{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:46:25Z","timestamp":1792514785065,"version":"4.5.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122029"],"award-info":[{"award-number":["62122029"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061160490"],"award-info":[{"award-number":["62061160490"]}],"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":["61872417"],"award-info":[{"award-number":["61872417"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11263-023-01872-0","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T11:02:37Z","timestamp":1692702157000},"page":"56-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Coatrsnet: Fully Exploiting Convolution and Attention for Stereo Matching by Region Separation"],"prefix":"10.1007","volume":"132","author":[{"given":"Junda","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gangwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6252-1061","authenticated-orcid":false,"given":"Peng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"1872_CR1","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., & Le, Q. V. (2019). Attention augmented convolutional networks. In proceedings of the IEEE\/CVF international conference on computer vision (pp. 3286-3295).","DOI":"10.1109\/ICCV.2019.00338"},{"key":"1872_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In proceedings of the IEEE\/CVF international conference on computer vision workshops (pp. 0-0).","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"1872_CR3","doi-asserted-by":"crossref","unstructured":"Chang, J. R., & Chen, Y. S. (2018). Pyramid stereo matching network. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5410-5418).","DOI":"10.1109\/CVPR.2018.00567"},{"key":"1872_CR4","unstructured":"Cheng, X., Zhong, Y., Harandi, M., Dai, Y., Chang, X., Drummond, T., & Ge, Z. (2020). Hierarchical neural architecture search for deep stereo matching. arXiv preprint arXiv:2010.13501."},{"key":"1872_CR5","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012, June). Are we ready for autonomous driving? The kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3354-3361). IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1872_CR6","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., & Li, H. (2019). Group-wise correlation stereo network. In proceedings of the IEEE\/cvf conference on computer vision and pattern recognition (pp. 3273-3282).","DOI":"10.1109\/CVPR.2019.00339"},{"key":"1872_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1872_CR8","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., & Lin, S. (2019). Local relation networks for image recognition. In proceedings of the IEEE\/CVF international conference on computer vision (pp. 3464-3473).","DOI":"10.1109\/ICCV.2019.00356"},{"key":"1872_CR9","doi-asserted-by":"crossref","unstructured":"Johnston, A., & Carneiro, G. (2020). Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume. In proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 4756-4765).","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"1872_CR10","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., & Bry, A. (2017). End-to-end learning of geometry and context for deep stereo regression. In Proceedings of the IEEE international conference on computer vision (pp. 66-75).","DOI":"10.1109\/ICCV.2017.17"},{"key":"1872_CR11","doi-asserted-by":"crossref","unstructured":"Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., & Bry, A. (2017). End-to-end learning of geometry and context for deep stereo regression. In proceedings of the IEEE international conference on computer vision (pp. 66-75).","DOI":"10.1109\/ICCV.2017.17"},{"key":"1872_CR12","doi-asserted-by":"crossref","unstructured":"Khamis, S., Fanello, S., Rhemann, C., Kowdle, A., Valentin, J., & Izadi, S. (2018). Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction. In proceedings of the European conference on computer vision (ECCV) (pp. 573-590).","DOI":"10.1007\/978-3-030-01267-0_35"},{"key":"1872_CR13","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"1872_CR14","doi-asserted-by":"crossref","unstructured":"Klaus, A., Sormann, M., & Karner, K. (2006, August). Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In 18th international conference on pattern recognition (ICPR\u201906) (Vol. 3, pp. 15-18). IEEE.","DOI":"10.1109\/ICPR.2006.1033"},{"key":"1872_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, X., Drenkow, N., Ding, A., Creighton, F. X., Taylor, R. H., & Unberath, M. (2021). Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In proceedings of the IEEE\/CVF international conference on computer vision (pp. 6197-6206).","DOI":"10.1109\/ICCV48922.2021.00614"},{"issue":"1","key":"1872_CR16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11263-020-01359-2","volume":"129","author":"J Ma","year":"2021","unstructured":"Ma, J., Jiang, X., Fan, A., Jiang, J., & Yan, J. (2021). Image matching from handcrafted to deep features: A survey. International Journal of Computer Vision, 129(1), 23\u201379.","journal-title":"International Journal of Computer Vision"},{"key":"1872_CR17","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4040-4048).","DOI":"10.1109\/CVPR.2016.438"},{"key":"1872_CR18","doi-asserted-by":"crossref","unstructured":"Mei, X., Sun, X., Dong, W., Wang, H., & Zhang, X. (2013). Segment-tree based cost aggregation for stereo matching. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 313-320).","DOI":"10.1109\/CVPR.2013.47"},{"key":"1872_CR19","doi-asserted-by":"publisher","first-page":"427","DOI":"10.5194\/isprsannals-II-3-W5-427-2015","volume":"2","author":"M Menze","year":"2015","unstructured":"Menze, M., Heipke, C., & Geiger, A. (2015). Joint 3d estimation of vehicles and scene flow. ISPRS annals of the photogrammetry, remote sensing and spatial information sciences, 2, 427.","journal-title":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences"},{"key":"1872_CR20","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., & Chanan, G. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32, 8026\u20138037.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1872_CR21","doi-asserted-by":"publisher","first-page":"e18","DOI":"10.1017\/ATSIP.2020.16","volume":"9","author":"Z Rao","year":"2020","unstructured":"Rao, Z., He, M., Dai, Y., Zhu, Z., Li, B., & He, R. (2020). Nlca-net: a non-local context attention network for stereo matching. APSIPA Transactions on Signal and Information Processing, 9, e18.","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"1872_CR22","doi-asserted-by":"publisher","first-page":"15152","DOI":"10.1109\/ACCESS.2019.2895271","volume":"7","author":"H Sang","year":"2019","unstructured":"Sang, H., Wang, Q., & Zhao, Y. (2019). Multi-scale context attention network for stereo matching. IEEE Access, 7, 15152\u201315161.","journal-title":"IEEE Access"},{"key":"1872_CR23","doi-asserted-by":"crossref","unstructured":"Scharstein, D., Hirschm\u00fcller, H., Kitajima, Y., Krathwohl, G., Ne\u0161i\u0107, N., Wang, X., & Westling, P. (2014, September). High-resolution stereo datasets with subpixel-accurate ground truth. In German conference on pattern recognition (pp. 31-42). Springer, Cham.","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"1872_CR24","doi-asserted-by":"crossref","unstructured":"Schops, T., Schonberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., & Geiger, A. (2017). A multi-view stereo benchmark with high-resolution images and multi-camera videos. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3260-3269).","DOI":"10.1109\/CVPR.2017.272"},{"key":"1872_CR25","doi-asserted-by":"crossref","unstructured":"Seki, A., & Pollefeys, M. (2017). Sgm-nets: Semi-global matching with neural networks. In proceedings of the IEEE conference on computer vision and pattern recognition (pp. 231\u2013240).","DOI":"10.1109\/CVPR.2017.703"},{"key":"1872_CR26","doi-asserted-by":"crossref","unstructured":"Senousy, Z., Abdelsamea, M., Gaber, M. M., Abdar, M., Acharya, R. U., Khosravi, A., & Nahavandi, S. (2021). MCUa: Multi-level context and uncertainty aware dynamic deep ensemble for breast cancer histology image classification. IEEE Transactions on Biomedical Engineering.","DOI":"10.1109\/TBME.2021.3107446"},{"key":"1872_CR27","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., & Rao, Z. (2021). CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13906\u201313915).","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"1872_CR28","doi-asserted-by":"crossref","unstructured":"Song, X., Zhao, X., Hu, H., & Fang, L. (2018, December). Edgestereo: A context integrated residual pyramid network for stereo matching. In Asian conference on computer vision (pp. 20-35). Springer, Cham.","DOI":"10.1007\/978-3-030-20873-8_2"},{"issue":"4","key":"1872_CR29","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/s11263-019-01287-w","volume":"128","author":"X Song","year":"2020","unstructured":"Song, X., Zhao, X., Fang, L., Hu, H., & Yu, Y. (2020). Edgestereo: An effective multi-task learning network for stereo matching and edge detection. International Journal of Computer Vision, 128(4), 910\u2013930.