{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:25:01Z","timestamp":1771467901711,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T00:00:00Z","timestamp":1721692800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T00:00:00Z","timestamp":1721692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903195"],"award-info":[{"award-number":["61903195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s00530-024-01429-2","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T12:19:01Z","timestamp":1721737141000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Gated feature aggregate and alignment network for real-time semantic segmentation of street scenes"],"prefix":"10.1007","volume":"30","author":[{"given":"Qian","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhensheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwei","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunbao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,23]]},"reference":[{"issue":"6","key":"1429_CR1","doi-asserted-by":"publisher","first-page":"3431","DOI":"10.1007\/s00530-023-01173-z","volume":"29","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Cao, X., Wang, J., et al.: G-unext: a lightweight mlp-based network for reducing semantic gap in medical image segmentation. Multimed. Syst. 29(6), 3431\u20133446 (2023)","journal-title":"Multimed. Syst."},{"key":"1429_CR2","doi-asserted-by":"crossref","unstructured":"Kampffmeyer, M., Salberg, AB., Jenssen, R.: Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In: IEEE conference on computer vision and pattern recognition workshops, pp 680\u2013688 (2016)","DOI":"10.1109\/CVPRW.2016.90"},{"key":"1429_CR3","doi-asserted-by":"crossref","unstructured":"Xu, H., Gao, Y., Yu, F., et\u00a0al.: End-to-end learning of driving models from large-scale video datasets. In: IEEE conference on computer vision and pattern recognition, pp 2174\u20132182 (2017)","DOI":"10.1109\/CVPR.2017.376"},{"key":"1429_CR4","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition, pp 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1429_CR5","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations, pp 2\u20134 (2016)"},{"issue":"4","key":"1429_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1429_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., et\u00a0al.: Pyramid scene parsing network. In: IEEE conference on computer vision and pattern recognition, pp 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"1429_CR8","doi-asserted-by":"crossref","unstructured":"Chen, LC., Zhu, Y., Papandreou, G., et\u00a0al.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European conference on computer vision, pp 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1429_CR9","doi-asserted-by":"crossref","unstructured":"Pang, Y., Li, Y., Shen, J., et\u00a0al.: Towards bridging semantic gap to improve semantic segmentation. In: IEEE\/CVF International Conference on Computer Vision, pp 4230\u20134239 (2019)","DOI":"10.1109\/ICCV.2019.00433"},{"key":"1429_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., et\u00a0al.: Ccnet: Criss-cross attention for semantic segmentation. In: IEEE\/CVF international conference on computer vision, pp 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1429_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et\u00a0al.: Dual attention network for scene segmentation. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1429_CR12","doi-asserted-by":"crossref","unstructured":"Chen, W., Zhu, X., Sun, R., et\u00a0al.: Tensor low-rank reconstruction for semantic segmentation. In: European conference on computer vision, pp 52\u201369 (2020)","DOI":"10.1007\/978-3-030-58520-4_4"},{"issue":"4","key":"1429_CR13","first-page":"1805","volume":"44","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Chen, Y., Lasang, P., et al.: Covariance attention for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 1805\u20131818 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1429_CR14","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: European conference on computer vision, pp 173\u2013190 (2020)","DOI":"10.1007\/978-3-030-58539-6_11"},{"issue":"5","key":"1429_CR15","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1109\/TCSVT.2020.3015866","volume":"31","author":"J Ji","year":"2020","unstructured":"Ji, J., Shi, R., Li, S., et al.: Encoder-decoder with cascaded crfs for semantic segmentation. IEEE Trans. Circ. Syst. Video Technol. 31(5), 1926\u20131938 (2020)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"1429_CR16","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhang L, Cheng MM, et\u00a0al.: Strip pooling: rethinking spatial pooling for scene parsing. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 4003\u20134012 (2020)","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"1429_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Zhou, T., Wang, W., et\u00a0al.: Deep hierarchical semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1246\u20131257 (2022)","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"1429_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pang, B., Lu, C.: Semantic segmentation by early region proxy. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1258\u20131268 (2022)","DOI":"10.1109\/CVPR52688.2022.00132"},{"issue":"12","key":"1429_CR19","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.