{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:41:06Z","timestamp":1777322466820,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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 Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651097","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"3202-3213","source":"Crossref","is-referenced-by-count":0,"title":["FluencyVE: Marrying Temporal-Aware Mamba with Bypass Attention for Video Editing"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8944-9164","authenticated-orcid":false,"given":"Mingshu","family":"Cai","sequence":"first","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4015-7681","authenticated-orcid":false,"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4192-554X","authenticated-orcid":false,"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Ieiri","sequence":"additional","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Ramesh","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00355"},{"key":"ref5","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref6","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00867"},{"key":"ref9","article-title":"SAVE: Spectral-shift-aware adaptation of image diffusion models for text-driven video editing","author":"Karim","year":"2023"},{"key":"ref10","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. Conf. Lang. Modeling","author":"Gu","year":"2024"},{"key":"ref11","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867934"},{"key":"ref13","first-page":"1060","article-title":"Generative adversarial text-to-image synthesis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref14","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref17","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref18","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340089"},{"key":"ref22","first-page":"6708","article-title":"Vid2Vid: Video-to-video synthesis","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref27","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","year":"2023"},{"key":"ref28","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref34","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geyer","year":"2024"},{"key":"ref35","article-title":"FLATTEN: Optical flow-guided attention for consistent text-to-video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cong","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref37","first-page":"9109","article-title":"Sliceedit: Zero-shot video editing with text-to-image diffusion models using spatio-temporal slices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref39","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref40","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu","year":"2021"},{"key":"ref41","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref42","first-page":"1474","article-title":"HiPPO: Recurrent memory with optimal polynomial projections","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu","year":"2020"},{"key":"ref43","article-title":"VMamba: Visual state space model","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref44","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref47","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref49","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.125"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref53","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref54","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref55","article-title":"CVPR 2023 text guided video editing competition","author":"Wu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329476.pdf?arnumber=11329476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:50:28Z","timestamp":1777319428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651097","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}