{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:23:04Z","timestamp":1780053784933,"version":"3.54.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3262972","type":"journal-article","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T19:16:46Z","timestamp":1680117406000},"page":"190-201","source":"Crossref","is-referenced-by-count":16,"title":["Controllable Video Generation With Text-Based Instructions"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8966-592X","authenticated-orcid":false,"given":"Ali","family":"K\u00f6ksal","sequence":"first","affiliation":[{"name":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenan E.","family":"Ak","sequence":"additional","affiliation":[{"name":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7224-6726","authenticated-orcid":false,"given":"Ying","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7788-8368","authenticated-orcid":false,"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4103-3824","authenticated-orcid":false,"given":"Joo Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2920613"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01284-z"},{"key":"ref3","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2950198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001536"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2963621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960700"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_33"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3306305.3332370"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2885235"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11012-3_32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00923"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01448"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"key":"ref28","article-title":"Vid2game: Controllable characters extracted from real-world videos","author":"Gafni","year":"2019"},{"key":"ref29","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen","year":"2018"},{"key":"ref30","first-page":"344","article-title":"Self-supervised visual planning with temporal skip connections","volume-title":"Proc. Conf. Robot Learn.","author":"Ebert","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"ref32","first-page":"3560","article-title":"Learning to generate long-term future via hierarchical prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Villegas","year":"2017"},{"key":"ref33","first-page":"1","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin","year":"2019"},{"key":"ref34","first-page":"1","article-title":"Action-conditional video prediction using deep networks in atari games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Oh","year":"2015"},{"key":"ref35","first-page":"1","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Finn","year":"2016"},{"key":"ref36","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"ref37","article-title":"Phenaki: Variable length video generation from open domain textual description","author":"Villegas","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref39","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref40","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref45","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref46","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref48","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018"},{"key":"ref49","first-page":"3233","article-title":"Stochastic latent residual video prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref51","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref52","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denton","year":"2018"},{"key":"ref53","article-title":"Stochastic variational video prediction","author":"Babaeizadeh","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5220\/0010241801010112"},{"key":"ref55","article-title":"Adversarial video generation on complex datasets","author":"Clark","year":"2019"},{"key":"ref56","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref57","article-title":"Transformation-based adversarial video prediction on large-scale data","author":"Luc","year":"2020"},{"key":"ref58","article-title":"Transframer: Arbitrary frame prediction with generative models","author":"Nash","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897982"},{"key":"ref60","first-page":"14042","article-title":"CCVS: Context-aware controllable video synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Moing","year":"2021"},{"key":"ref61","article-title":"Scaling autoregressive video models","author":"Weissenborn","year":"2019"},{"key":"ref62","article-title":"FitVid: Overfitting in pixel-level video prediction","author":"Babaeizadeh","year":"2021"},{"key":"ref63","article-title":"Masked conditional video diffusion for prediction, generation, and interpolation","author":"Voleti","year":"2022"},{"key":"ref64","article-title":"Diffusion models for video prediction and infilling","author":"Hppe","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10086635.pdf?arnumber=10086635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:02:53Z","timestamp":1705024973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10086635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3262972","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}