{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:24Z","timestamp":1777890264060,"version":"3.51.4"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00518","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5458-5468","source":"Crossref","is-referenced-by-count":0,"title":["Met\n                    <sup>2<\/sup>\n                    Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems"],"prefix":"10.1109","author":[{"given":"Shaohan","family":"Li","sequence":"first","affiliation":[{"name":"Chengdu University of Information Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Chengdu University of Information Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Qin","sequence":"additional","affiliation":[{"name":"Chengdu Institute of Computer Applications, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06185-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"26950","article-title":"Mau: A motionaware unit for video prediction and beyond","volume":"34","author":"Chang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Fengwu: Pushing the skillful global mediumrange weather forecast beyond 10 days lead","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02178"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41612-023-00512-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3431099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/393"},{"key":"ref10","first-page":"1970","volume-title":"The atlas of mortality and economic losses from weather, climate and water extremes","author":"Douris","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s43247-023-01144-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413914"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/15481603.2023.2203363"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00593"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosenv.2021.118737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.122155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref24","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"International conference on machine learning","author":"Kornblith"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi2336"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110176"},{"key":"ref28","article-title":"Moganet: Multi-order gated aggregation network","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref29","first-page":"7","article-title":"Moganet: Multi-order gated aggregation network","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01836"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3444789"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2023.05.006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119580"},{"key":"ref36","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5194\/hess-24-3451-2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28230"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0285713"},{"key":"ref42","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.129499"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0752"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1029\/2020MS002203"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref49","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","volume-title":"International conference on machine learning","author":"Srivastava"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3060"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s40641-024-00193-9"},{"key":"ref53","article-title":"Predrnn: Recurrent neural networks for predictive learning using spatiotemporal 1stms","volume":"30","author":"Wang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref54","first-page":"5123","article-title":"Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref55","article-title":"Eidetic 3d lstm: A model for video prediction and beyond","volume-title":"International conference on learning representations","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00937"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117766"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref59","article-title":"ivideogpt: Interactive videogpts are scalable world models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Fashionmnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446132.pdf?arnumber=11446132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:29Z","timestamp":1777613609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00518","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}