{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:03:27Z","timestamp":1782576207291,"version":"3.54.5"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["62373009"],"award-info":[{"award-number":["62373009"]}],"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":["62073004"],"award-info":[{"award-number":["62073004"]}],"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":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3578768","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T13:45:11Z","timestamp":1749735911000},"page":"12023-12037","source":"Crossref","is-referenced-by-count":5,"title":["Dual Attention Guidance Network for Self-Supervised Monocular Depth Estimation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6592-9115","authenticated-orcid":false,"given":"Ying","family":"Zhu","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4666-8551","authenticated-orcid":false,"given":"Guoliang","family":"Hua","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2077-1246","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5236-7010","authenticated-orcid":false,"given":"Yidi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibo","family":"Huang","sequence":"additional","affiliation":[{"name":"Hangzhou Ease Future Intelligent Technology Co., Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793610"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798174"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DSC50466.2020.00028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1364\/AO.57.004960"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00598"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2907904"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2943019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746689"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989537"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560885"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128505"},{"key":"ref23","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"2","author":"Eigen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2839602"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2772892"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.064"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00343"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506550"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00751"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02052"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891946"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27927"},{"key":"ref41","article-title":"Dynamo-depth: Fixing unsupervised depth estimation for dynamical scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01249"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00576"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_20"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref49","article-title":"Semantically-guided representation learning for self-supervised monocular depth","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Guizilini"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00471"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25401"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109297"},{"key":"ref54","article-title":"SAFENet: Self-supervised monocular depth estimation with semantic-aware feature extraction","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Choi"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20035"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169842"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/PRAI62207.2024.10827781"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979190"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120670"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0071-y"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01484-6"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104862"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803247"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00697"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3167307"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3215587"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275584"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2930258"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_6"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref88","first-page":"767","article-title":"T2Net: Synthetic-to-realistic translation for solving single-image depth estimation tasks","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Zheng"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_9"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.073"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096716"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301711"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01488"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref99","first-page":"22690","article-title":"Vision transformer with super token sampling","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322549"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref102","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11031167.pdf?arnumber=11031167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:10:56Z","timestamp":1765260656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11031167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":102,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3578768","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}