{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:28:01Z","timestamp":1780500481215,"version":"3.54.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887818","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["SVTNet: Dual Branch of Swin Transformer and Vision Transformer for Monocular Depth Estimation"],"prefix":"10.1109","author":[{"given":"Shuwen","family":"Jia","sequence":"first","affiliation":[{"name":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology,School of Optical-Electrical and Computer Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00787"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00400"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416065"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1458-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3310259"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020","journal-title":"arxiv preprint arxiv:2010.11929"},{"key":"ref13","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","volume-title":"9th International Conference on Learning Representations ICLR","author":"Zhu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref16","first-page":"1","article-title":"The cityscapes dataset[C]","volume-title":"CVPR Workshop on the Future of Datasets in Vision","volume":"2","author":"Cordts"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref19","first-page":"1908","article-title":"Unsupervised monocular depth learning in dynamic scenes","volume-title":"Conference on Robot Learning. PMLR","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802239"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887818.pdf?arnumber=10887818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:00Z","timestamp":1774416120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887818","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}