{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:07:24Z","timestamp":1774890444325,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,4,19]],"date-time":"2018-04-19T00:00:00Z","timestamp":1524096000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61401228"],"award-info":[{"award-number":["61401228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11280-018-0556-3","type":"journal-article","created":{"date-parts":[[2018,4,19]],"date-time":"2018-04-19T09:11:41Z","timestamp":1524129101000},"page":"555-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":114,"title":["Multi-scale deep context convolutional neural networks for semantic segmentation"],"prefix":"10.1007","volume":"22","author":[{"given":"Quan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangwei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longin Jan","family":"Latecki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,19]]},"reference":[{"key":"556_CR1","doi-asserted-by":"crossref","unstructured":"Badrinarayanan, V., Alex, K., Roberto, C.: SegNet: A deep convolutional encoder-decoder architecture for scene segmentation. IEEE TPAMI (2017)","DOI":"10.1109\/TPAMI.2016.2644615"},{"issue":"7","key":"556_CR2","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1109\/TPAMI.2011.231","volume":"34","author":"J Carreira","year":"2012","unstructured":"Carreira, J., Sminchisescu, C.: Cpmc: Automatic object segmentation using constrained parametric min-cuts. IEEE TPAMI. 34(7), 1312\u20131328 (2012)","journal-title":"IEEE TPAMI."},{"key":"556_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: Proceedings of CVPR, pp. 3640\u20133649 (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"556_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE TPAMI (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"556_CR5","doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: Proceedings of CVPR, pp. 2147\u20132154 (2014)","DOI":"10.1109\/CVPR.2014.276"},{"issue":"1","key":"556_CR6","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"11","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van, G.L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 11(1), 98\u2013136 (2015)","journal-title":"IJCV"},{"issue":"8","key":"556_CR7","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.: Learning hierarchical features for scene labeling. IEEE TPAMI. 35(8), 1915\u20131929 (2013)","journal-title":"IEEE TPAMI."},{"key":"556_CR8","doi-asserted-by":"crossref","unstructured":"Fulkerson, B., Vedaldi, A., Soatto, S.: Class Segmentation and Object Localization with Superpixel Neighborhoods. In: Proceedings of ICCV, pp. 670-677 (2009)","DOI":"10.1109\/ICCV.2009.5459175"},{"key":"556_CR9","doi-asserted-by":"crossref","unstructured":"Gao, L.L., Song, J.K., Nie, F.P., Zhou, F.H., Sebe, N., Shen, H.T.: Graph-Without-Cut: an ideal graph learning for image segmentation. In: Proceedings of AAAI, pp. 1188\u20131194 (2016)","DOI":"10.1609\/aaai.v30i1.10177"},{"issue":"9","key":"556_CR10","first-page":"2045","volume":"19","author":"LL Gao","year":"2017","unstructured":"Gao, L.L., Guo, Z., Zhang, H.W., Xu, X., Shen, H.T.: Video captioning with Attention-Based LSTM and semantic consistency. IEEE TMM. 19(9), 2045\u20132055 (2017)","journal-title":"IEEE TMM."},{"key":"556_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-Cnn. In: Proceedings of ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"556_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"556_CR13","doi-asserted-by":"crossref","unstructured":"Hariharan, B., ArbelAez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: Proceedings of ICCV, pp. 991\u2013998 (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"issue":"9","key":"556_CR14","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"KM He","year":"2015","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE TPAMI. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE TPAMI."