{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:20:35Z","timestamp":1776784835405,"version":"3.51.2"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,24]],"date-time":"2024-02-24T00:00:00Z","timestamp":1708732800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,24]],"date-time":"2024-02-24T00:00:00Z","timestamp":1708732800000},"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":["61973120"],"award-info":[{"award-number":["61973120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973120"],"award-info":[{"award-number":["61973120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973120"],"award-info":[{"award-number":["61973120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973120"],"award-info":[{"award-number":["61973120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11554-024-01414-y","type":"journal-article","created":{"date-parts":[[2024,2,24]],"date-time":"2024-02-24T05:02:10Z","timestamp":1708750930000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Cross-CBAM: a lightweight network for real-time scene segmentation"],"prefix":"10.1007","volume":"21","author":[{"given":"Zhengbin","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zhenhao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xingsheng","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,24]]},"reference":[{"issue":"2","key":"1414_CR1","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. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"1414_CR2","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vis. 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"1414_CR3","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, Springer, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1414_CR4","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":"1414_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3258455","author":"Y Wu","year":"2023","unstructured":"Wu, Y., Kong, Q., Zhang, L., Castiglione, A., Nappi, M., Wan, S.: Cdt-cad: context-aware deformable transformers for end-to-end chest abnormality detection on X-ray images. IEEE\/ACM Trans. Comput. Biol. Bioinform. (2023). https:\/\/doi.org\/10.1109\/TCBB.2023.3258455","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"issue":"4","key":"1414_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571734","volume":"23","author":"Y Wu","year":"2023","unstructured":"Wu, Y., Cao, H., Yang, G., Lu, T., Wan, S.: Digital twin of intelligent small surface defect detection with cyber-manufacturing systems. ACM Trans. Internet Technol. 23(4), 1\u201320 (2023)","journal-title":"ACM Trans. Internet Technol."},{"key":"1414_CR7","unstructured":"Wu, Z., Shen, C., Hengel, A.V.D.: Real-time semantic image segmentation via spatial sparsity. arXiv preprint arXiv:1712.00213 (2017)"},{"issue":"12","key":"1414_CR8","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":"1414_CR9","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)"},{"key":"1414_CR10","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":"1414_CR11","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1414_CR12","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., et\u00a0al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1414_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":"1414_CR14","doi-asserted-by":"crossref","unstructured":"Hung, S.-W., Lo, S.-Y., Hang, H.-M.: Incorporating luminance, depth and color information by a fusion-based network for semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2374\u20132378 (2019)","DOI":"10.1109\/ICIP.2019.8803360"},{"key":"1414_CR15","doi-asserted-by":"crossref","unstructured":"Li, X., You, A., Zhu, Z., Zhao, H., Yang, M., Yang, K., Tan, S., Tong, Y.: Semantic flow for fast and accurate scene parsing. In: European Conference on Computer Vision, Springer, pp. 775\u2013793 (2020)","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"1414_CR16","doi-asserted-by":"crossref","unstructured":"Song, Q., Mei, K., Huang, R.: Attanet: attention-augmented network for fast and accurate scene parsing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2567\u20132575 (2021)","DOI":"10.1609\/aaai.v35i3.16359"},{"key":"1414_CR17","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"1414_CR18","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"},{"key":"1414_CR19","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":"1414_CR20","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1414_CR21","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1414_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1414_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, Q., Liu, J., Xiong, J., Gao, G., Wu, X., Latecki, L.J.: Lednet: A lightweight encoder-decoder network for real-time semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 1860\u20131864 (2019)","DOI":"10.1109\/ICIP.2019.8803154"},{"key":"1414_CR24","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. arXiv preprint arXiv:2204.02681 (2022)"},{"key":"1414_CR25","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"3","key":"1414_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3587038","volume":"22","author":"Y Wu","year":"2023","unstructured":"Wu, Y., Zhang, L., Gu, Z., Lu, H., Wan, S.: Edge-ai-driven framework with efficient mobile network design for facial expression recognition. ACM Trans. Embed. Comput. Syst. 22(3), 1\u201317 (2023)","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"1414_CR27","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Vedaldi, A.: Gather-excite: exploiting feature context in convolutional neural networks. Adv. Neural Inform. Process. Syst. 31 (2018)"},{"key":"1414_CR28","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"11","key":"1414_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., Yu, G., Shen, C., Sang, N.: Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129(11), 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1414_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104470","volume":"123","author":"C Xiao","year":"2022","unstructured":"Xiao, C., Hao, X., Li, H., Li, Y., Zhang, W.: Real-time semantic segmentation with local spatial pixel adjustment. Image Vis. Comput. 123, 104470 (2022)","journal-title":"Image Vis. Comput."},{"key":"1414_CR31","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":"1414_CR32","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"issue":"1","key":"1414_CR33","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1007\/s11063-022-10957-9","volume":"55","author":"Y Li","year":"2023","unstructured":"Li, Y., Li, M., Li, Z., Xiao, C., Li, H.: Correction to: Efrnet: efficient feature reuse network for real-time semantic segmentation. Neural Process. Lett. 55(1), 873\u2013873 (2023)","journal-title":"Neural Process. Lett."},{"key":"1414_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40747-023-01063-x","volume":"9","author":"Y Dong","year":"2023","unstructured":"Dong, Y., Yang, H., Pei, Y., Shen, L., Zheng, L., Li, P.: Compact interactive dual-branch network for real-time semantic segmentation. Complex Intell. Syst. 9, 1\u201314 (2023)","journal-title":"Complex Intell. Syst."},{"key":"1414_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248089","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. (2023). https:\/\/doi.org\/10.1109\/TITS.2023.3248089","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1414_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40747-023-01046-y","volume":"9","author":"P Meng","year":"2023","unstructured":"Meng, P., Jia, S., Li, Q.: Dmbr-net: deep multiple-resolution bilateral network for real-time and accurate semantic segmentation. Complex Intell. Syst. 9, 1\u201310 (2023)","journal-title":"Complex Intell. Syst."},{"key":"1414_CR37","unstructured":"Guo, M.-H., Lu, C.-Z., Hou, Q., Liu, Z., Cheng, M.-M., Hu, S.-M.: Segnext: Rethinking convolutional attention design for semantic segmentation. arXiv preprint arXiv:2209.08575 (2022)"},{"key":"1414_CR38","unstructured":"Hong, Y., Pan, H., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. arXiv preprint arXiv:2101.06085 (2021)"},{"key":"1414_CR39","doi-asserted-by":"crossref","unstructured":"Hu, P., Caba, F., Wang, O., Lin, Z., Sclaroff, S., Perazzi, F.: Temporally distributed networks for fast video semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8818\u20138827 (2020)","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"1414_CR40","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"issue":"2","key":"1414_CR41","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 Recogn. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recogn. Lett."},{"key":"1414_CR42","unstructured":"Contributors, M.: MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation (2020)"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01414-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01414-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01414-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T12:29:22Z","timestamp":1712320162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01414-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,24]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["1414"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01414-y","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,24]]},"assertion":[{"value":"13 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"38"}}