{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:48:07Z","timestamp":1775540887720,"version":"3.50.1"},"reference-count":70,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006"],"award-info":[{"award-number":["62032006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472098"],"award-info":[{"award-number":["62472098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651052","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:52Z","timestamp":1768255312000},"page":"2460-2473","source":"Crossref","is-referenced-by-count":1,"title":["LSTD: Long Short-Term Temporal Diffusion for Video Generation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3832-6439","authenticated-orcid":false,"given":"Haoyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6201-9503","authenticated-orcid":false,"given":"Jiaxi","family":"Gu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3981-0552","authenticated-orcid":false,"given":"Shicong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7803-194X","authenticated-orcid":false,"given":"Tianyi","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1721-035X","authenticated-orcid":false,"given":"Xing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5807","authenticated-orcid":false,"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-8972","authenticated-orcid":false,"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah'ark Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209702"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3226413"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3262972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref7","first-page":"1","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref8","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref9","first-page":"1","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hong","year":"2023"},{"key":"ref10","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref12","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref13","first-page":"31769","article-title":"Generating long videos of dynamic scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Brooks","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.73"},{"key":"ref15","article-title":"Videodirectorgpt: Consistent multi-scene video generation via LLM-guided planning","author":"Lin","year":"2023"},{"key":"ref16","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-68677-4","volume-title":"Artificial General Intelligence","volume":"2","author":"Goertzel","year":"2007"},{"key":"ref19","article-title":"AI-gas: Ai-generating algorithms, an alternate paradigm for producing general artificial intelligence","author":"Clune","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-020-0494-4"},{"key":"ref21","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref26","first-page":"1","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","article-title":"Enhancing diffusion-based image synthesis with robust classifier guidance","author":"Kawar","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref31","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref32","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":"ref33","first-page":"1","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vondrick","year":"2016,"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref36","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref40","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3262180"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251095"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3284989"},{"key":"ref46","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126682"},{"key":"ref51","article-title":"A short note on the kinetics-700-2020 human action dataset","author":"Smaira","year":"2020"},{"key":"ref52","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"ref54","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref55","first-page":"1","article-title":"FVD: A new metric for video generation","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Unterthiner","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref59","article-title":"GODIVA: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref60","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref61","first-page":"7594","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00628"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref67","first-page":"22185","article-title":"Video-LaVIT: Unified video-language pre-training with decoupled visual-motional tokenization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin","year":"2024"},{"key":"ref68","article-title":"VideoCrafter11: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref69","article-title":"ConsistI2V2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_21"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11345153.pdf?arnumber=11345153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:52:46Z","timestamp":1775537566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651052","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}