{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:29:20Z","timestamp":1755998960528,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T00:00:00Z","timestamp":1623024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T00:00:00Z","timestamp":1623024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11042-021-11102-9","type":"journal-article","created":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T07:04:57Z","timestamp":1623049497000},"page":"28583-28601","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multiple attention networks for stereo matching"],"prefix":"10.1007","volume":"80","author":[{"given":"Longyuan","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7281-6282","authenticated-orcid":false,"given":"Houyu","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Wuwei","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,7]]},"reference":[{"key":"11102_CR1","doi-asserted-by":"crossref","unstructured":"Aleotti F, Poggi M, Tosi F, et al. (2019) Learning end-to-end scene flow by distilling single tasks knowledge[J]","DOI":"10.1609\/aaai.v34i07.6613"},{"key":"11102_CR2","first-page":"154","volume-title":"Exploiting semantic information and deep matching for optical flow[C]\/\/European conference on computer vision","author":"M Bai","year":"2016","unstructured":"Bai M, Luo W, Kundu K, Urtasun R (2016) Exploiting semantic information and deep matching for optical flow[C]\/\/European conference on computer vision. Springer, Cham, pp 154\u2013170"},{"key":"11102_CR3","doi-asserted-by":"crossref","unstructured":"Batsos K, Mordohai P (2018) Recresnet: a recurrent residual cnn architecture for disparity map enhancement[C]\/\/2018 international conference on 3D vision (3DV). IEEE, 238\u2013247","DOI":"10.1109\/3DV.2018.00036"},{"issue":"2","key":"11102_CR4","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.image.2006.11.012","volume":"22","author":"M Bleyer","year":"2007","unstructured":"Bleyer M, Gelautz M (2007) Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions[J]. Signal Process Image Commun 22(2):127\u2013143","journal-title":"Signal Process Image Commun"},{"key":"11102_CR5","doi-asserted-by":"crossref","unstructured":"Bleyer M, Rhemann C, Rother C (2011) Patchmatch stereo-stereo matching with slanted support windows[C]\/\/Bmvc. 11: 1\u201311","DOI":"10.5244\/C.25.14"},{"key":"11102_CR6","doi-asserted-by":"crossref","unstructured":"Bullinger S, Bodensteiner C, Arens M (2019) 3d object trajectory reconstruction using stereo matching and instance flow based multiple object tracking[C]\/\/2019 16th international conference on machine vision applications (MVA). IEEE, 1\u20136","DOI":"10.23919\/MVA.2019.8757921"},{"key":"11102_CR7","doi-asserted-by":"crossref","unstructured":"Chang J R, Chen Y S (2018) Pyramid stereo matching network[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5410\u20135418","DOI":"10.1109\/CVPR.2018.00567"},{"key":"11102_CR8","first-page":"228","volume-title":"Mutual information based semi-global stereo matching on the GPU[C]\/\/international symposium on visual computing","author":"I Ernst","year":"2008","unstructured":"Ernst I, Hirschm\u00fcller H (2008) Mutual information based semi-global stereo matching on the GPU[C]\/\/international symposium on visual computing. Springer, Berlin, Heidelberg, pp 228\u2013239"},{"key":"11102_CR9","doi-asserted-by":"crossref","unstructured":"Fan R, Liu Y, Yang X, Bocus, M J, Dahnoun (2018) et al. Real-time stereo vision for road surface 3-d reconstruction[C]\/\/2018 IEEE International Conference on Imaging Systems and Techniques (IST). IEEE, 1\u20136","DOI":"10.1109\/IST.2018.8577119"},{"key":"11102_CR10","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, et al. (2019) Dual attention network for scene segmentation[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"11102_CR11","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite,\u201d in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"11102_CR12","doi-asserted-by":"crossref","unstructured":"Guney F, Geiger A (2015) Displets: Resolving stereo ambiguities using object knowledge[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4165\u20134175","DOI":"10.1109\/CVPR.2015.7299044"},{"key":"11102_CR13","doi-asserted-by":"crossref","unstructured":"Guo X, Yang K, Yang W, Wang X, Li H (2019) Group-wise Correlation Stereo Network[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3273\u20133282","DOI":"10.1109\/CVPR.2019.00339"},{"issue":"2","key":"11102_CR14","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller H (2007) Stereo processing