{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:02:00Z","timestamp":1790794920509,"version":"4.1.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11760-026-05692-w","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T08:30:17Z","timestamp":1789201817000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-supervised monocular depth estimation with hybrid CNN-transformer architecture using skip attention mechanism"],"prefix":"10.1007","volume":"20","author":[{"given":"Afrasiab","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tahir","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md","family":"Asaduzzaman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad S.","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayesha","family":"Zeb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anjum Naeem","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anas bin","family":"Aqeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faisal","family":"Shafait","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"5692_CR1","unstructured":"Eigen, D.: Depth map prediction from a single image using a multi-scale deep network. NeurIPS, (2014)"},{"key":"5692_CR2","doi-asserted-by":"crossref","unstructured":"Casser, V.: Unsupervised monocular depth and ego-motion learning with structure and semantics. In: CVPR Workshops, (2019)","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"5692_CR3","doi-asserted-by":"crossref","unstructured":"Godard, C.: Digging into self-supervised monocular depth estimation. CVPR, (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"5692_CR4","doi-asserted-by":"crossref","unstructured":"Pillai, S.: SuperDepth: self-supervised, super-resolved monocular depth estimation. ICRA, pp. 9250\u20139256. (2019)","DOI":"10.1109\/ICRA.2019.8793621"},{"key":"5692_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, N.: Lite-Mono: A Lightweight CNN and transformer architecture for self-supervised monocular depth estimation. CVPR, (2023)","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"5692_CR6","doi-asserted-by":"crossref","unstructured":"Zhou Z et\u00a0al. R-MSFNet: recurrent multi-scale feature modulation for monocular depth estimation. ICCV, 2021","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"5692_CR7","unstructured":"Dosovitskiy A et\u00a0al. An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv:2010.11929, 2020"},{"key":"5692_CR8","unstructured":"Zhao, W.: MonoFormer: towards generalization of self-supervised monocular depth estimation with transformers, (2022). arXiv:2205.08508"},{"issue":"12","key":"5692_CR9","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J., Zhou, W., Liu, N., Sun, H., Li, D., Zhang, Y.: An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23(12), 24330\u201324342 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"5692_CR10","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. 27(4), 4569\u20134586 (2026)","DOI":"10.1109\/TITS.2025.3642410"},{"key":"5692_CR11","unstructured":"Zhong, S.: Mix-pooling strategy for attention mechanism, (2022). arXiv:2208.10322"},{"key":"5692_CR12","doi-asserted-by":"crossref","unstructured":"Laina I et\u00a0al. Deeper depth prediction with fully convolutional residual networks. 3DV, 2016","DOI":"10.1109\/3DV.2016.32"},{"key":"5692_CR13","doi-asserted-by":"crossref","unstructured":"Rahman, M.A.: DwinFormer: Dual Window Transformers for End-to-End Monocular Depth Estimation. IEEE Sensors J, (2023)","DOI":"10.1109\/JSEN.2023.3299782"},{"key":"5692_CR14","doi-asserted-by":"crossref","unstructured":"Ronneberger O et\u00a0al. U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI, 2015","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5692_CR15","doi-asserted-by":"crossref","unstructured":"Drozdzal, M.: The importance of skip connections in biomedical image segmentation. DLMIA, (2016)","DOI":"10.1007\/978-3-319-46976-8_19"},{"key":"5692_CR16","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","volume":"121","author":"N Ibtehaz","year":"2020","unstructured":"Ibtehaz, N., et al.: MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 121, 74\u201387 (2020)","journal-title":"Neural Netw."},{"key":"5692_CR17","unstructured":"Oktay, O.: Attention U-Net: Learning Where to Look for the Pancreas, (2018). arXiv:1804.03999"},{"key":"5692_CR18","doi-asserted-by":"crossref","first-page":"116064","DOI":"10.1109\/ACCESS.2020.2997997","volume":"8","author":"Y Song","year":"2020","unstructured":"Song, Y., et al.: SANet: feature Re-use and attention-based semantic segmentation network for point cloud. IEEE Access 8, 116064\u2013116074 (2020)","journal-title":"IEEE Access"},{"key":"5692_CR19","unstructured":"Howard, A.G.: MobileNets: efficient convolutional neural networks for mobile vision applications, (2017). arXiv:1704.04861"},{"key":"5692_CR20","unstructured":"Zhang, X.: ShuffleNet: an extremely efficient cnn for mobile devices. CVPR, (2018)"},{"key":"5692_CR21","doi-asserted-by":"crossref","unstructured":"Rudolph, M.: Lightweight monocular depth estimation through guided decoding. ICRA, (2022)","DOI":"10.1109\/ICRA46639.2022.9812220"},{"key":"5692_CR22","doi-asserted-by":"crossref","unstructured":"Zhou T et\u00a0al. Unsupervised learning of depth and ego-motion from video. CVPR, 2017","DOI":"10.1109\/CVPR.2017.700"},{"key":"5692_CR23","doi-asserted-by":"crossref","unstructured":"Wang, C.: Learning depth from monocular videos using direct methods. CVPR, (2018)","DOI":"10.1109\/CVPR.2018.00216"},{"key":"5692_CR24","doi-asserted-by":"crossref","unstructured":"Lyu, X.: HR-depth: high-resolution self-supervised monocular depth estimation. AAAI, (2021)","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"5692_CR25","doi-asserted-by":"crossref","unstructured":"Qi, Z.: UNetPro: combining attention with skip connection in UNet for efficient IR drop prediction. ISEDA, (2024)","DOI":"10.1109\/ISEDA62518.2024.10617653"},{"key":"5692_CR26","doi-asserted-by":"crossref","unstructured":"Geiger, A.: Vision meets robotics: the KITTI dataset. IJRR, (2013)","DOI":"10.1177\/0278364913491297"},{"key":"5692_CR27","doi-asserted-by":"crossref","unstructured":"Saxena, A.: Make3D: learning 3D scene structure from a single still image. IEEE TPAMI, (2008)","DOI":"10.1109\/TPAMI.2008.132"},{"key":"5692_CR28","doi-asserted-by":"crossref","unstructured":"Silberman, N.: Indoor segmentation and support inference from RGBD images. ECCV, (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"5692_CR29","unstructured":"Loshchilov, I.: Decoupled weight decay regularization. ICLR, (2018)"},{"key":"5692_CR30","doi-asserted-by":"crossref","unstructured":"Deng, J.: ImageNet: a large-scale hierarchical image database. CVPR, (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5692_CR31","doi-asserted-by":"crossref","unstructured":"Yan J et\u00a0al. Channel-wise attention-based network for self-supervised monocular depth estimation. 3DV, (2021)","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"5692_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104769","volume":"156","author":"B Zhao","year":"2025","unstructured":"Zhao, B., et al.: RTIA-Mono: real-time lightweight self-supervised monocular depth estimation with global-local information aggregation. Digital Signal Process. 156, 104769 (2025)","journal-title":"Digital Signal Process."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05692-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05692-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05692-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:51:56Z","timestamp":1790794316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05692-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":32,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["5692"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05692-w","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"31 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"638"}}