{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:56:18Z","timestamp":1762800978254,"version":"build-2065373602"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3624055","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:10:01Z","timestamp":1761066601000},"page":"187236-187245","source":"Crossref","is-referenced-by-count":0,"title":["4EV: Adaptive Video Editing With Spatial Temporal Dynamics and Motion Pathways"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2944-7493","authenticated-orcid":false,"given":"Namrata","family":"Patel","sequence":"first","affiliation":[{"name":"Artificial Intelligence, Yeshiva University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3593-9598","authenticated-orcid":false,"given":"Lakshmi","family":"Priya Ramisetty","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Yeshiva University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7605-3232","authenticated-orcid":false,"given":"Aditya","family":"Singh Parmar","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Yeshiva University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8276-9664","authenticated-orcid":false,"given":"Jialu","family":"Li","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Yeshiva University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-0979","authenticated-orcid":false,"given":"Youshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chuzhou University, Chuzhou, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MotionDirector: Motion customization of text-to-video diffusion models","author":"Zhao","year":"2023","journal-title":"arXiv:2310.08465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687652"},{"key":"ref3","article-title":"Tune-A-Video: One-shot tuning of image diffusion models for text-to-video generation","author":"Wu","year":"2022","journal-title":"arXiv:2212.11565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/244130.244145"},{"key":"ref6","article-title":"CustomVideo: Customizing text-to-video generation with multiple subjects","author":"Wang","year":"2024","journal-title":"arXiv:2401.09962"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2668904.2668936"},{"key":"ref8","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021","journal-title":"arXiv:2110.04627"},{"key":"ref9","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"volume-title":"What Are Diffusion Models?","year":"2021","author":"Weng","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015763"},{"key":"ref12","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref13","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref14","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref15","article-title":"AnyV2V: A tuning-free framework for any video-to-video editing tasks","author":"Ku","year":"2024","journal-title":"arXiv:2403.14468"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_30"},{"article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Meng","key":"ref17"},{"key":"ref18","article-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2303.07909"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref21","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480546"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref24","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv:2302.01329"},{"key":"ref25","article-title":"Control-A-video: Controllable text-to-video diffusion models with motion prior and reward feedback learning","author":"Chen","year":"2023","journal-title":"arXiv:2305.13840"},{"key":"ref26","article-title":"MagicProp: Diffusion-based video editing via motion-aware appearance propagation","author":"Yan","year":"2023","journal-title":"arXiv:2309.00908"},{"key":"ref27","article-title":"SinFusion: Training diffusion models on a single image or video","author":"Nikankin","year":"2022","journal-title":"arXiv:2211.11743"},{"key":"ref28","first-page":"16761","article-title":"Hierarchical patch VAE-GAN: Generating diverse videos from a single sample","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Gur"},{"key":"ref29","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"ref32","article-title":"Controlnet: Conditional control of diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv.2302.05543"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11214174.pdf?arnumber=11214174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:50:06Z","timestamp":1762800606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3624055","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}