{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T04:05:34Z","timestamp":1776139534212,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012182","type":"print"},{"value":"9783030012199","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01219-9_25","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:23:51Z","timestamp":1538835831000},"page":"418-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1072,"title":["ICNet for Real-Time Semantic Segmentation on High-Resolution Images"],"prefix":"10.1007","author":[{"given":"Hengshuang","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Xiaoyong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Jianping","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"25_CR2","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: ICLR (2015)"},{"key":"25_CR3","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561 (2015)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"25_CR6","unstructured":"Wu, Z., Shen, C., van den Hengel, A.: Wider or deeper: revisiting the ResNet model for visual recognition. arXiv:1611.10080 (2016)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"25_CR8","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv:1606.02147 (2016)"},{"key":"25_CR9","unstructured":"Treml, M., et al.: Speeding up semantic segmentation for autonomous driving. In: NIPS Workshop (2016)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Understanding convolution for semantic segmentation. arXiv:1702.08502 (2017)","DOI":"10.1109\/WACV.2018.00163"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.D.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Pohlen, T., Hermans, A., Mathias, M., Leibe, B.: Full-resolution residual networks for semantic segmentation in street scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.353"},{"key":"25_CR13","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv:1606.00915 (2016)"},{"key":"25_CR14","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.162"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"25_CR17","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recognit. Lett. 30, 88\u201397 (2009)","journal-title":"Pattern Recognit. Lett."},{"key":"25_CR18","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. arXiv:1612.03716 (2016)"},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TPAMI.2011.131","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu, C., Yuen, J., Torralba, A.: Nonparametric scene parsing via label transfer. TPAMI 33, 2368\u20132382 (2011)","journal-title":"TPAMI"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Chen, L., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P.A., Girshick, R.B., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"25_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1007\/978-3-319-46454-1_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Xia","year":"2016","unstructured":"Xia, F., Wang, P., Chen, L.-C., Yuille, A.L.: Zoom better to see clearer: human and object parsing with hierarchical auto-zoom net. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 648\u2013663. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_39"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"25_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS. (2015)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"25_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Romera, E., Alvarez, J.M., Bergasa, L.M., Arroyo, R.: Efficient ConvNet for real-time semantic segmentation. In: Intelligent Vehicles Symposium (IV) (2017)","DOI":"10.1109\/IVS.2017.7995966"},{"key":"25_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-49409-8_69","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Shelhamer","year":"2016","unstructured":"Shelhamer, E., Rakelly, K., Hoffman, J., Darrell, T.: Clockwork convnets for video semantic segmentation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 852\u2013868. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_69"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.441"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Kundu, A., Vineet, V., Koltun, V.: Feature space optimization for semantic video segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.345"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Gadde, R., Jampani, V., Gehler, P.V.: Semantic video CNNs through representation warping. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.477"},{"key":"25_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"25_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-319-46487-9_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Ghiasi","year":"2016","unstructured":"Ghiasi, G., Fowlkes, C.C.: Laplacian pyramid reconstruction and refinement for semantic segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 519\u2013534. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_32"},{"key":"25_CR35","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes VOC challenge. IJCV 88, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ADE20K dataset. arXiv:1608.05442 (2016)","DOI":"10.1109\/CVPR.2017.544"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM MM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"25_CR38","unstructured":"Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$1mb model size. arXiv:1602.07360 (2016)"},{"key":"25_CR39","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and Huffman coding. In: ICLR (2016)"},{"key":"25_CR40","unstructured":"Han, S., et al.: DSD: regularizing deep neural networks with dense-sparse-dense training flow. In: ICLR (2017)"},{"key":"25_CR41","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: ICLR (2017)"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Sturgess, P., Alahari, K., Ladicky, L., Torr, P.H.: Combining appearance and structure from motion features for road scene understanding. In: BMVC (2009)","DOI":"10.5244\/C.23.62"},{"key":"25_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01219-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T01:09:36Z","timestamp":1665018576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}