{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T06:35:47Z","timestamp":1773470147048,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Key R & D Program","award":["2021YFE0105000"],"award-info":[{"award-number":["2021YFE0105000"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["52074213"],"award-info":[{"award-number":["52074213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Xi \u2019an science and technology plan project university institute science and technology personnel service enterprise project","award":["22GXFW0110"],"award-info":[{"award-number":["22GXFW0110"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00530-024-01605-4","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T21:59:51Z","timestamp":1733867991000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["PAR-mono: monocular video depth estimation network based on channel separation and dynamic attention"],"prefix":"10.1007","volume":"31","author":[{"given":"Hongyan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoming","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoqing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"1605_CR1","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/j.patcog.2018.05.016","volume":"83","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Xu, C., Yang, J., Tai, Y., Chen, L.: Deep hierarchical guidance and regularization learning for end-to-end depth estimation. Pattern Recogn. 83, 430\u2013442 (2018). https:\/\/doi.org\/10.1016\/j.patcog.2018.05.016","journal-title":"Pattern Recogn."},{"key":"1605_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100881","volume":"23","author":"F Yu","year":"2023","unstructured":"Yu, F., Zhang, G., Zhao, F., Wang, X., Liu, H., Lin, P., Chen, Y.: Improved yolo-v5 model for boosting face mask recognition accuracy on heterogeneous iot computing platforms. Internet Things. 23, 100881 (2023). https:\/\/doi.org\/10.1016\/j.iot.2023.100881","journal-title":"Internet Things."},{"key":"1605_CR3","doi-asserted-by":"publisher","DOI":"10.3390\/s23249906","author":"S Li","year":"2023","unstructured":"Li, S., Huang, H., Meng, X., Wang, M., Li, Y., Xie, L.: A glove-wearing detection algorithm based on improved yolov8. Sensors (2023). https:\/\/doi.org\/10.3390\/s23249906","journal-title":"Sensors"},{"key":"1605_CR4","doi-asserted-by":"publisher","DOI":"10.3390\/app12199902","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Ma, P., Jiang, T., Zhao, X., Tan, W., Zhang, J., Zou, S., Huang, X., Grzegorzek, M., Li, C.: Sem-rcnn: a squeeze-and-excitation-based mask region convolutional neural network for multi-class environmental microorganism detection. Appl. Sci. (2022). https:\/\/doi.org\/10.3390\/app12199902","journal-title":"Appl. Sci."},{"key":"1605_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108881","volume":"131","author":"W Wu","year":"2022","unstructured":"Wu, W., Chu, T., Liu, Q.: Complementarity-aware cross-modal feature fusion network for rgb-t semantic segmentation. Pattern Recogn. 131, 108881 (2022). https:\/\/doi.org\/10.1016\/j.patcog.2022.108881","journal-title":"Pattern Recogn."},{"key":"1605_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110196","volume":"149","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Quan, Z., Li, Q., Zhu, D., Yang, W.: Sed: searching enhanced decoder with switchable skip connection for semantic segmentation. Pattern Recogn. 149, 110196 (2024). https:\/\/doi.org\/10.1016\/j.patcog.2023.110196","journal-title":"Pattern Recogn."},{"key":"1605_CR7","doi-asserted-by":"publisher","DOI":"10.3390\/jmse9060671","author":"H Fu","year":"2021","unstructured":"Fu, H., Meng, D., Li, W., Wang, Y.: Bridge crack semantic segmentation based on improved deeplabv3+. J. Mar. Sci. Eng. (2021). https:\/\/doi.org\/10.3390\/jmse9060671","journal-title":"J. Mar. Sci. Eng."},{"key":"1605_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109896","volume":"145","author":"L Zou","year":"2024","unstructured":"Zou, L., Huang, Z., Gu, N., Wang, G.: Learning geometric consistency and discrepancy for category-level 6d object pose estimation from point clouds. Pattern Recogn. 145, 109896 (2024). https:\/\/doi.org\/10.1016\/j.patcog.2023.109896","journal-title":"Pattern Recogn."},{"key":"1605_CR9","doi-asserted-by":"publisher","unstructured":"Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Unsupervised monocular depth and ego-motion learning with structure and semantics. