{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:51:56Z","timestamp":1782201116665,"version":"3.54.5"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Henan Provincial Science and Technology Research Project","award":["No. 252102211015"],"award-info":[{"award-number":["No. 252102211015"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62472145"],"award-info":[{"award-number":["No.62472145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00371-026-04547-2","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T13:03:37Z","timestamp":1781442217000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SGTNet: real-time semantic segmentation via sparse transformer integration and multi-scale feature fusion"],"prefix":"10.1007","volume":"42","author":[{"given":"Shan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fukai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanqiang","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingxu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,14]]},"reference":[{"key":"4547_CR1","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"4547_CR2","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."},{"key":"4547_CR3","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. Preprint at arXiv:1606.02147 (2016)"},{"key":"4547_CR4","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 405\u2013420 (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"4547_CR5","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","volume":"30","author":"T Wu","year":"2020","unstructured":"Wu, T., Tang, S., Zhang, R., Cao, J., Zhang, Y.: CGNet: a light-weight context guided network for semantic segmentation. IEEE Trans. Image Process. 30, 1169\u20131179 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"4547_CR6","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925\u20131934 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"4547_CR7","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. Preprint at arXiv:1412.7062 (2014)"},{"issue":"4","key":"4547_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","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 Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4547_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"4547_CR10","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arxiv 2017. Preprint at arXiv:1706.05587 2, 1 (2019)"},{"key":"4547_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"4547_CR12","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"4547_CR13","doi-asserted-by":"crossref","unstructured":"Fan, M., Lai, S., Huang, J., Wei, X., Chai, Z., Luo, J., Wei, X.: Rethinking BiSeNet for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9716\u20139725 (2021)","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"4547_CR14","unstructured":"Hong, Y., Pan, H., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. Preprint at arXiv:2101.06085 (2021)"},{"key":"4547_CR15","doi-asserted-by":"crossref","unstructured":"Yang, G., Wang, Y., Shi, D.: Reparameterizable dual-resolution network for real-time semantic segmentation. Preprint at arXiv:2406.12496 (2024)","DOI":"10.2139\/ssrn.5248070"},{"key":"4547_CR16","doi-asserted-by":"crossref","unstructured":"Xu, J., Xiong, Z., Bhattacharyya, S.P.: PIDNet: a real-time semantic segmentation network inspired by PID controllers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19529\u201319539 (2023)","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"4547_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S.: An image is worth 16x16 words: transformers for image recognition at scale. Preprint at arXiv:2010.11929 (2020)"},{"key":"4547_CR18","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"4547_CR19","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Real. Intell. Hardw. 5(1), 57\u201367 (2023)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"4547_CR20","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4547_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, W., Huang, Z., Luo, G., Chen, T., Wang, X., Liu, W., Yu, G., Shen, C.: Topformer: Token pyramid transformer for mobile semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12083\u201312093 (2022)","DOI":"10.1109\/CVPR52688.2022.01177"},{"issue":"1","key":"4547_CR22","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., Zhu, M., You, L., Yang, X., Zhang, J., Zhao, H., Zeng, D.: TMSDNet: transformer with multi-scale dense network for single and multi-view 3d reconstruction. Comput. Anim. Virtual Worlds 35(1), 2201 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"4547_CR23","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"4547_CR24","doi-asserted-by":"publisher","first-page":"7423","DOI":"10.52202\/068431-0539","volume":"35","author":"J Wang","year":"2022","unstructured":"Wang, J., Gou, C., Wu, Q., Feng, H., Han, J., Ding, E., Wang, J.: RTFormer: efficient design for real-time semantic segmentation with transformer. Adv. Neural. Inf. Process. Syst. 35, 7423\u20137436 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4547_CR25","unstructured":"Wan, Q., Huang, Z., Lu, J., Yu, G., Zhang, L.: SeaFormer: squeeze-enhanced axial transformer for mobile semantic segmentation. