{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T12:32:45Z","timestamp":1788957165269,"version":"build-2803163510"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61401113"],"award-info":[{"award-number":["61401113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province of China","doi-asserted-by":"crossref","award":["LC201426"],"award-info":[{"award-number":["LC201426"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","award":["3072020CF0807"],"award-info":[{"award-number":["3072020CF0807"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ph.D. Student Research and Innovation Fund of the Fundamental Research Funds for the Central Universities","award":["3072019GIP0807"],"award-info":[{"award-number":["3072019GIP0807"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s00521-020-05192-z","type":"journal-article","created":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T19:03:38Z","timestamp":1595444618000},"page":"3209-3220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Geometry understanding from autonomous driving scenarios based on feature refinement"],"prefix":"10.1007","volume":"33","author":[{"given":"Mingliang","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6185-833X","authenticated-orcid":false,"given":"Xuezhi","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,22]]},"reference":[{"key":"5192_CR1","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, et al (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. ArXiv: 1603.04467"},{"key":"5192_CR2","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-030-01240-3_15","volume-title":"Computer vision\u2014ECCV 2018","author":"S Chen","year":"2018","unstructured":"Chen S, Tan X, Wang B, Hu X (2018) Reverse attention for salient object detection. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision\u2014ECCV 2018. Springer International Publishing, Cham, pp 236\u2013252"},{"key":"5192_CR3","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Fischer P, Ilg E, H\u00e4usser P, Hazirbas C, Golkov V, vd Smagt P, Cremers D, Brox T (2015) Flownet: Learning optical flow with convolutional networks. In: 2015 IEEE international conference on computer vision (ICCV). pp 2758\u20132766","DOI":"10.1109\/ICCV.2015.316"},{"key":"5192_CR4","first-page":"2366","volume-title":"Advances in neural information processing systems 27","author":"D Eigen","year":"2014","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in neural information processing systems 27. Curran Associates, Inc., Red Hook, pp 2366\u20132374"},{"key":"5192_CR5","doi-asserted-by":"crossref","unstructured":"Fu H, Gong M, Wang C, Batmanghelich K, Tao D (2018) Deep ordinal regression network for monocular depth estimation. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 2002\u20132011","DOI":"10.1109\/CVPR.2018.00214"},{"key":"5192_CR6","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-46484-8_45","volume-title":"Computer vision\u2014ECCV 2016","author":"R Garg","year":"2016","unstructured":"Garg R, Bg VK, Carneiro G, Reid I (2016) Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision\u2014ECCV 2016. Springer International Publishing, Cham, pp 740\u2013756"},{"key":"5192_CR7","doi-asserted-by":"crossref","unstructured":"Godard C, Aodha OM, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). pp 6602\u20136611","DOI":"10.1109\/CVPR.2017.699"},{"key":"5192_CR8","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"5192_CR9","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) Flownet 2.0: Evolution of optical flow estimation with deep networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). pp 1647\u20131655","DOI":"10.1109\/CVPR.2017.179"},{"key":"5192_CR10","unstructured":"Kingma D, Ba J (2018) Adam: a method for stochastic optimization. ArXiv: 1412.6980"},{"key":"5192_CR11","doi-asserted-by":"crossref","unstructured":"Laina I, Rupprecht C, Belagiannis V, Tombari F, Navab N (2016) Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth international conference on 3D vision (3DV). pp 239\u2013248","DOI":"10.1109\/3DV.2016.32"},{"key":"5192_CR12","doi-asserted-by":"crossref","unstructured":"Lee W, Chuang P, Wang YF (2019) Perceptual quality preserving image super-resolution via channel attention. In: ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP). pp 1737\u20131741","DOI":"10.1109\/ICASSP.2019.8683507"},{"issue":"10","key":"5192_CR13","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 (2016) Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024\u20132039","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5192_CR14","doi-asserted-by":"crossref","unstructured":"Mahjourian R, Wicke M, Angelova A (2018) Unsupervised learning of depth and ego-motion from monocular video using 3d geometric constraints. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 5667\u20135675","DOI":"10.1109\/CVPR.2018.00594"},{"issue":"5","key":"5192_CR15","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal R, Montiel JMM, Tard\u00f3s JD (2015) ORB-SLAM: A versatile and accurate monocular slam system. IEEE Trans Robot 31(5):1147\u20131163","journal-title":"IEEE Trans Robot"},{"key":"5192_CR16","doi-asserted-by":"crossref","unstructured":"Newcombe RA, Lovegrove SJ, Davison AJ (2011) DTAM: Dense tracking and mapping in real-time. In: 2011 International conference on computer vision. pp 2320\u20132327","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"5192_CR17","doi-asserted-by":"crossref","unstructured":"Ren Z, Yan J, Ni B, Liu B, Yang X, Zha H (2017) Unsupervised deep learning for optical flow estimation. In: AAAI conference on artificial intelligence (AAAI)","DOI":"10.1609\/aaai.v31i1.10723"},{"issue":"2","key":"5192_CR18","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s11263-007-0107-3","volume":"80","author":"N Snavely","year":"2008","unstructured":"Snavely