{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:30Z","timestamp":1792786950770,"version":"4.5.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information and communications Technology Planning and Evaluation","id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Ministry of Science and ICT","award":["RS2022-00144444"],"award-info":[{"award-number":["RS2022-00144444"]}],"id":[{"id":"https:\/\/ror.org\/01wpjm123","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3722239","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:04:13Z","timestamp":1786475053000},"page":"15571-15588","source":"Crossref","is-referenced-by-count":1,"title":["PRIMEdit: Probability Redistribution for Instance-Aware Multi-Object Video Editing With a New Benchmark Dataset"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1893-0551","authenticated-orcid":false,"given":"Samuel","family":"Teodoro","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology","place":["Daejeon, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agus","family":"Gunawan","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology","place":["Daejeon, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8104-4100","authenticated-orcid":false,"given":"Soo Ye","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-0529","authenticated-orcid":false,"given":"Jihyong","family":"Oh","sequence":"additional","affiliation":[{"name":"Chung-Ang University","place":["Seoul, South Korea"],"department":["Department of Imaging Science, GSAIM"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0146-5419","authenticated-orcid":false,"given":"Munchurl","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology","place":["Daejeon, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"The rise of mobile and social short-form video: An in-depth measurement study of vine","volume-title":"Proc. Workshop Social Multimedia Storytelling","author":"Vandersmissen"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642476"},{"key":"ref3","first-page":"1","article-title":"Automation in video editing: Assisted workflows in video editing","volume-title":"Proc. Workshop Automat. Experience Workplace Co-Located Conf. Hum. Factors Comput. Syst.","volume":"2905","author":"Soe"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app13063386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00684"},{"key":"ref12","article-title":"Consistent video-to-video transfer using synthetic dataset","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"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":"FLATTEN: Optical flow-guided attention for consistent text-to-video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cong"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"ref19","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geyer"},{"key":"ref20","article-title":"Ground-a-video: Zero-shot grounded video editing using text-to-image diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jeong"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13436"},{"key":"ref24","article-title":"VideoGrain: Modulating space-time attention for multi-grained video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1143"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref31","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref32","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref34","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref36","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref39","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref40","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref42","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref44","first-page":"9109","article-title":"Slicedit: Zero-shot video editing with text-to-image diffusion models using spatio-temporal slices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3061"},{"key":"ref47","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref49","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_w01851"},{"key":"ref51","article-title":"HunyuanVideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00616"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0586"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2423"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00674"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02179"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01762"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref64","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref65","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref69","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref72","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref73","article-title":"CVPR 2023 text guided video editing competition","author":"Wu","year":"2023"},{"key":"ref74","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00081"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11646984.pdf?arnumber=11646984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:12:00Z","timestamp":1791486720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11646984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":79,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3722239","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}