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"4547_CR26","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: Efficientvit: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14420\u201314430 (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"4547_CR27","unstructured":"Han, D., Pan, X., Han, Y., Song, S., Huang, G.: Flatten transformer: vision transformer using focused linear attention"},{"key":"4547_CR28","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Pan, S., Wan, P., Song, S., Huang, G.: Agent attention: on the integration of softmax and linear attention. In: European Conference on Computer Vision, pp. 124\u2013140. Springer (2024)","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"4547_CR29","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.1109\/TIP.2023.3261747","volume":"32","author":"G Gao","year":"2023","unstructured":"Gao, G., Xu, Z., Li, J., Yang, J., Zeng, T., Qi, G.-J.: CTCNet: a CNN-transformer cooperation network for face image super-resolution. IEEE Trans. Image Process. 32, 1978\u20131991 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4547_CR30","doi-asserted-by":"crossref","unstructured":"Kienzle, D., Kantonis, M., Sch\u00f6n, R., Lienhart, R.: Segformer++: efficient token-merging strategies for high-resolution semantic segmentation. In: 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 75\u201381. IEEE (2024)","DOI":"10.1109\/MIPR62202.2024.00019"},{"issue":"12","key":"4547_CR31","doi-asserted-by":"publisher","first-page":"8274","DOI":"10.1109\/TPAMI.2024.3401450","volume":"46","author":"Q Hou","year":"2024","unstructured":"Hou, Q., Lu, C.-Z., Cheng, M.-M., Feng, J.: Conv2former: a simple transformer-style convnet for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 8274\u20138283 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4547_CR32","unstructured":"Ge, C., Ding, X., Tong, Z., Yuan, L., Wang, J., Song, Y., Luo, P.: Advancing vision transformers with group-mix attention. Preprint at arXiv:2311.15157 (2023)"},{"key":"4547_CR33","unstructured":"Hatamizadeh, A., Heinrich, G., Yin, H., Tao, A., Alvarez, J.M., Kautz, J., Molchanov, P.: FasterViT: Fast vision transformers with hierarchical attention. Preprint at arXiv:2306.06189 (2023)"},{"key":"4547_CR34","doi-asserted-by":"crossref","unstructured":"Tan, W., Geng, Y., Xie, X.: FMViT: a multiple-frequency mixing vision transformer. Preprint at arXiv:2311.05707 (2023)","DOI":"10.3233\/FAIA240476"},{"issue":"10","key":"4547_CR35","doi-asserted-by":"publisher","first-page":"6858","DOI":"10.1109\/TPAMI.2024.3387116","volume":"46","author":"T Zhou","year":"2024","unstructured":"Zhou, T., Wang, W.: Prototype-based semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 46(10), 6858\u20136872 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4547_CR36","doi-asserted-by":"crossref","unstructured":"Yin, J., Chen, T., Pei, G., Liu, H., Yao, Y., Nie, L., Hua, X.: Semi-supervised semantic segmentation with multi-constraint consistency learning. IEEE Trans. Multimed. (2025)","DOI":"10.1109\/TMM.2025.3586111"},{"key":"4547_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104146","volume":"249","author":"J Yin","year":"2024","unstructured":"Yin, J., Yan, S., Chen, T., Chen, Y., Yao, Y.: Class probability space regularization for semi-supervised semantic segmentation. Comput. Vis. Image Underst. 249, 104146 (2024)","journal-title":"Comput. Vis. Image Underst."