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"1872_CR30","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1109\/TPAMI.2003.1206509","volume":"25","author":"J Sun","year":"2003","unstructured":"Sun, J., Zheng, N. N., & Shum, H. Y. (2003). Stereo matching using belief propagation. IEEE Transactions on pattern analysis and machine intelligence, 25(7), 787\u2013800.","journal-title":"IEEE Transactions on pattern analysis and machine intelligence"},{"key":"1872_CR31","doi-asserted-by":"crossref","unstructured":"Tankovich, V., Hane, C., Zhang, Y., Kowdle, A., Fanello, S., & Bouaziz, S. (2021). Hitnet: Hierarchical iterative tile refinement network for real-time stereo matching. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14362-14372).","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"1872_CR32","doi-asserted-by":"crossref","unstructured":"Tomasi, C., & Manduchi, R. (1998, January). Bilateral filtering for gray and color images. In sixth international conference on computer vision (IEEE Cat. No. 98CH36271) (pp. 839-846). IEEE.","DOI":"10.1109\/ICCV.1998.710815"},{"key":"1872_CR33","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., & Shlens, J. (2021). Scaling local self-attention for parameter efficient visual backbones. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12894-12904).","DOI":"10.1109\/CVPR46437.2021.01270"},{"issue":"6","key":"1872_CR34","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/s11263-019-01157-5","volume":"127","author":"S Wu","year":"2019","unstructured":"Wu, S., Kan, M., Shan, S., & Chen, X. (2019). Hierarchical attention for part-aware face detection. International Journal of Computer Vision, 127(6), 560\u2013578.","journal-title":"International Journal of Computer Vision"},{"key":"1872_CR35","doi-asserted-by":"crossref","unstructured":"Xu, H., & Zhang, J. (2020). Aanet: Adaptive aggregation network for efficient stereo matching. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1959-1968).","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"1872_CR36","doi-asserted-by":"crossref","unstructured":"Yang, Q. (2012, June). A non-local cost aggregation method for stereo matching. In 2012 IEEE conference on computer vision and pattern recognition (pp. 1402-1409). IEEE.","DOI":"10.1109\/CVPR.2012.6247827"},{"key":"1872_CR37","doi-asserted-by":"crossref","unstructured":"Yang, G., Zhao, H., Shi, J., Deng, Z., & Jia, J. (2018). Segstereo: Exploiting semantic information for disparity estimation. In proceedings of the European conference on computer vision (ECCV) (pp. 636-651).","DOI":"10.1007\/978-3-030-01234-2_39"},{"key":"1872_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., & Torr, P. H. (2019). Ga-net: Guided aggregation net for end-to-end stereo matching. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 185-194).","DOI":"10.1109\/CVPR.2019.00027"},{"issue":"2","key":"1872_CR39","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/LRA.2019.2894913","volume":"4","author":"J Zhang","year":"2019","unstructured":"Zhang, J., Skinner, K. A., Vasudevan, R., & Johnson-Roberson, M. (2019). Dispsegnet: Leveraging semantics for end-to-end learning of disparity estimation from stereo imagery. IEEE Robotics and Automation Letters, 4(2), 1162\u20131169.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1872_CR40","doi-asserted-by":"publisher","first-page":"51681","DOI":"10.1109\/ACCESS.2019.2911618","volume":"7","author":"G Zhang","year":"2019","unstructured":"Zhang, G., Zhu, D., Shi, W., Ye, X., Li, J., & Zhang, X. (2019). Multi-dimensional residual dense attention network for stereo matching. IEEE Access, 7, 51681\u201351690.","journal-title":"IEEE Access"},{"key":"1872_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Hu, Y., Wang, H., Cao, X., & Zhang, B. (2021). Long-range Attention Network for Multi-View Stereo. In proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 3782-3791).","DOI":"10.1109\/WACV48630.2021.00383"},{"key":"1872_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, H., Ummenhofer, B., & Brox, T. (2020). DeepTAM: Deep tracking and mapping with convolutional neural networks. International Journal of Computer Vision,128(3), 756\u2013769.","DOI":"10.1007\/s11263-019-01221-0"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01872-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01872-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01872-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T15:14:27Z","timestamp":1729955667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01872-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,22]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1872"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01872-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,22]]},"assertion":[{"value":"15 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}