{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:47:45Z","timestamp":1766062065735,"version":"3.48.0"},"reference-count":41,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","award":["RS-2024-00397359"],"award-info":[{"award-number":["RS-2024-00397359"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003708","name":"Korea Institute of Science and Technology Information","doi-asserted-by":"publisher","award":["K25L1M2C2-01"],"award-info":[{"award-number":["K25L1M2C2-01"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3638813","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:00Z","timestamp":1764355440000},"page":"206919-206931","source":"Crossref","is-referenced-by-count":0,"title":["MoBA-VP: Segmentation-Guided Motion-Biased Attention for Long-Term Video Prediction"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-5042","authenticated-orcid":false,"given":"Yuseon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Applied AI, University of Science and Technology (UST), Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5164-7099","authenticated-orcid":false,"given":"Kyongseok","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Applied AI, University of Science and Technology (UST), Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref3","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref4","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Shi"},{"key":"ref5","first-page":"879","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"30","author":"Wang"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref8","first-page":"13714","article-title":"Convolutional tensor-train LSTM for spatio-temporal learning","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Su"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref11","article-title":"MaskViT: Masked visual pre-training for video prediction","author":"Gupta","year":"2022","journal-title":"arXiv:2206.11894"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104612"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25289"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00525"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref17","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref18","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Sutskever"},{"key":"ref19","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bahdanau"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref22","first-page":"14014","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"32","author":"Michel"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00408"},{"key":"ref25","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Lu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02147"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3589132.3625570"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01820"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref33","first-page":"344","article-title":"Self-supervised visual planning with temporal skip connections","volume-title":"Proc. Conf. Robot Learn.","author":"Ebert"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146721"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01239"},{"key":"ref40","article-title":"CrevNet: Conditionally reversible video prediction","author":"Yu","year":"2019","journal-title":"arXiv:1910.11577"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11271509.pdf?arnumber=11271509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:43:38Z","timestamp":1766061818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3638813","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}