{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:52:42Z","timestamp":1780764762813,"version":"3.54.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0114903"],"award-info":[{"award-number":["2022ZD0114903"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3312664","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:45:21Z","timestamp":1694108721000},"page":"2439-2452","source":"Crossref","is-referenced-by-count":9,"title":["SPTR: Structure-Preserving Transformer for Unsupervised Indoor Depth Completion"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9635-0715","authenticated-orcid":false,"given":"Linqing","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7188-3734","authenticated-orcid":false,"given":"Wenzhao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1190-6663","authenticated-orcid":false,"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep depth completion from extremely sparse data: A survey","author":"Hu","year":"2022","journal-title":"arXiv:2205.05335"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793637"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969938"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058072"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01255"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560831"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00225"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3155626"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3284479"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.029"},{"key":"ref28","first-page":"35","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. NIPS","author":"Bian"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16311"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3079821"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120042"},{"key":"ref38","article-title":"RigNet: Repetitive image guided network for depth completion","author":"Yan","year":"2021","journal-title":"arXiv:2107.13802"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3117254"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20055"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6635"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00343"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00290"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01273"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00261"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062602"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3247103"},{"key":"ref51","article-title":"Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition","author":"Xu","year":"2023","journal-title":"arXiv:2302.02327"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00305"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3132047"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636494"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00606"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00415"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3275584"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00768"},{"key":"ref62","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Qi"},{"key":"ref63","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. NIPS","volume":"30","author":"Qi"},{"key":"ref64","first-page":"1","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. NIPS","volume":"32","author":"Ramachandran"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref66","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_11"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref71","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3214316"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2896963"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917294"},{"key":"ref78","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":"ref79","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021","journal-title":"arXiv:2102.10882"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10243117.pdf?arnumber=10243117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:54:43Z","timestamp":1712692483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":80,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3312664","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}