},{"key":"556_CR15","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"556_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Y.Q., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of ACMMM, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"556_CR17","doi-asserted-by":"crossref","unstructured":"Kamran, S.A., Sabbir, A.S.: Efficient yet deep convolutional neural networks for semantic segmentation. In: Arxiv (2017)","DOI":"10.1109\/SAIN.2018.8673354"},{"key":"556_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of NIPS, pp. 1097\u20131105 (2012)"},{"key":"556_CR19","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of CVPR, pp. 2169\u20132178 (2006)","DOI":"10.1109\/CVPR.2006.68"},{"key":"556_CR20","doi-asserted-by":"crossref","unstructured":"Lin, G.S., Shen, C.H., Van, D.H., Reid, I.: Exploring context with deep structured models for semantic segmentation. IEEE TPAMI (2017)","DOI":"10.1109\/CVPR.2016.348"},{"issue":"5","key":"556_CR21","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: Dense correspondence across scenes and its applications. IEEE TPAMI. 33(5), 978\u2013994 (2011)","journal-title":"IEEE TPAMI."},{"key":"556_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z.W., Li, X.X., Luo, P., Loy, C.C., Tang, X.O.: Semantic image segmentation via deep parsing network. In: Proceedings of ICCV, pp. 1377\u20131385 (2015)","DOI":"10.1109\/ICCV.2015.162"},{"key":"556_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, M.M., Hu, X.W., Wang, K., Bai, X.: Richer convolutional features for edge detection. In: Proceedings of CVPR, pp. 5872\u20135881 (2017)","DOI":"10.1109\/CVPR.2017.622"},{"issue":"4","key":"556_CR24","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"J Long","year":"2017","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE TPAMI. 39(4), 640\u2013651 (2017)","journal-title":"IEEE TPAMI."},{"key":"556_CR25","unstructured":"Long, J.L., Zhang, N., Darrell, T.: Do convnets learn correspondence? In: Proceedings of NIPS, pp. 1601\u20131609 (2014)"},{"key":"556_CR26","doi-asserted-by":"crossref","unstructured":"Mostajabi, M., Yadollahpour, P., Shakhnarovich, G.: Feedforward semantic segmentation with zoom-out features. In: Proceedings of CVPR, pp. 3376\u20133385 (2015)","DOI":"10.1109\/CVPR.2015.7298959"},{"key":"556_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Fookes, C., Sridharan, S.: Deep context modeling for semantic segmentation. In: Proceedings of WACV, pp. 56\u201363 (2017)","DOI":"10.1109\/WACV.2017.14"},{"key":"556_CR28","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.Y.: Learning deconvolution network for semantic segmentation. In: Proceedings of ICCV, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"556_CR29","unstructured":"Pinherio, R.C., Pedro, H.: Recurrent convolutional neural networks for scene parsing. In: Proceedings of ICML (2014)"},{"key":"556_CR30","unstructured":"Ren, S.Q., He, K.M., Girshick, R., Sun, J.: Faster R-Cnn: towards real-time object detection with region proposal networks. In: Proceedings of NIPS, pp. 91\u201399 (2015)"},{"key":"556_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of MICCAI, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"556_CR32","doi-asserted-by":"crossref","unstructured":"Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: Proceedings of CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587503"},{"issue":"1","key":"556_CR33","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J Shotton","year":"2009","unstructured":"Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81(1), 2\u201323 (2009)","journal-title":"IJCV"},{"key":"556_CR34","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556 (2014)"},{"issue":"11","key":"556_CR35","first-page":"4999","volume":"25","author":"JK Song","year":"2016","unstructured":"Song, J.K., Gao, L.L., Nie, F.P., Shen, H.T., Yan, Y., Sebe, N.: Optimized graph learning using partial tags and multiple features for image and video annotation. IEEE TIP. 25(11), 4999\u20135011 (2016)","journal-title":"IEEE TIP."},{"key":"556_CR36","doi-asserted-by":"crossref","unstructured":"Song, J.K., Gao, L.L., Puscas, M.M., Nie, F.P., Shen, F.M., Sebe, N.: Joint graph learning and video segmentation via multiple cues and topology calibration. In: Proceedings of ACM MM, pp. 831\u2013840 (2016)","DOI":"10.1145\/2964284.2964295"},{"key":"556_CR37","doi-asserted-by":"crossref","unstructured":"Song, J.K., Gao, L., Liu, L., Zhu, X., Sebe, N.: Quantization-based hashing: a general framework for scalable image and video retrieval. PR (2017)","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"556_CR38","doi-asserted-by":"crossref","unstructured":"Song, J.K., Zhang, H.W., Li, X.P., Gao, L.L., Wang, M., Hong, R.C.: Self-supervised video hashing with hierarchical binary auto-encoder. IEEE TIP (2018)","DOI":"10.1109\/TIP.2018.2814344"},{"key":"556_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y.Q., Sermanet, P., Reed, S., Anguelo, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"556_CR40","doi-asserted-by":"crossref","unstructured":"Tighe, J., Lazebnik, S.: Finding things: image parsing with regions and per-exemplar detectors. In: Proceedings of CVPR, pp. 3001\u20133008 (2013)","DOI":"10.1109\/CVPR.2013.386"},{"issue":"10","key":"556_CR41","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2009.186","volume":"32","author":"ZW Tu","year":"2010","unstructured":"Tu, Z.W., Bai, X.: Auto-context and its application to high-level vision tasks and 3d brain image segmentation. IEEE TPAMI. 32(10), 1744\u20131757 (2010)","journal-title":"IEEE TPAMI."},{"issue":"2","key":"556_CR42","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van, D.S., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV. 104(2), 154\u2013171 (2013)","journal-title":"IJCV."},{"key":"556_CR43","unstructured":"Vladlen, K.: Efficient Inference in Fully Connected Crfs with Gaussian Edge Potentials. In: Proceedings of NIPS, pp. 4\u201310 (2011)"},{"key":"556_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., Gao, L., Wang, P., Sun, X., Liu, X.: Two-stream 3D convNet fusion for action recognition in videos with arbitrary size and length. IEEE Transactions on Multimedia (2017)","DOI":"10.1109\/TMM.2017.2749159"},{"issue":"3","key":"556_CR45","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.neucom.2015.11.133","volume":"21","author":"X Xu","year":"2016","unstructured":"Xu, X., He, L., Shimada, A., Taniguchi, R.I., Lu, H: Self-supervised video hashing with hierarchical binary auto-encoder. Neurocomputing 21(3), 191\u2013203 (2016)","journal-title":"Neurocomputing"},{"issue":"5","key":"556_CR46","first-page":"2494","volume":"26","author":"X Xu","year":"2017","unstructured":"Xu, X., Shen, F., Yang, Y., Shen, H.T., Li, X.L.: Learning discriminative binary codes for large-scale cross-modal retrieval. IEEE TIP. 26(5), 2494\u20132507 (2017)","journal-title":"IEEE TIP."},{"key":"556_CR47","doi-asserted-by":"crossref","unstructured":"Yang, W.B., Zhou, Q., Fan, Y.W., Gao, G.W., Wu, S.S., Ou, W.H., Lu, H.M., Cheng, J., Longin, J.L.: Deep context convolutional neural networks for semantic segmentation. In: Proceedings of CCCV (2017)","DOI":"10.1007\/978-981-10-7299-4_58"},{"key":"556_CR48","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv: 1511.07122 (2015)"},{"key":"556_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, H.H., Shi, J.P., Qi, X.J., Wang, X.G., Jia, J.Y.: Pyramid scene parsing network. arXiv: 1612.01105 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"556_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Paredes, B.R., Vineet, V., Su, Z.Z., Du, D.L., Huang, C., Torr, P.H.: Conditional random fields as recurrent neural networks. In: Proceedings of ICCV, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"},{"issue":"6","key":"556_CR51","first-page":"2219","volume":"22","author":"Q Zhou","year":"2013","unstructured":"Zhou, Q., Zhu, J., Liu, W.Y.: Learning dynamic hybrid Markov random field for image labeling. IEEE TIP. 22(6), 2219\u20132232 (2013)","journal-title":"IEEE TIP."},{"issue":"59","key":"556_CR52","first-page":"312","volume":"2016","author":"Q Zhou","year":"2016","unstructured":"Zhou, Q., Zheng, B.Y., Zhu, W.P., Latecki, L.J.: Multi-scale context for scene labeling via flexible segmentation graph. PR 2016(59), 312\u2013324 (2016)","journal-title":"PR"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-018-0556-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-018-0556-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-018-0556-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T07:25:56Z","timestamp":1660980356000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-018-0556-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,19]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["556"],"URL":"https:\/\/doi.org\/10.1007\/s11280-018-0556-3","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,19]]},"assertion":[{"value":"16 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}