{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T21:40:17Z","timestamp":1777585217475,"version":"3.51.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Sunchon National University's Glocal University","award":["2024-0470"],"award-info":[{"award-number":["2024-0470"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11265-025-01977-4","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T11:58:01Z","timestamp":1765367881000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CSA\u2009\u2212\u2009HRNet: Channel and Spatial Attention High-Resolution Networks for Semantic Segmentation"],"prefix":"10.1007","volume":"98","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8080-8071","authenticated-orcid":false,"given":"Jin-Seong","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1051-9263","authenticated-orcid":false,"given":"Sung-Wook","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6712-6730","authenticated-orcid":false,"given":"Hyun-Sung","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0802-6355","authenticated-orcid":false,"given":"Chun-Bo","family":"Sim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1776-9823","authenticated-orcid":false,"given":"Se-Hoon","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"issue":"4","key":"1977_CR1","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y Lecun","year":"1989","unstructured":"Lecun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4), 541\u2013551.","journal-title":"Neural Computation"},{"key":"1977_CR2","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv Preprint. arXiv:2010.11929"},{"issue":"22","key":"1977_CR3","doi-asserted-by":"publisher","first-page":"27001","DOI":"10.1007\/s10489-023-04807-x","volume":"53","author":"W Sung","year":"2023","unstructured":"Sung, W., Park, Jun, Y., Kim, J., Park, Se, H., Jung., and, Chun, B., & Sim (2023). How to train your pre-trained GAN models. Applied Intelligence, 53(22), 27001\u201327026.","journal-title":"Applied Intelligence"},{"key":"1977_CR4","unstructured":"Sung, W., Park, S., Jung, H., Chun, B. S. (2025). NeXtSRGAN: Enhancing super-resolution GAN with ConvNeXt discriminator for superior realism. The Visual Computer, pp. 1\u201327."},{"key":"1977_CR5","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. In Advances Neural Information Processing Systems (NIPS), pp. 1106\u20131114.","DOI":"10.1145\/3065386"},{"issue":"11","key":"1977_CR6","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"1977_CR7","unstructured":"Simonyan, K., Zisserman,\u00a0A. (2014). Very deep convolutional networks for large-scale image recognition. ArXiv Preprint arXiv:1409.1556."},{"key":"1977_CR8","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1977_CR9","unstructured":"Ciresan, D. C., Giusti, A., Gambardella, L. M., & Schmidhuber, J. (2012). Deep neural networks segment neuronal membranes in electron microscopy images. In Advances Neural Information Processing Systems (NIPS), pp. 2852\u20132860."},{"key":"1977_CR10","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"1977_CR11","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. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1977_CR12","doi-asserted-by":"crossref","unstructured":"Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In proceedings of the European conference on computer vision (ECCV), pp. 833\u2013851.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1977_CR13","unstructured":"Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., et al. (2019). High-resolution representations for labeling pixels and regions. ArXiv Preprint. arXiv:1904.04514"},{"key":"1977_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, M., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In advances neural information processing systems(NIPS), pp. 5998\u20136008."},{"key":"1977_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1977_CR16","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., & Kweon, I. (2018). CBAM: Convolutional block attention module. In proceedings of the European conference on computer vision (ECCV), pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1977_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, F., Fan, X., & Huang, D. (2021). Polarized self-attention: Towards high-quality pixel-wise regression. ArXiv Preprint. arXiv:2107.00782","DOI":"10.1016\/j.neucom.2022.07.054"},{"key":"1977_CR18","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019). Stand-alone self-attention in vision models. In advances neural information processing systems (NIPS), 32."