{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:25:21Z","timestamp":1782318321796,"version":"3.54.5"},"reference-count":77,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01052","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11305-11316","source":"Crossref","is-referenced-by-count":2,"title":["Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent"],"prefix":"10.1109","author":[{"given":"Xinyao","family":"Liao","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianfang","family":"Zeng","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liao","family":"Wang","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01334"},{"key":"ref11","article-title":"Animateanything: Finegrained open domain image animation with motion guidance","author":"Dai","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"I2vcontrol: Disentangled and unified video motion synthesis control","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref19","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref24","article-title":"Direct2v: Large language models are frame-level directors for zero-shot text-to-video generation","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Free-bloom: Zero-shot text-to-video generator with 11 m director and 1 dm animator","volume":"36","author":"Huang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref27","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02602"},{"key":"ref30","article-title":"Animdirector: A large multimodal model powered agent for controllable animation video generation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Image conductor: Precision control for interactive video synthesis","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Videodirectorgpt: Consistent multi-scene video generation via 11 m -guided planning","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1726"},{"key":"ref35","article-title":"Flowzero: Zero-shot text-to-video synthesis with 11 m -driven dynamic scene syntax","volume-title":"arXiv preprint","author":"Lu","year":"2023"},{"key":"ref36","article-title":"Cinemo: Consistent and controllable image animation with motion diffusion models","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Follow-your-click: Opendomain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref40","article-title":"Mtvg: Multi-text video generation with text-tovideo models","author":"Oh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","volume-title":"Chatgpt","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref43","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"234","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference","author":"Ronneberger"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref47","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Videoagent: Self-improving video generation","author":"Soni","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Motionzero: Exploiting motion priors for zero-shot text-to-video generation","author":"Su","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Vidgen-1m: A large-scale dataset for text-to-video generation","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","volume-title":"Vbench leaderboard","year":"2024"},{"key":"ref52","first-page":"16558","article-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref53","article-title":"Videotetris: Towards compositional text-to-video generation","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00789"},{"key":"ref55","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Cpa: Camera-pose-awareness diffusion transformer for video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02810-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref59","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref61","article-title":"Dreamfactory: Pioneering multi-scene long video generation with a multi-agent framework","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref64","article-title":"Cavia: Camera-controllable multi-view video diffusion with view-integrated attention","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref68","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00198"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713600"},{"key":"ref73","article-title":"Moonshot: Towards controllable video generation and editing with multimodal conditions","author":"Junhao Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"}],"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\/11444765.pdf?arnumber=11444765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:47Z","timestamp":1777530047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01052","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}