by semiglobal matching and mutual information[J]. IEEE Trans Pattern Anal Mach Intell 30(2):328\u2013341","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"11102_CR15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TPAMI.2012.156","volume":"35","author":"A Hosni","year":"2012","unstructured":"Hosni A, Rhemann C, Bleyer M, Rother C, Gelautz M (2012) Fast cost-volume filtering for visual correspondence and beyond[J]. IEEE Trans Pattern Anal Mach Intell 35(2):504\u2013511","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11102_CR16","unstructured":"Junming Z , Skinner K A , Vasudevan R , et al. (2019) DispSegNet: leveraging semantics for end-to-end learning of disparity estimation from stereo imagery[J]. IEEE Robot Autom Lett, 1\u20131"},{"key":"11102_CR17","doi-asserted-by":"crossref","unstructured":"Kanade T, Okutomi M (1991) A stereo matching algorithm with an adaptive window: Theory and experiment[C]\/\/Proceedings. 1991 IEEE International Conference on Robotics and Automation. IEEE, 1088\u20131095","DOI":"10.1109\/ROBOT.1991.131738"},{"key":"11102_CR18","doi-asserted-by":"crossref","unstructured":"Kendall A, Martirosyan H, Dasgupta S, Henry P, Kennedy R, Bachrach A (2017) End-to-end learning of geometry and context for deep stereo regression[C]\/\/Proceedings of the IEEE International Conference on Computer Vision. 66\u201375","DOI":"10.1109\/ICCV.2017.17"},{"issue":"37","key":"11102_CR19","doi-asserted-by":"publisher","first-page":"27039","DOI":"10.1007\/s11042-020-09260-3","volume":"79","author":"Z Kerkaou","year":"2020","unstructured":"Kerkaou Z, El Ansari M (2020) Support vector machines based stereo matching method for advanced driver assistance systems[J]. Multimed Tools Appl 79(37):27039\u201327055","journal-title":"Multimed Tools Appl"},{"key":"11102_CR20","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization[J]. Computer ence"},{"key":"11102_CR21","unstructured":"Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks[C]\/\/Advances in neural information processing systems. 1097\u20131105"},{"key":"11102_CR22","unstructured":"Liang Z, Guo Y, Feng Y, Chen W, Qiao L, Zhou L, et al. (2019) Stereo matching using multi-level cost volume and multi-scale feature Constancy[J]. IEEE Trans Pattern Anal Mach Intell."},{"key":"11102_CR23","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"11","key":"11102_CR24","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.3390\/rs10111844","volume":"10","author":"C Lu","year":"2018","unstructured":"Lu C, Uchiyama H, Thomas D, Shimada A, Taniguchi R (2018) Sparse cost volume for efficient stereo matching[J]. Remote Sens 10(11):1844","journal-title":"Remote Sens"},{"key":"11102_CR25","doi-asserted-by":"crossref","unstructured":"Luo W, Schwing A G, Urtasun R (2016) Efficient deep learning for stereo matching[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5695\u20135703","DOI":"10.1109\/CVPR.2016.614"},{"key":"11102_CR26","doi-asserted-by":"crossref","unstructured":"Mayer N, Ilg E, Hausser P, Fischer P, Cremers D, Dosovitskiy A (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4040\u20134048","DOI":"10.1109\/CVPR.2016.438"},{"key":"11102_CR27","doi-asserted-by":"crossref","unstructured":"Nie GY, Cheng MM, Liu Y, et al. (2019) Multi-level context ultra-aggregation for stereo matching[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 3283\u20133291","DOI":"10.1109\/CVPR.2019.00340"},{"key":"11102_CR28","doi-asserted-by":"publisher","first-page":"108152","DOI":"10.1109\/ACCESS.2019.2931922","volume":"7","author":"X Ou","year":"2019","unstructured":"Ou X, Yan P, Zhang Y, Tu B, Zhang G, Wu J, Li W (2019) Moving object detection method via ResNet-18 with encoder\u2013decoder structure in complex scenes[J]. IEEE Access 7:108152\u2013108160","journal-title":"IEEE Access"},{"key":"11102_CR29","doi-asserted-by":"crossref","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[J]. APSIPA Trans Signal Inf Process, 9","DOI":"10.1017\/ATSIP.2020.16"},{"key":"11102_CR30","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"11102_CR31","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[J]. IEEE Access 7:15152\u201315161","journal-title":"IEEE Access"},{"issue":"1\u20133","key":"11102_CR32","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. Int J Comput Vis 47(1\u20133):7\u201342","journal-title":"Int J Comput Vis"},{"key":"11102_CR33","doi-asserted-by":"crossref","unstructured":"Seki A, Pollefeys M (2017) Sgm-nets: Semi-global matching with neural networks[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 