},{"key":"1977_CR19","doi-asserted-by":"crossref","unstructured":"Jin, S., Kim, Sung, W., Park, Jun, Y., Kim, Jun, Park, Se, H., Jung., and, & Chun, B. S. (2023). E-HRNet: Enhanced semantic segmentation using squeeze and excitation.\u00a0Electronics, 12(17), 3619.","DOI":"10.3390\/electronics12173619"},{"key":"1977_CR20","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Shen, X., & Lin, L. (2017). Look into person: Self-supervised structure-sensitive learning and A new benchmark for human parsing. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 932\u2013940.","DOI":"10.1109\/CVPR.2017.715"},{"key":"1977_CR21","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N. G., Lee, S. W., Fidler, S. (2014). The role of context for object detection and semantic segmentation in the wild. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 891\u2013898.","DOI":"10.1109\/CVPR.2014.119"},{"issue":"3","key":"1977_CR22","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., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1977_CR23","unstructured":"Chen, L., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. ArXiv Preprint. arXiv:1706.05587"},{"key":"1977_CR24","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1977_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1977_CR26","unstructured":"Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. In advances neural information processing systems (NIPS), pp. 3104\u20133112."},{"key":"1977_CR27","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., & Vaswani, A. (2018). Self-attention with relative position representations. ArXiv Preprint. arXiv:1803.02155","DOI":"10.18653\/v1\/N18-2074"},{"key":"1977_CR28","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Le, Q., Vaswani, A., & Shlens, J. (2019). Attention augmented convolutional networks. In proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 3286\u20133295.","DOI":"10.1109\/ICCV.2019.00338"},{"key":"1977_CR29","unstructured":"Andreoli, J. M. (2019). convolution, attention and structure embedding. In advances neural information processing systems (NIPS)."},{"key":"1977_CR30","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019). GCNet: Non-local networks meet squeeze-excitation networks and beyond. In proceedings of the IEEE\/CVF international conference on computer vision workshop(ICCVW), pp. 1971\u20131980.","DOI":"10.1109\/ICCVW.2019.00246"},{"issue":"4","key":"1977_CR31","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/s11227-025-07135-8","volume":"81","author":"H Xu","year":"2025","unstructured":"Xu, H., Xu, Y., & Hu, K. (2025). A vision-based inspection system for pharmaceutical production line. The Journal of Supercomputing, 81(4), 625.","journal-title":"The Journal of Supercomputing"},{"key":"1977_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108261","volume":"133","author":"Y Yu","year":"2024","unstructured":"Yu, Y., Zhang, Y., Cheng, Z., Song, Z., & Tang, C. (2024). Multi-scale spatial pyramid attention mechanism for image recognition: An effective approach. Engineering Applications of Artificial Intelligence, 133, Article 108261.","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"9","key":"1977_CR33","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/s11760-025-04335-w","volume":"19","author":"H Xu","year":"2025","unstructured":"Xu, H., Liu, Q., Zhu, J., Dai, H., & Zhang, D. (2025). CSLNet: An enhanced YOLOv8-based approach to defect surface foreign objects in lyophilized powder. Signal Image and Video Processing, 19(9), 728.","journal-title":"Signal Image and Video Processing"},{"key":"1977_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-025-01953-y","author":"S Govind","year":"2025","unstructured":"Govind, S., et al. (2025). Lightweight stereo image super-resolution using modified parallax attention. Journal of Signal Processing Systems. https:\/\/doi.org\/10.1007\/s11265-025-01953-y","journal-title":"Journal of Signal Processing Systems"},{"issue":"2","key":"1977_CR35","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s11265-023-01839-x","volume":"95","author":"Q Cheng","year":"2023","unstructured":"Cheng, Q., Wu, Y., Castiglione, A., Narducci, F., & Wan, S. (2023). DA-Net: Dual attention network for flood forecasting. Journal of Signal Processing Systems, 95(2), 351\u2013362.","journal-title":"Journal of Signal Processing Systems"},{"issue":"1","key":"1977_CR36","doi-asserted-by":"publisher","first-page":"26030","DOI":"10.1038\/s41598-024-76874-0","volume":"14","author":"S Ma","year":"2024","unstructured":"Ma, S., Zhu, X., Xu, L., Zhou, L., & Chen, D. (2024). Lrnet: Lightweight attention-oriented residual fusion network for light field salient object