{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:38:30Z","timestamp":1772933910026,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["2205472"],"award-info":[{"award-number":["2205472"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401904","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"1307-1316","source":"Crossref","is-referenced-by-count":0,"title":["DAADiff: A Dual-Axis Adaptive Framework for Real-Time Video Inpainting"],"prefix":"10.1109","author":[{"given":"Zheyan","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern University,Department of Industrial Engineering and Management Sciences,Evanston,IL,USA,60208"}]},{"given":"Diego","family":"Klabjan","sequence":"additional","affiliation":[{"name":"Northwestern University,Department of Industrial Engineering and Management Sciences,Evanston,IL,USA,60208"}]},{"given":"Renee C. B.","family":"Manworren","sequence":"additional","affiliation":[{"name":"College of Nursing and Health Innovation, The University of Texas at Arlington,Arlington,TX,USA,76019"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app132011189"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3497918"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"ref4","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2019.05.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3550038"},{"key":"ref9","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref10","author":"Polyak","year":"2025","journal-title":"Movie gen: a cast of media foundation models"},{"key":"ref11","article-title":"Make-a-video: text-to-video generation without text-video data","volume-title":"International Conference on Learning Representations","author":"Singer","year":"2023"},{"key":"ref12","author":"Villegas","year":"2022","journal-title":"Phenaki: variable length video generation from open domain textual description"},{"key":"ref13","first-page":"10674","article-title":"Stable video diffusion: scaling latent video diffusion models to large datasets","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Blattmann","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref15","article-title":"Cogvideo: large-scale pretraining for text-to-video generation via transformers","volume-title":"International Conference on Learning Representations","author":"Hong","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32477"},{"key":"ref18","article-title":"Real-time facial surface geometry from monocular video on mobile GPUs","volume-title":"Proceedings of the IEEE\/CVF Workshop on Computer Vision Patterns for Augmented and Virtual Reality","author":"Kartynnik","year":"2019"},{"key":"ref19","article-title":"VideoPainter: a dual-branch diffusion transformer for high-quality video inpainting","volume-title":"Proceedings of the SIGGRAPH Conference","author":"Yu","year":"2025"},{"issue":"11","key":"ref20","first-page":"139144","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2014","journal-title":"Communications of the ACM"},{"key":"ref21","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"International Conference on Learning Representations","author":"Brock","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref23","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"Razavi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"van den Oord","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_42"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford","year":"2021"},{"key":"ref31","article-title":"Cross-modal contextualized diffusion models for text-guided visual generation and editing","volume-title":"International Conference on Learning Representations","author":"Yang","year":"2024"},{"key":"ref32","first-page":"3887","article-title":"One-shot talking face generation from a single image","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Wang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/informatics11030059"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref37","author":"Wan","year":"2025","journal-title":"Wan: open and advanced largescale video generative models"},{"key":"ref38","author":"Labs","year":"2025","journal-title":"FLUX. 1 Kontext: flow matching for in-context image generation and editing in latent space"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"ref42","author":"Qiu","year":"2025","journal-title":"Skyreels-a1: Expressive portrait animation in video diffusion transformers"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00247"},{"key":"ref44","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref46","article-title":"Towards accurate generative models of video: a new metric & challenges","volume-title":"International Conference on Learning Representations","author":"Unterthiner","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref48","article-title":"Evaluation agent: a comprehensive evaluation framework for visual generative models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3321534"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401904.pdf?arnumber=11401904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:03Z","timestamp":1772866503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401904","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}