231\u2013240","DOI":"10.1109\/CVPR.2017.703"},{"key":"11102_CR34","doi-asserted-by":"crossref","unstructured":"Shaked A, Wolf L (2017) Improved stereo matching with constant highway networks and reflective confidence learning[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4641\u20134650","DOI":"10.1109\/CVPR.2017.730"},{"key":"11102_CR35","first-page":"20","volume-title":"Edgestereo: a context integrated residual pyramid network for stereo matching[C]\/\/Asian conference on computer vision","author":"X Song","year":"2018","unstructured":"Song X, Zhao X, Hu H, Fang L (2018) Edgestereo: a context integrated residual pyramid network for stereo matching[C]\/\/Asian conference on computer vision. Springer, Cham, pp 20\u201335"},{"key":"11102_CR36","doi-asserted-by":"crossref","unstructured":"Tulyakov S, Ivanov A, Fleuret F (2017) Weakly supervised learning of deep metrics for stereo reconstruction[C]\/\/Proceedings of the IEEE International Conference on Computer Vision. 1339\u20131348","DOI":"10.1109\/ICCV.2017.150"},{"key":"11102_CR37","doi-asserted-by":"crossref","unstructured":"Xu H, Zhang J (2020) AANet: Adaptive Aggregation Network for Efficient Stereo Matching[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1959-1968","DOI":"10.1109\/CVPR42600.2020.00203"},{"issue":"31\u201332","key":"11102_CR38","doi-asserted-by":"publisher","first-page":"23189","DOI":"10.1007\/s11042-020-09127-7","volume":"79","author":"M Yao","year":"2020","unstructured":"Yao M, Ouyang W, Xu B (2020) Hybrid cost aggregation for dense stereo matching[J]. Multimed Tools Appl 79(31\u201332):23189\u201323202","journal-title":"Multimed Tools Appl"},{"key":"11102_CR39","doi-asserted-by":"crossref","unstructured":"Yee K, Chakrabarti A (2020) Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures[C]\/\/The IEEE Winter Conference on Applications of Computer Vision. 183\u2013191","DOI":"10.1109\/WACV45572.2020.9093273"},{"key":"11102_CR40","doi-asserted-by":"crossref","unstructured":"Yin Z, Darrell T, Yu F (2019) Hierarchical discrete distribution decomposition for match density estimation[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6044\u20136053","DOI":"10.1109\/CVPR.2019.00620"},{"key":"11102_CR41","doi-asserted-by":"crossref","unstructured":"Zbontar J, LeCun Y (2015) Computing the stereo matching cost with a convolutional neural network[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 1592\u20131599","DOI":"10.1109\/CVPR.2015.7298767"},{"issue":"1\u201332","key":"11102_CR42","first-page":"2","volume":"17","author":"J Zbontar","year":"2016","unstructured":"Zbontar J, LeCun Y (2016) Stereo matching by training a convolutional neural network to compare image patches[J]. J Mach Learn Res 17(1\u201332):2","journal-title":"J Mach Learn Res"},{"issue":"2","key":"11102_CR43","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1109\/TIP.2017.2752370","volume":"27","author":"F Zhang","year":"2017","unstructured":"Zhang F, Wah BW (2017) Fundamental principles on learning new features for effective dense matching[J]. IEEE Trans Image Process 27(2):822\u2013836","journal-title":"IEEE Trans Image Process"},{"key":"11102_CR44","doi-asserted-by":"crossref","unstructured":"Zhang F, Prisacariu V, Yang R, Torr P, H S. (2019) GA-Net: Guided Aggregation Net for End-to-end Stereo Matching[C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 185\u2013194","DOI":"10.1109\/CVPR.2019.00027"},{"key":"11102_CR45","doi-asserted-by":"crossref","unstructured":"Zhang Y, Chen Y, Bai X, et al. (2020) Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching[C]\/\/AAAI. 12926\u201312934","DOI":"10.1609\/aaai.v34i07.6991"},{"key":"11102_CR46","unstructured":"Zhang Z, Lin Z, Xu J, et al. (2020) Bilateral attention network for rgb-d salient object detection[J]. arXiv preprint arXiv:2004.14582"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11102-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11102-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11102-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T15:32:05Z","timestamp":1627140725000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11102-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,7]]},"references-count":46,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["11102"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11102-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,6,7]]},"assertion":[{"value":"20 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2021","order":4,"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. The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}