detection. Scientific Reports, 14(1), 26030.","journal-title":"Scientific Reports"},{"key":"1977_CR37","doi-asserted-by":"crossref","unstructured":"Ruan, T., Liu, T., Huang, Z., Wei, Y., Wei, S., & Zhao, Y. (2019). Devil in the details: Towards accurate single and multiple human parsing. In proceedings of the AAAI conference on artificial intelligence, Vol. 33, No. 1, pp. 4814\u20134821.","DOI":"10.1609\/aaai.v33i01.33014814"},{"key":"1977_CR38","doi-asserted-by":"crossref","unstructured":"Qi, J., Wang, X., Hu, Y., Tang, X., & Liu, W. (2021). Pyramid self-attention for semantic segmentation. In Chinese conference on pattern recognition and computer vision (PRCV), Springer, pp. 480\u2013492.","DOI":"10.1007\/978-3-030-88004-0_39"},{"key":"1977_CR39","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zheng, Z., Zheng, L., Guan, T., Yu, J., & Yang, Y. (2018). Macro-micro adversarial network for human parsing. In proceedings of the European conference on computer vision (ECCV), pp. 418\u2013434.","DOI":"10.1007\/978-3-030-01240-3_26"},{"key":"1977_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, J., Nie, X., Zhao, F., Chen, Y., Wang, Z., Feng, J., & Yan, S. (2017). Self-supervised neural aggregation networks for human parsing. In proceedings of the IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp. 1595\u20131603.","DOI":"10.1109\/CVPRW.2017.204"},{"key":"1977_CR41","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., & Yan, S. (2018). Mutual learning to adapt for joint human parsing and pose estimation. In proceedings of the European Conference on computer vision (ECCV), pp. 502\u2013517.","DOI":"10.1007\/978-3-030-01228-1_31"},{"key":"1977_CR42","doi-asserted-by":"crossref","unstructured":"Liang, X., Gong, K., Shen, X., & Lin, L. (2018). Look into person: Joint body parsing & pose estimation network and a new benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(4), 871\u2013885.","DOI":"10.1109\/TPAMI.2018.2820063"},{"issue":"2","key":"1977_CR43","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. V., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The PASCAL visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1977_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D. (2014). Microsoft coco: Common objects in context. In proceedings of European conference on computer vision (ECCV), pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1977_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"},{"key":"1977_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K. J., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018). Context encoding for semantic segmentation. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 7151\u20137160.","DOI":"10.1109\/CVPR.2018.00747"},{"key":"1977_CR47","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2018). Context contrasted feature and gated multi-scale aggregation for scene segmentation. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 2393\u20132402.","DOI":"10.1109\/CVPR.2018.00254"},{"key":"1977_CR48","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Sun, J. (2015). Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In proceedings of the IEEE international conference on computer vision (ICCV), pp. 1635\u20131643.","DOI":"10.1109\/ICCV.2015.191"},{"key":"1977_CR49","doi-asserted-by":"crossref","unstructured":"Arnab, A., Jayasumana, S., Zheng, S., & Torr, P. H. S. (2016). Higher order conditional random fields in deep neural networks. In proceedings of the European conference on computer vision (ECCV), pp. 524\u2013540.","DOI":"10.1007\/978-3-319-46475-6_33"},{"key":"1977_CR50","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Hengel, A., & Reid, I. D. (2016). Efficient piecewise training of deep structured models for semantic segmentation. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 3194\u20133203.","DOI":"10.1109\/CVPR.2016.348"},{"key":"1977_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, pp. 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"1977_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-025-01977-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11265-025-01977-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-025-01977-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T11:58:09Z","timestamp":1765367889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11265-025-01977-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1977"],"URL":"https:\/\/doi.org\/10.1007\/s11265-025-01977-4","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"assertion":[{"value":"19 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"6"}}