{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T18:10:06Z","timestamp":1756491006983,"version":"3.44.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP)-Innovative Human Resource Development for Local Intellectualization Program"},{"name":"Korean Government [Ministry of Science and Information and Communications Technology (MSIT)]","award":["IITP-2025-RS-2022-00156287"],"award-info":[{"award-number":["IITP-2025-RS-2022-00156287"]}]},{"name":"IITP through the Artificial Intelligence Convergence Innovation Human Resources Development"},{"name":"Korean Government (MSIT)","award":["IITP-2023-RS-2023-00256629"],"award-info":[{"award-number":["IITP-2023-RS-2023-00256629"]}]},{"name":"MSIT, South Korea, through the Information Technology Research Center (ITRC) Support Program"},{"name":"IITP","award":["IITP-2024-RS-2024-00437718"],"award-info":[{"award-number":["IITP-2024-RS-2024-00437718"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3573639","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T14:04:18Z","timestamp":1748268258000},"page":"148961-148971","source":"Crossref","is-referenced-by-count":0,"title":["DATC-STP: Towards Accurate yet Efficient Spatiotemporal Prediction With Transformer-Style CNN"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8271-6792","authenticated-orcid":false,"given":"Hyeonseok","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9985-3051","authenticated-orcid":false,"given":"Kyungbaek","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-79148-7"},{"key":"ref3","first-page":"25390","article-title":"Earthformer: Exploring space-time transformers for Earth system forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3162882"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921978"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.390"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3021409"},{"key":"ref10","first-page":"1","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Finn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01239"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118541"},{"key":"ref13","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref14","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956707"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25289"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104612"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref20","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Luo"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref23","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","first-page":"879","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wang"},{"key":"ref26","first-page":"5123","article-title":"PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref27","first-page":"1","article-title":"Training very deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref28","first-page":"1","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"ref32","first-page":"1","article-title":"Efficient and information-preserving future frame prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref35","first-page":"26950","article-title":"MAU: A motion-aware unit for video prediction and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00575"},{"key":"ref38","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref40","article-title":"SimVPv2: Towards simple yet powerful spatiotemporal predictive learning","author":"Tan","year":"2022","journal-title":"arXiv:2211.12509"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00394"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28230"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128663"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00688"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref51","first-page":"69819","article-title":"OpenSTL: A comprehensive benchmark of spatio-temporal predictive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11015442.pdf?arnumber=11015442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:43:43Z","timestamp":1756489423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3573639","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}