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 381\u2013388 (2019). https:\/\/doi.org\/10.1109\/CVPRW.2019.00051","DOI":"10.1109\/CVPRW.2019.00051"},{"key":"1605_CR10","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Fan, X., Shi, P., Xin, Y.: R-msfm: recurrent multi-scale feature modulation for monocular depth estimating. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12757\u201312766 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01254","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"1605_CR11","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-030-58565-5_35","volume-title":"Computer Vision\u2013ECCV 2020","author":"M Klingner","year":"2020","unstructured":"Klingner, M., Term\u00f3hlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision\u2013ECCV 2020, pp. 582\u2013600. Springer, Cham (2020)"},{"key":"1605_CR12","doi-asserted-by":"publisher","unstructured":"Lyu, X., Liu, L., Wang, M., Kong, X., Liu, L., Liu, Y., Chen, X., Yuan, Y.: Hr-depth: high resolution self-supervised monocular depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2294\u20132301 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i3.16329","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"1605_CR13","doi-asserted-by":"publisher","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612\u20136619 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.700","DOI":"10.1109\/CVPR.2017.700"},{"key":"1605_CR14","unstructured":"Guizilini, V.C., Hou, R., Li, J., Ambrus, R., Gaidon., A.: Semantically-guided representation learning for self-supervised monocular depth. arXiv abs\/2002.12319 (2020)"},{"key":"1605_CR15","doi-asserted-by":"publisher","unstructured":"Klingner, M., Term\u00f3hlen, J.-A., Mikolajczyk, J., Fingscheidt, T.: Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Computer Vision\u2014ECCV 2020, pp. 582\u2013600. Springer, Berlin, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_35","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"1605_CR16","doi-asserted-by":"publisher","unstructured":"Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M.J.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12232\u201312241 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01252","DOI":"10.1109\/CVPR.2019.01252"},{"key":"1605_CR17","doi-asserted-by":"publisher","first-page":"2548","DOI":"10.1007\/s11263-021-01484-6","volume":"129","author":"J Bian","year":"2021","unstructured":"Bian, J., Zhan, H., Wang, N., Li, Z., Zhang, L., Shen, C., Cheng, M.-M.: Unsupervised scale-consistent depth learning from video. Int. J. Comput. Vis. 129, 2548\u20132564 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1605_CR18","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1109\/TPAMI.2023.3322549","volume":"46","author":"L Sun","year":"2022","unstructured":"Sun, L., Bian, J., Zhan, H., Yin, W., Reid, I.D., Shen, C.: Sc-depthv3: Robust self-supervised monocular depth estimation for dynamic scenes. IEEE Trans. Pattern Anal. Mach. Intell. 46, 497\u2013508 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1605_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, N., Nex, F., Vosselman, G., Kerle, N.: Lite-mono: a lightweight cnn and transformer architecture for self-supervised monocular depth estimation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18537\u201318546 (2022)","DOI":"10.1109\/CVPR52729.2023.01778"},{"key":"1605_CR20","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2012)","journal-title":"Commun. ACM"},{"issue":"10","key":"1605_CR21","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2016","unstructured":"Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024\u20132039 (2016). https:\/\/doi.org\/10.1109\/TPAMI.2015.2505283","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1605_CR22","volume-title":"Advances in Neural Information Processing Systems","author":"D Eigen","year":"2014","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates Inc., USA (2014)"},{"key":"1605_CR23","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"1605_CR24","doi-asserted-by":"publisher","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., Navab, N.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248 (2016). https:\/\/doi.org\/10.1109\/3DV.2016.32","DOI":"10.1109\/3DV.2016.32"},{"issue":"11","key":"1605_CR25","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1109\/TCSVT.2021.3049869","volume":"31","author":"M Song","year":"2021","unstructured":"Song, M., Lim, S., Kim, W.: Monocular depth estimation using Laplacian pyramid-based depth residuals. IEEE Trans. Circuits Syst. Video Technol. 