{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:26:34Z","timestamp":1782318394987,"version":"3.54.5"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L221013"],"award-info":[{"award-number":["L221013"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Planning Project","doi-asserted-by":"publisher","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Council, Taiwan","award":["113-2221-E-006-161-MY3"],"award-info":[{"award-number":["113-2221-E-006-161-MY3"]}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tvcg.2025.3568880","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T13:44:06Z","timestamp":1747057446000},"page":"8372-8384","source":"Crossref","is-referenced-by-count":3,"title":["MotionCrafter: Plug-and-Play Motion Guidance for Diffusion Models"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6433-2678","authenticated-orcid":false,"given":"Yuxin","family":"Zhang","sequence":"first","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-6584","authenticated-orcid":false,"given":"Nisha","family":"Huang","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-6428","authenticated-orcid":false,"given":"Haibin","family":"Huang","sequence":"additional","affiliation":[{"name":"Visual Generation and Interaction Center, Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8243-9513","authenticated-orcid":false,"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Visual Generation and Interaction Center, Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Visual Generation and Interaction Center, Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","article-title":"Video diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ho"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref5","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref7","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref8","article-title":"Animate-A-Story: Storytelling with retrieval-augmented video generation","author":"He","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3398538"},{"key":"ref11","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref12","article-title":"Imagen Video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref14","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref15","article-title":"ControlVideo: Training-free controllable text-to-video generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref16","article-title":"Control-a-Video: Controllable text-to-video generation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref19","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref20","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref22","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref26","first-page":"51008","article-title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref27","article-title":"$p+$p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_16"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.82"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09396-3_9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref45","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_34"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11151252\/10999055.pdf?arnumber=10999055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:52:12Z","timestamp":1757371932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10999055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":44,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3568880","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}