{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T15:46:32Z","timestamp":1774799192471,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T00:00:00Z","timestamp":1660348800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T00:00:00Z","timestamp":1660348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020YJS029"],"award-info":[{"award-number":["2020YJS029"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51827813,61472029"],"award-info":[{"award-number":["51827813,61472029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003213","name":"Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KJZD20191000402"],"award-info":[{"award-number":["KJZD20191000402"]}],"id":[{"id":"10.13039\/501100003213","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10489-022-04003-3","type":"journal-article","created":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T04:02:36Z","timestamp":1660363356000},"page":"9978-9991","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["SA-Net: Scene-Aware Network for Cross-domain Stereo Matching"],"prefix":"10.1007","volume":"53","author":[{"given":"Ai-Xin","family":"Chong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4226-4368","authenticated-orcid":false,"given":"Hui","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Yan-Ting","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qian-Qian","family":"Du","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,13]]},"reference":[{"key":"4003_CR1","doi-asserted-by":"crossref","unstructured":"Shaked A, Wolf L (2017) Improved stereo matching with constant highway networks and reflective confidence learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4641\u20134650","DOI":"10.1109\/CVPR.2017.730"},{"issue":"1","key":"4003_CR2","first-page":"2287","volume":"17","author":"J \u017ebontar","year":"2016","unstructured":"\u017ebontar J, Lecun Y (2016) Stereo matching by training a convolutional neural network to compare image patches. J Mach Learn Res 17(1):2287\u20132318","journal-title":"J Mach Learn Res"},{"key":"4003_CR3","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: 2016 The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4040\u20134048","DOI":"10.1109\/CVPR.2016.438"},{"key":"4003_CR4","doi-asserted-by":"crossref","unstructured":"Chang J, Chen Y (2018) Pyramid stereo matching network. In: 2018 The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5410\u20135418","DOI":"10.1109\/CVPR.2018.00567"},{"key":"4003_CR5","doi-asserted-by":"crossref","unstructured":"Guo FX, Yang K, Yang W, Wang X, Li H (2019) Group-wise correlation stereo network. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3273\u20133282","DOI":"10.1109\/CVPR.2019.00339"},{"key":"4003_CR6","doi-asserted-by":"crossref","unstructured":"Xu H, Zhang J (2020) AANet: adaptive aggregation network for efficient stereo matching. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1959\u20131968","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"4003_CR7","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\u201375","DOI":"10.1109\/ICCV.2017.17"},{"key":"4003_CR8","doi-asserted-by":"crossref","unstructured":"Zhang F, Prisacariu V, Yang R, Torr P (2019) GA-Net: guided aggregation net for end-to-end stereo matching. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 185\u2013194","DOI":"10.1109\/CVPR.2019.00027"},{"key":"4003_CR9","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. Springer, pp 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"issue":"8","key":"4003_CR10","doi-asserted-by":"publisher","first-page":"5219","DOI":"10.1007\/s10489-020-02107-2","volume":"51","author":"Y Chong","year":"2021","unstructured":"Chong Y, Peng C, Zhang C, Wang Y, Feng W, Pan S (2021) Learning domain invariant and specific representation for cross-domain person re-identification. Applied Intelligence 51(8):5219\u20135232","journal-title":"Applied Intelligence"},{"issue":"3","key":"4003_CR11","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.1007\/s10489-021-02551-8","volume":"52","author":"Z Pang","year":"2021","unstructured":"Pang Z, Guo J, Sun W, Xiao Y, Yu M (2021) Cross-domain person re-identification by hybrid supervised and unsupervised learning. Applied Intelligence 52(3):2987\u20133001","journal-title":"Applied Intelligence"},{"issue":"8","key":"4003_CR12","doi-asserted-by":"publisher","first-page":"5701","DOI":"10.1007\/s10489-020-02145-w","volume":"51","author":"Y Guo","year":"2021","unstructured":"Guo Y, Peng Y, Zhang B (2021) CAFR-CNN: coarse-to-fine adaptive faster R-CNN for cross-domain joint optic disc and cup segmentation. Applied Intelligence 51(8):5701\u20135725","journal-title":"Applied Intelligence"},{"key":"4003_CR13","doi-asserted-by":"crossref","unstructured":"Shi H, Huang C, Zhang X, Zhao J, Li S (2022) Wasserstein distance based multi-scale adversarial domain adaptation method for remaining useful life prediction. Appl Intell, 1\u201316","DOI":"10.1007\/s10489-022-03670-6"},{"key":"4003_CR14","doi-asserted-by":"crossref","unstructured":"Guo X, Li H, Yi S, Ren J, Wang X (2018) Learning monocular depth by distilling cross-domain stereo networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 484\u2013500","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"4003_CR15","doi-asserted-by":"crossref","unstructured":"Pang J, Sun W, Yang C, Ren J, Xiao R, Zeng J, Lin L (2018) Zoom and learn: generalizing deep stereo matching to novel domains. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 2070\u20132079","DOI":"10.1109\/CVPR.2018.00221"},{"key":"4003_CR16","doi-asserted-by":"crossref","unstructured":"Tonioni A, Rahnama O, Joy T, Stefano L, Ajanthan T, Torr P (2019) Learning to adapt for stereo. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 9661\u20139670","DOI":"10.1109\/CVPR.2019.00989"},{"key":"4003_CR17","doi-asserted-by":"crossref","unstructured":"Zhang F., Qi X, Yang R, Prisacariu V, Wah B, Torr P (2020) Domain-invariant stereo matching networks. In: European conference on computer vision, pp 420\u2013439","DOI":"10.1007\/978-3-030-58536-5_25"},{"key":"4003_CR18","doi-asserted-by":"crossref","unstructured":"Mousavian A, Pirsiavash H, Ko\u0161eck\u00e1 J (2016) Joint semantic segmentation and depth estimation with deep convolutional networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp 611\u2013619","DOI":"10.1109\/3DV.2016.69"},{"key":"4003_CR19","doi-asserted-by":"crossref","unstructured":"Zama Ramirez P, Poggi M, Tosi F, Mattoccia S, Di Stefano L (2018) Geometry meets semantics for semi-supervised monocular depth estimation. In: Asian Conference on Computer Vision. Springer, pp 298\u2013313","DOI":"10.1007\/978-3-030-20893-6_19"},{"key":"4003_CR20","doi-asserted-by":"crossref","unstructured":"Wang P, Shen X, Lin Z, Cohen S, Price B, Yuille A (2015) Towards unified depth and semantic prediction from a single image. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2800\u20132809","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"4003_CR21","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\u2013651","DOI":"10.1007\/978-3-030-01234-2_39"},{"key":"4003_CR22","doi-asserted-by":"crossref","unstructured":"Wu Z, Wu X, Zhang X, Wang S, Ju L (2019) Semantic stereo matching with pyramid cost volumes. In: International Conference on Computer Vision (ICCV), pp 7484\u20137493","DOI":"10.1109\/ICCV.2019.00758"},{"key":"4003_CR23","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, 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 4:1162\u20131169","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"7","key":"4003_CR24","first-page":"12926","volume":"34","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Chen Y, Bai X, Yu S, Yu K, Li Z, Yang K (2019) Adaptive unimodal cost volume filtering for deep stereo matching. The IEEE conference on computer vision and pattern recognition (CVPR) 34(7):12926\u201312934","journal-title":"The IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"4003_CR25","doi-asserted-by":"crossref","unstructured":"Song X, Zhao X, Hu H, Fang L (2018) EdgeStereo: A context integrated residual pyramid network for stereo matching. In: Asian conference on computer vision, pp 20\u201335","DOI":"10.1007\/978-3-030-20873-8_2"},{"key":"4003_CR26","doi-asserted-by":"crossref","unstructured":"Luo W, Schwing AG, Urtasun R (2016) Efficient deep learning for stereo matching. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5695\u20135703","DOI":"10.1109\/CVPR.2016.614"},{"key":"4003_CR27","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2017) Detect, Replace, Refine: Deep structured prediction for pixel wise labeling. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5248\u20135257","DOI":"10.1109\/CVPR.2017.760"},{"issue":"2","key":"4003_CR28","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s00371-020-01811-x","volume":"37","author":"S Chen","year":"2021","unstructured":"Chen S, Zhang J, Jin M (2021) A simplified ICA-based local similarity stereo matching. Vis Comput 37(2):411\u2013419","journal-title":"Vis Comput"},{"key":"4003_CR29","doi-asserted-by":"crossref","unstructured":"Li X, Fan Y, Lv G, Ma H (2021) Area-based correlation and non-local attention network for stereo matching. In: The Visual Computer, pp 1\u201315","DOI":"10.1007\/s00371-021-02228-w"},{"key":"4003_CR30","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\u201314372","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"4003_CR31","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":"4003_CR32","doi-asserted-by":"crossref","unstructured":"Chen PY, Liu A, Liu Y, Wang Y (2019) Towards scene understanding: unsupervised monocular depth estimation with semantic aware representation. In: 2019 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2624\u2013 2632","DOI":"10.1109\/CVPR.2019.00273"},{"key":"4003_CR33","doi-asserted-by":"crossref","unstructured":"Dovesi PL, Poggi M, Andraghetti L, Mart\u00ed M, Kjellstr\u00f6m H, Pieropan A, Mattoccia S (2020) Real-Time Semantic stereo matching. In: 2020 IEEE international conference on robotics and automation (ICRA), pp 10780\u201310787","DOI":"10.1109\/ICRA40945.2020.9196784"},{"key":"4003_CR34","doi-asserted-by":"crossref","unstructured":"He K, et al. (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"4003_CR35","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587"},{"key":"4003_CR36","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Adv Neural Inf Process Syst"},{"key":"4003_CR37","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The KITTI vision benchmark suite. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"4003_CR38","doi-asserted-by":"crossref","unstructured":"Menze M, Geiger A (2015) Object scene flow for autonomous vehicles. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3061\u20133070","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"4003_CR39","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M et al (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"4003_CR40","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"4003_CR41","doi-asserted-by":"crossref","unstructured":"Rao Z, He M, Dai Y, Shen Z (2020) Patch attention network with generative adversarial model for semi-supervised binocular disparity prediction. In: The Visual Computer, pp 1\u201317","DOI":"10.1007\/s00371-020-02001-5"},{"key":"4003_CR42","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1109\/LSP.2020.2993776","volume":"27","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Li Y, Kong Y, Liu B (2020) Attention aggregation encoder-decoder network framework for stereo matching. IEEE Signal Processing Letters 27:760\u2013764","journal-title":"IEEE Signal Processing Letters"},{"key":"4003_CR43","doi-asserted-by":"crossref","unstructured":"Li Z, Liu X, Drenkow N, Ding A, Creighton F, Taylor R, 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\u20136206","DOI":"10.1109\/ICCV48922.2021.00614"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04003-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04003-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04003-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T11:35:52Z","timestamp":1684496152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04003-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,13]]},"references-count":43,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["4003"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04003-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,13]]},"assertion":[{"value":"13 July 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}