7","article-title":"Panda-70m: Captioning 70 m videos with multiple cross-modality teachers","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref8","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref11","article-title":"Challenge report: Track 2 of multimodal perception and comprehension of corner cases in autonomous driving","volume-title":"ECCV Workshop","author":"Du","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref13","article-title":"3dtrajmaster: Mastering 3d trajectory for multientity motion in video generation","author":"Fu","year":"2025","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref16","article-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Video diffusion models","volume":"35","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref21","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00772"},{"key":"ref23","volume-title":"JovianZM. Pexels-400k dataset","year":"2024"},{"key":"ref24","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","author":"Ju","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref26","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref28","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref31","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref32","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref35","article-title":"Sg-i2v: Selfguided trajectory control in image-to-video generation","author":"Namekata","year":"2025","journal-title":"ICLR"},{"key":"ref36","author":"Nichol","year":"2021","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00387"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","author":"Qiu","year":"2024","journal-title":"Freetraj: Tuning-free trajectory control in video diffusion models"},{"key":"ref40","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref41","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref42","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. transfer.","author":"Ranftl","year":"2020","journal-title":"TPAMI"},{"key":"ref43","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref44","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref47","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref49","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref50","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref51","author":"Tian","year":"2025","journal-title":"Unigen: Enhanced training & test-time strategies for unified multimodal understanding and generation"},{"key":"ref52","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00753"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"ref57","author":"Tu","year":"2025","journal-title":"Stableanimator++: Overcoming pose misalignment and face distortion for human image animation"},{"key":"ref58","author":"Wan","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01165"},{"key":"ref60","volume-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024"},{"key":"ref61","author":"Wang","year":"2025","journal-title":"Simplear: Pushing the frontier of autoregressive visual generation through pretraining, sft, and rl"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730755"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02810-6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref67","author":"Wei","year":"2024","journal-title":"Dreamvideo-2: Zero-shot subjectdriven video customization with precise motion control"},{"key":"ref68","article-title":"Genrec: Unifying video generation and recognition with diffusion models","author":"Weng","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38086"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"ref74","author":"Xing","year":"2023","journal-title":"Vidiff: Translating videos via multi-modal instructions with diffusion models"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref76","author":"Xing","year":"2024","journal-title":"Aid: Adapting image2video diffusion models for instruction-guided video prediction"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref82","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01696"},{"key":"ref84","author":"Yin","year":"2023","journal-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33075"},{"key":"ref86","author":"Zhang","year":"2024","journal-title":"Creatilayout: Siamese multimodal diffusion transformer for creative layout-to-image generation"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01203"},{"key":"ref88","author":"Zhang","year":"2025","journal-title":"Creatidesign: A unified multi-conditional diffusion transformer for creative graphic design"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref90","author":"Zhang","year":"2025","journal-title":"Reasongen-r1: Cot for autoregressive image generation models through sft and rl"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00198"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref93","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"}],"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\/11444518.pdf?arnumber=11444518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:32Z","timestamp":1777530092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01126","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}