{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:13:31Z","timestamp":1775596411390,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3637304","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:06:05Z","timestamp":1764183965000},"page":"5258-5273","source":"Crossref","is-referenced-by-count":1,"title":["SwinFVO: Self-Supervised Visual Odometry With Enhanced Global Spatiotemporal Perception"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-7541","authenticated-orcid":false,"given":"Rujun","family":"Song","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"given":"Ruoqi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8118-2330","authenticated-orcid":false,"given":"Zhuoling","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"given":"Bo","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.421"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref11","first-page":"16558","article-title":"DROID-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Teed"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.128"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3227017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3370804"},{"key":"ref18","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3384911"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.029"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_34"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636756"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3053412"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636131"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3166457"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3312950"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793479"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00136"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3533256"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00826"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00570"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144958"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00249"},{"key":"ref45","article-title":"DF-VO: What should be learnt for visual odometry?","author":"Zhan","year":"2021","journal-title":"arXiv:2103.00933"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3451584"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref48","first-page":"39033","article-title":"Deep patch visual odometry","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Teed"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3462596"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3531667"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3439529"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref54","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Shi"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref56","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913507326"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322549"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096716"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181346"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275584"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3578768"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976301"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01484-6"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301711"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11269706.pdf?arnumber=11269706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:04:19Z","timestamp":1775592259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":75,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3637304","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}