N, Seitz SM, Szeliski R (2008) Modeling the world from internet photo collections. Int J Comput Vis 80(2):189\u2013210","journal-title":"Int J Comput Vis"},{"issue":"10","key":"5192_CR19","doi-asserted-by":"publisher","first-page":"2972","DOI":"10.1109\/TCSVT.2018.2875449","volume":"29","author":"K Song","year":"2019","unstructured":"Song K, Yang H, Yin Z (2019) Multi-scale attention deep neural network for fast accurate object detection. IEEE Trans Circ Syst Video Technol 29(10):2972\u20132985","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"5192_CR20","doi-asserted-by":"crossref","unstructured":"Sun D, Yang X, Liu M, Kautz J (2018) PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 8934\u20138943","DOI":"10.1109\/CVPR.2018.00931"},{"key":"5192_CR21","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). pp 6450\u20136458","DOI":"10.1109\/CVPR.2017.683"},{"issue":"10","key":"5192_CR22","doi-asserted-by":"publisher","first-page":"2908","DOI":"10.1109\/TCSVT.2017.2746092","volume":"28","author":"H Wang","year":"2018","unstructured":"Wang H, Wang L (2018) Cross-agent action recognition. IEEE Trans Circ Syst Video Technol 28(10):2908\u20132919","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"5192_CR23","doi-asserted-by":"crossref","unstructured":"Wang X, Hu Y, Radwin RG, Lee JD (2018) Frame-subsampled, drift-resilient video object tracking. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). pp 1573\u20131577","DOI":"10.1109\/ICASSP.2018.8461923"},{"key":"5192_CR24","doi-asserted-by":"crossref","unstructured":"Wang Y, Yang Y, Yang Z, Zhao L, Wang P, Xu W (2018) Occlusion aware unsupervised learning of optical flow. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 4884\u20134893","DOI":"10.1109\/CVPR.2018.00513"},{"issue":"4","key":"5192_CR25","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"5192_CR26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer vision\u2014ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) CBAM: Convolutional block attention module. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision\u2014ECCV 2018. Springer International Publishing, Cham, pp 3\u201319"},{"key":"5192_CR27","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang P, Wang Y, Xu W, Nevatia R (2018) Lego: Learning edge with geometry all at once by watching videos. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 225\u2013234","DOI":"10.1109\/CVPR.2018.00031"},{"key":"5192_CR28","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang P, Xu W, Zhao L, Nevatia R (2018) Unsupervised learning of geometry from videos with edge-aware depth-normal consistency. In: AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"5192_CR29","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J (2018) Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 1983\u20131992","DOI":"10.1109\/CVPR.2018.00212"},{"issue":"10","key":"5192_CR30","doi-asserted-by":"publisher","first-page":"2504","DOI":"10.1109\/TMM.2019.2907060","volume":"21","author":"T Yu","year":"2019","unstructured":"Yu T, Wang L, Da C, Gu H, Xiang S, Pan C (2019) Weakly semantic guided action recognition. IEEE Trans Multimed 21(10):2504\u20132517","journal-title":"IEEE Trans Multimed"},{"key":"5192_CR31","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS, Li K, Agarwal H, Reid IM (2018) Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. pp 340\u2013349","DOI":"10.1109\/CVPR.2018.00043"},{"key":"5192_CR32","doi-asserted-by":"crossref","unstructured":"Zhang C, Kim J (2019) Modeling long- and short-term temporal context for video object detection. In: 2019 IEEE international conference on image processing (ICIP). pp 71\u201375","DOI":"10.1109\/ICIP.2019.8802920"},{"issue":"11","key":"5192_CR33","doi-asserted-by":"publisher","first-page":"7361","DOI":"10.1007\/s00521-018-3579-x","volume":"31","author":"H Zhang","year":"2019","unstructured":"Zhang H, Ji Y, Huang W, Liu L (2019) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl 31(11):7361\u20137380","journal-title":"Neural Comput Appl"},{"key":"5192_CR34","doi-asserted-by":"crossref","unstructured":"Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: Computer vision\u2014ECCV 2018. Springer International Publishing, Cham, pp 294\u2013310","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"5192_CR35","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N, Lowe DG (2017) Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). pp 6612\u20136619","DOI":"10.1109\/CVPR.2017.700"},{"key":"5192_CR36","doi-asserted-by":"crossref","unstructured":"Zhu Y, Newsam S (2018) Learning optical flow via dilated networks and occlusion reasoning. In: 2018 25th IEEE international conference on image processing (ICIP). pp 3333\u20133337","DOI":"10.1109\/ICIP.2018.8451790"},{"issue":"1","key":"5192_CR37","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TIP.2018.2865280","volume":"28","author":"Y Zhu","year":"2019","unstructured":"Zhu Y, Zhao C, Guo H, Wang J, Zhao X, Lu H (2019) Attention couplenet: fully convolutional attention coupling network for object detection. IEEE Trans Image Process 28(1):113\u2013126","journal-title":"IEEE Trans Image Process"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05192-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05192-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05192-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:02:51Z","timestamp":1667523771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05192-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,22]]},"references-count":37,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["5192"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05192-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,22]]},"assertion":[{"value":"2 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}