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"1429_CR20","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2017","unstructured":"Romera, E., Alvarez, J.M., Bergasa, L.M., et al.: Erfnet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans. Intell. Transp. Syst. 19(1), 263\u2013272 (2017)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1429_CR21","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., et\u00a0al.: Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. In: European conference on computer vision, pp 552\u2013568 (2018)","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"1429_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., et\u00a0al.: Icnet for real-time semantic segmentation on high-resolution images. In: European conference on computer vision, pp 405\u2013420 (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"1429_CR23","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., et\u00a0al.: Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: European conference on computer vision, pp 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"1429_CR24","doi-asserted-by":"crossref","unstructured":"Lo, SY., Hang, HM., Chan, SW., et\u00a0al.: Efficient dense modules of asymmetric convolution for real-time semantic segmentation. In: ACM multimedia Asia, pp 1\u20136 (2019)","DOI":"10.1145\/3338533.3366558"},{"key":"1429_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, Q., Liu, J., et\u00a0al.: Lednet: a lightweight encoder-decoder network for real-time semantic segmentation. In: IEEE international conference on image processing, pp 1860\u20131864 (2019)","DOI":"10.1109\/ICIP.2019.8803154"},{"key":"1429_CR26","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., et\u00a0al.: In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12607\u201312616 (2019)","DOI":"10.1109\/CVPR.2019.01289"},{"key":"1429_CR27","doi-asserted-by":"crossref","unstructured":"Li, H., Xiong, P., Fan, H., et\u00a0al.: Dfanet: Deep feature aggregation for real-time semantic segmentation. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 9522\u20139531 (2019)","DOI":"10.1109\/CVPR.2019.00975"},{"key":"1429_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, W., Xie, Z., Li, Y., et\u00a0al.: Lrnnet: a light-weighted network with efficient reduced non-local operation for real-time semantic segmentation. In: IEEE international conference on multimedia and expo workshops, pp 1\u20136 (2020)","DOI":"10.1109\/ICMEW46912.2020.9106038"},{"key":"1429_CR29","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., et al.: Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129, 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1429_CR30","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Wolf, L., Hassner, T.: Hyperseg: Patch-wise hypernetwork for real-time semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4061\u20134070 (2021)","DOI":"10.1109\/CVPR46437.2021.00405"},{"issue":"3","key":"1429_CR31","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1007\/s10489-021-02603-z","volume":"52","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Jiang, J., Huang, Z., et al.: Fpanet: feature pyramid aggregation network for real-time semantic segmentation. Appl. Intell. 52(3), 3319\u20133336 (2022)","journal-title":"Appl. Intell."},{"issue":"11","key":"1429_CR32","doi-asserted-by":"publisher","first-page":"20991","DOI":"10.1109\/TITS.2022.3182311","volume":"23","author":"M Lu","year":"2022","unstructured":"Lu, M., Chen, Z., Liu, C., et al.: Mfnet: multi-feature fusion network for real-time semantic segmentation in road scenes. IEEE Trans. Intell. Transp. Syst. 23(11), 20991\u201321003 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1429_CR33","unstructured":"Mazzini, D.: Guided upsampling network for real-time semantic segmentation. In: British Machine Vision Conference, pp 117\u2013125 (2018)"},{"key":"1429_CR34","doi-asserted-by":"crossref","unstructured":"Li, X., You, A., Zhu, Z., et\u00a0al.: Semantic flow for fast and accurate scene parsing. In: European conference on computer vision, pp 775\u2013793 (2020)","DOI":"10.1007\/978-3-030-58452-8_45"},{"issue":"1","key":"1429_CR35","first-page":"550","volume":"44","author":"Z Huang","year":"2021","unstructured":"Huang, Z., Wei, Y., Wang, X., et al.: Alignseg: feature-aligned segmentation networks. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 550\u2013557 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1429_CR36","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., et\u00a0al: The cityscapes dataset for semantic urban scene understanding. In: IEEE conference on computer vision and pattern recognition, pp 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"1429_CR37","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 Recog. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recog. Lett."},{"key":"1429_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al: Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1429_CR39","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE conference on computer vision and pattern recognition, pp 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1429_CR40","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et\u00a0al: Mobilenetv2: inverted residuals and linear bottlenecks. In: IEEE conference on computer vision and pattern recognition, pp 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01429-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01429-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01429-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T08:32:35Z","timestamp":1724315555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01429-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,23]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1429"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01429-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,23]]},"assertion":[{"value":"18 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2024","order":3,"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.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving human participants and\/or animals"}}],"article-number":"213"}}