{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:53:14Z","timestamp":1770274394261,"version":"3.49.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T00:00:00Z","timestamp":1557792000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T00:00:00Z","timestamp":1557792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s11063-019-10047-3","type":"journal-article","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T23:38:36Z","timestamp":1557877116000},"page":"2665-2679","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Online Hard Region Mining for Semantic Segmentation"],"prefix":"10.1007","volume":"50","author":[{"given":"Jin","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5404-0003","authenticated-orcid":false,"given":"Jingsong","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,14]]},"reference":[{"issue":"12","key":"10047_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10047_CR2","doi-asserted-by":"crossref","unstructured":"Brostow GJ, Shotton J, Fauqueur J, Cipolla R (2008) Segmentation and recognition using structure from motion point clouds. In: European conference on computer vision. Springer, pp 44\u201357","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"10047_CR3","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade R-CNN: Delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"issue":"4","key":"10047_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10047_CR5","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint \narXiv:1706.05587"},{"key":"10047_CR6","doi-asserted-by":"crossref","unstructured":"Chen LC, Yang Y, Wang J, Xu W, Yuille AL (2016) Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3640\u20133649","DOI":"10.1109\/CVPR.2016.396"},{"key":"10047_CR7","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Liang-Chieh Chen","year":"2018","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 801\u2013818"},{"key":"10047_CR8","doi-asserted-by":"crossref","unstructured":"Cire\u015fan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. arXiv preprint \narXiv:1202.2745","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"10047_CR9","doi-asserted-by":"crossref","unstructured":"Dai J, He K, Sun J (2016) Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3150\u20133158","DOI":"10.1109\/CVPR.2016.343"},{"issue":"8","key":"10047_CR10","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915\u20131929","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10047_CR11","unstructured":"Garcia-Garcia A, Orts-Escolano S, Oprea S, Villena-Martinez V, Garcia-Rodriguez J (2017) A review on deep learning techniques applied to semantic segmentation. arXiv preprint \narXiv:1704.06857"},{"key":"10047_CR12","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"10047_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"10047_CR14","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: International conference on computer vision. pp 991\u2013998","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"10047_CR15","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Girshick R, Malik J (2014) Simultaneous detection and segmentation. In: European conference on computer vision. Springer, pp 297\u2013312","DOI":"10.1007\/978-3-319-10584-0_20"},{"issue":"9","key":"10047_CR16","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Machine Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"10047_CR17","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\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10047_CR18","doi-asserted-by":"crossref","unstructured":"Hong C, Yu J, Chen X (2013) Image-based 3D human pose recovery with locality sensitive sparse retrieval. In: 2013 IEEE international conference on systems, man, and cybernetics. IEEE, pp 2103\u20132108","DOI":"10.1109\/SMC.2013.360"},{"issue":"12","key":"10047_CR19","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"key":"10047_CR20","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.ins.2015.03.032","volume":"320","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, You J, Chen X, Tao D (2015) Multi-view ensemble manifold regularization for 3D object recognition. Inf Sci 320:395\u2013405","journal-title":"Inf Sci"},{"issue":"7","key":"10047_CR21","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"Chaoqun Hong","year":"2019","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee K (2018) Multi-modal face pose estimation with multi-task manifold deep learning. IEEE Trans Ind Inform. \nhttps:\/\/doi.org\/10.1109\/TII.2018.2884211","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10047_CR22","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"10047_CR23","doi-asserted-by":"crossref","unstructured":"Li X, Liu Z, Luo P, Change\u00a0Loy C, Tang X (2017) Not all pixels are equal: difficulty-aware semantic segmentation via deep layer cascade. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3193\u20133202","DOI":"10.1109\/CVPR.2017.684"},{"key":"10047_CR24","unstructured":"Liu W, Rabinovich A, Berg AC (2015) ParseNet: Looking wider to see better. arXiv preprint \narXiv:1506.04579"},{"key":"10047_CR25","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10047_CR26","unstructured":"Loshchilov I, Hutter F (2015) Online batch selection for faster training of neural networks. arXiv preprint \narXiv:1511.06343"},{"key":"10047_CR27","doi-asserted-by":"crossref","unstructured":"Murthy VN, Singh V, Chen T, Manmatha R, Comaniciu D (2016) Deep decision network for multi-class image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2240\u20132248","DOI":"10.1109\/CVPR.2016.246"},{"key":"10047_CR28","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1520\u20131528","DOI":"10.1109\/ICCV.2015.178"},{"key":"10047_CR29","doi-asserted-by":"crossref","unstructured":"Peng C, Zhang X, Yu G, Luo G, Sun J (2017) Large kernel matters\u2014improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353\u20134361","DOI":"10.1109\/CVPR.2017.189"},{"key":"10047_CR30","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"10047_CR31","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"10047_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10047_CR33","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"10047_CR34","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint \narXiv:1409.1556"},{"key":"10047_CR35","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"issue":"11","key":"10047_CR36","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TPAMI.2016.2636150","volume":"39","author":"Y Wei","year":"2017","unstructured":"Wei Y, Liang X, Chen Y, Shen X, Cheng MM, Feng J, Zhao Y, Yan S (2017) STC: a simple to complex framework for weakly-supervised semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(11):2314\u20132320","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10047_CR37","unstructured":"Wu Z, Shen C, van den Hengel A (2016) High-performance semantic segmentation using very deep fully convolutional networks. arXiv preprint \narXiv:1604.04339"},{"key":"10047_CR38","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint \narXiv:1511.07122"},{"issue":"5","key":"10047_CR39","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/TIFS.2017.2787986","volume":"13","author":"J Yu","year":"2018","unstructured":"Yu J, Kuang Z, Zhang B, Zhang W, Lin D, Fan J (2018) Leveraging content sensitiveness and user trustworthiness to recommend fine-grained privacy settings for social image sharing. IEEE Trans Inf Forensics Secur 13(5):1317\u20131332","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"5","key":"10047_CR40","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1109\/TIFS.2016.2636090","volume":"12","author":"J Yu","year":"2017","unstructured":"Yu J, Zhang B, Kuang Z, Lin D, Fan J (2017) iPrivacy: image privacy protection by identifying sensitive objects via deep multi-task learning. IEEE Trans Inf Forensics Secur 12(5):1005\u20131016","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10047_CR41","unstructured":"Yuan Y, Wang J (2018) OCNet: Object context network for scene parsing. arXiv preprint \narXiv:1809.00916"},{"key":"10047_CR42","unstructured":"Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? In: European conference on computer vision. Springer, pp 443\u2013457"},{"key":"10047_CR43","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10047-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-019-10047-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-019-10047-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T23:42:39Z","timestamp":1589326959000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-019-10047-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,14]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["10047"],"URL":"https:\/\/doi.org\/10.1007\/s11063-019-10047-3","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,14]]},"assertion":[{"value":"14 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}