{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:44:14Z","timestamp":1774716254663,"version":"3.50.1"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["12174341"],"award-info":[{"award-number":["12174341"]}],"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":["62473139"],"award-info":[{"award-number":["62473139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hangzhou SurImage Technology Company Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tiv.2024.3418497","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T16:11:27Z","timestamp":1719245487000},"page":"775-793","source":"Crossref","is-referenced-by-count":2,"title":["Beyond the Field-of-View: Enhancing Scene Visibility and Perception With Clip-Recurrent Transformer"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0184-2245","authenticated-orcid":false,"given":"Hao","family":"Shi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Extreme Photonics and Instrumentation and the National Engineering Research Center of Optical Instrumentation, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7484-3030","authenticated-orcid":false,"given":"Qi","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Extreme Photonics and Instrumentation and the National Engineering Research Center of Optical Instrumentation, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1090-667X","authenticated-orcid":false,"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7708-7819","authenticated-orcid":false,"given":"Xiaoting","family":"Yin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Extreme Photonics and Instrumentation and the National Engineering Research Center of Optical Instrumentation, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3718-2605","authenticated-orcid":false,"given":"Ze","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Extreme Photonics and Instrumentation and the National Engineering Research Center of Optical Instrumentation, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8272-3119","authenticated-orcid":false,"given":"Kaiwei","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Extreme Photonics and Instrumentation and the National Engineering Research Center of Optical Instrumentation, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086409"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3235057"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.04.035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2018.02.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","first-page":"36081","article-title":"Rethinking alignment in video super-resolution transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shi","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3216675"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1364\/AO.395598"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1364\/AO.46.007850"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-DAT.2014.6834863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1364\/COSI.2019.JW4B.4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12596-015-0260-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1117\/12.2285587"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00405"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3123070"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3241212"},{"key":"ref29","first-page":"10520","article-title":"Boundless: Generative adversarial networks for image extension","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Teterwak","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3342570"},{"key":"ref32","article-title":"FisheyeEX: Polar outpainting for extending the FoV of fisheye lens","author":"Liao","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00684"},{"key":"ref34","article-title":"Painting outside the box: Image outpainting with GANs","author":"Sabini","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.815261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00217"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00408"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/140954933"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_23"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982398"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_22"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_5"},{"key":"ref55","article-title":"Flow-guided diffusion for video inpainting","author":"Gu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015232"},{"key":"ref61","article-title":"Deficiency-aware masked transformer for video inpainting","author":"Yu","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref63","article-title":"Adversarial video generation on complex datasets","author":"Clark","year":"2019"},{"key":"ref64","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref65","article-title":"FitVid: Overfitting in pixel-level video prediction","author":"Babaeizadeh","year":"2021"},{"key":"ref66","article-title":"Sora: A. review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref68","first-page":"1","article-title":"MaskViT: Masked visual pre-training for video prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gupta","year":"2023"},{"key":"ref69","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Austin","year":"2021"},{"key":"ref70","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref71","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref73","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord","year":"2017"},{"key":"ref74","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Razavi","year":"2019"},{"key":"ref75","article-title":"FDAN: Flow-guided deformable alignment network for video super-resolution","author":"Lin","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372454"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00536"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00791"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref81","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie","year":"2021"},{"key":"ref82","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang","year":"2021"},{"key":"ref83","first-page":"1","article-title":"How do vision transformers work?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref85","article-title":"Axial attention in multidimensional transformers","author":"Ho","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref89","first-page":"1152","article-title":"Video-to-video synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wang","year":"2018"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref91","first-page":"1","article-title":"Learnable gated temporal shift module for deep video inpainting","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chang","year":"2019"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref96","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11104066\/10570336.pdf?arnumber=10570336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T04:54:37Z","timestamp":1753937677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":99,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3418497","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}