31(11), 4381\u20134393 (2021). https:\/\/doi.org\/10.1109\/TCSVT.2021.3049869","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1605_CR26","doi-asserted-by":"crossref","unstructured":"Xia, Z., Sullivan, P., Chakrabarti, A.: Generating and exploiting probabilistic monocular depth estimates. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 62\u201371 (2019)","DOI":"10.1109\/CVPR42600.2020.00014"},{"key":"1605_CR27","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer Vision\u2013ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg, R., Vijaya Kumar, B.G., Carneiro, G., Reid, I.: Unsupervised cnn for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision\u2013ECCV 2016, pp. 740\u2013756. Springer, Cham (2016)"},{"key":"1605_CR28","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow., G.J.: Unsupervised monocular depth estimation with left-right consistency. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602\u20136611 (2016)","DOI":"10.1109\/CVPR.2017.699"},{"key":"1605_CR29","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Love","year":"2004","unstructured":"Love, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"issue":"5","key":"1605_CR30","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans. Rob. 33(5), 1255\u20131262 (2017). https:\/\/doi.org\/10.1109\/TRO.2017.2705103","journal-title":"IEEE Trans. Rob."},{"key":"1605_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cad.2017.12.003","volume":"98","author":"D Kim","year":"2018","unstructured":"Kim, D., Park, J., Ko, K.H.: Development of an ar based method for augmentation of 3d cad data onto a real ship block image. Computer-Aided Des. 98, 1\u201311 (2018). https:\/\/doi.org\/10.1016\/j.cad.2017.12.003","journal-title":"Computer-Aided Des."},{"key":"1605_CR32","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M.K., Cipolla, R.: Posenet: a convolutional network for real-time 6-dof camera relocalization. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"1605_CR33","unstructured":"Zhang, R., Luo, Z., Dhanjal, S.S., Schmotzer, C., Hasija, S.: Posenet + + : A CNN Framework for Online Pose Regression and Robot Re-localization (2018)"},{"key":"1605_CR34","doi-asserted-by":"publisher","unstructured":"Huang, Z., Xu, Y., Shi, J., Zhou, X., Bao, H., Zhang, G.: Prior guided dropout for robust visual localization in dynamic environments. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2791\u20132800 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00288","DOI":"10.1109\/ICCV.2019.00288"},{"key":"1605_CR35","doi-asserted-by":"crossref","unstructured":"Tian, M., Nie, Q., Shen, H.: 3d scene geometry-aware constraint for camera localization with deep learning. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4211\u20134217 (2020)","DOI":"10.1109\/ICRA40945.2020.9196940"},{"key":"1605_CR36","doi-asserted-by":"publisher","unstructured":"Xian, K., Zhang, J., Wang, O., Mai, L., Lin, Z., Cao, Z.: Structure-guided ranking loss for single image depth prediction. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 608\u2013617 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00069","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"1605_CR37","doi-asserted-by":"publisher","unstructured":"Godard, C., Aodha, O.M., Firman, M., Brostow, G.: Digging into self-supervised monocular depth estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3827\u20133837 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00393","DOI":"10.1109\/ICCV.2019.00393"},{"issue":"12","key":"1605_CR38","doi-asserted-by":"publisher","first-page":"9802","DOI":"10.1109\/TPAMI.2021.3136220","volume":"44","author":"J-W Bian","year":"2022","unstructured":"Bian, J.-W., Zhan, H., Wang, N., Chin, T.-J., Shen, C., Reid, I.: Auto-rectify network for unsupervised indoor depth estimation. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9802\u20139813 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3136220","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01605-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01605-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01605-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T11:06:08Z","timestamp":1740740768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01605-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1605"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01605-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"11 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"6"}}