},{"key":"4547_CR38","doi-asserted-by":"crossref","unstructured":"Yin, J., Peng, N., Chen, Y., Zheng, Z., Gu, Y., Zhou, J.: Class-level multiple distributions representation are necessary for semantic segmentation. In: International Conference on Database Systems for Advanced Applications, pp. 340\u2013351. Springer (2024)","DOI":"10.1007\/978-981-97-5575-2_25"},{"issue":"12","key":"4547_CR39","doi-asserted-by":"publisher","first-page":"15897","DOI":"10.1109\/TITS.2023.3248089","volume":"24","author":"G Xu","year":"2023","unstructured":"Xu, G., Li, J., Gao, G., Lu, H., Yang, J., Yue, D.: Lightweight real-time semantic segmentation network with efficient transformer and CNN. IEEE Trans. Intell. Transp. Syst. 24(12), 15897\u201315906 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"4547_CR40","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wu, D., Yu, C., Chu, X., Sang, N., Gao, C.: SCTNet: single-branch CNN with transformer semantic information for real-time segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6378\u20136386 (2024)","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"4547_CR41","doi-asserted-by":"crossref","unstructured":"Dong, B., Wang, P., Wang, F.: Head-free lightweight semantic segmentation with linear transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 516\u2013524 (2023)","DOI":"10.1609\/aaai.v37i1.25126"},{"issue":"5","key":"4547_CR42","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1002\/cav.2293","volume":"35","author":"Z Xiao","year":"2024","unstructured":"Xiao, Z., Chen, Y., Zhou, X., He, M., Liu, L., Yu, F., Jiang, M.: Human action recognition in immersive virtual reality based on multi-scale spatio-temporal attention network. Comput. Anim. Virtual Worlds 35(5), 2293 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"4547_CR43","doi-asserted-by":"crossref","unstructured":"Wen, Y., Luo, B., Shi, W., Ji, J., Cao, W., Yang, X., Sheng, B.: SAT-Net: structure-aware transformer-based attention fusion network for low-quality retinal fundus images enhancement. IEEE Trans. Multimed. (2025)","DOI":"10.1109\/TMM.2025.3565935"},{"key":"4547_CR44","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"4547_CR45","doi-asserted-by":"crossref","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recogn. Lett. 30(2), 88\u201397 (2009)","DOI":"10.1016\/j.patrec.2008.04.005"},{"issue":"2","key":"4547_CR46","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"4547_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"4547_CR48","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"4547_CR49","unstructured":"MMS Contributors: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020)"},{"issue":"3","key":"4547_CR50","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"4547_CR51","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., Arroyo, R.: 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":"4547_CR52","unstructured":"Poudel, R.P., Liwicki, S., Cipolla, R.: Fast-SCNN: fast semantic segmentation network. Preprint at arXiv:1902.04502 (2019)"},{"key":"4547_CR53","doi-asserted-by":"crossref","unstructured":"Si, H., Zhang, Z., Lv, F., Yu, G., Lu, F.: Real-time semantic segmentation via multiply spatial fusion network. Preprint at arXiv:1911.07217 (2019)","DOI":"10.5244\/C.34.153"},{"key":"4547_CR54","doi-asserted-by":"crossref","unstructured":"Orsic, M., Kreso, I., Bevandic, P., Segvic, S.: In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12607\u201312616 (2019)","DOI":"10.1109\/CVPR.2019.01289"},{"issue":"11","key":"4547_CR55","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., Yu, G., Shen, C., Sang, N.: BiSeNet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vision 129(11), 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"4547_CR56","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Wolf, L., Hassner, T.: HyperSeg: patch-wise hypernetwork for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4061\u20134070 (2021)","DOI":"10.1109\/CVPR46437.2021.00405"},{"key":"4547_CR57","unstructured":"Peng, J., Liu, Y., Tang, S., Hao, Y., Chu, L., Chen, G., Wu, Z., Chen, Z., Yu, Z., Du, Y., et al.: PP-LiteSeg: a superior real-time semantic segmentation model. Preprint at arXiv:2204.02681 (2022)"},{"key":"4547_CR58","doi-asserted-by":"crossref","unstructured":"Yang, G., Wang, Y., Shi, D., Wang, Y.: Golden cudgel network for real-time semantic segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 25367\u201325376 (2025)","DOI":"10.1109\/CVPR52734.2025.02362"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04547-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04547-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04547-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:44:44Z","timestamp":1782200684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04547-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":58,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["4547"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04547-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"6 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2026","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"}}],"article-number":"338"}}