{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:53:19Z","timestamp":1782395599902,"version":"3.54.5"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T00:00:00Z","timestamp":1780185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T00:00:00Z","timestamp":1780185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Xuzhou Vocational College of Industrial Technology","award":["No. XGY2025B038"],"award-info":[{"award-number":["No. XGY2025B038"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11554-026-01903-2","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T07:59:03Z","timestamp":1780300743000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-time RGB-T semantic segmentation via hierarchical semantic guidance and detail-preserving PIDNet"],"prefix":"10.1007","volume":"23","author":[{"given":"Haiyu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinfeng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,31]]},"reference":[{"key":"1903_CR1","doi-asserted-by":"publisher","unstructured":"Ha, Q., Watanabe, K., Karasawa, T.: MFNet: towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5108\u20135115 (2017). https:\/\/doi.org\/10.1109\/IROS.2017.8206396","DOI":"10.1109\/IROS.2017.8206396"},{"issue":"3","key":"1903_CR2","doi-asserted-by":"publisher","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","volume":"4","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Zuo, W., Liu, M.: RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot. Autom. Lett. 4(3), 2576\u20132583 (2019). https:\/\/doi.org\/10.1109\/LRA.2019.2904733","journal-title":"IEEE Robot. Autom. Lett."},{"key":"1903_CR3","doi-asserted-by":"publisher","unstructured":"Deng, F., Feng, H., Liang, M.: FEANet: feature-enhanced attention network for RGB-thermal real-time semantic segmentation. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4467\u20134473 (2021). https:\/\/doi.org\/10.1109\/IROS51168.2021.9636084","DOI":"10.1109\/IROS51168.2021.9636084"},{"issue":"3","key":"1903_CR4","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/TCSVT.2022.3208833","volume":"33","author":"G Li","year":"2023","unstructured":"Li, G., Wang, Y., Liu, Z., et al.: RGB-T semantic segmentation with location, activation, and sharpening. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1223\u20131235 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2022.3208833","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1903_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104579","volume":"151","author":"Z Shen","year":"2024","unstructured":"Shen, Z., Wang, J., Weng, Y., et al.: ECFNet: efficient cross-layer fusion network for real-time RGB-thermal urban scene parsing. Digit. Signal Process. 151, 104579 (2024). https:\/\/doi.org\/10.1016\/j.dsp.2024.104579","journal-title":"Digit. Signal Process."},{"issue":"5","key":"1903_CR6","doi-asserted-by":"publisher","first-page":"6477","DOI":"10.1109\/TITS.2025.3528064","volume":"26","author":"X Zhou","year":"2025","unstructured":"Zhou, X., Wu, X., Bao, L., et al.: AGFNet: adaptive gated fusion network for RGB-T semantic segmentation. IEEE Trans. Intell. Transp. Syst. 26(5), 6477\u20136492 (2025). https:\/\/doi.org\/10.1109\/TITS.2025.3528064","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1903_CR7","doi-asserted-by":"publisher","unstructured":"Ji, W., Li, J., Bian, C.: SemanticRT: a large-scale dataset and method for robust semantic segmentation in multispectral images. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 3307\u20133316 (2023). https:\/\/doi.org\/10.1145\/3581783.3611738","DOI":"10.1145\/3581783.3611738"},{"key":"1903_CR8","doi-asserted-by":"publisher","unstructured":"Liu, J., Liu, Z., Wu, G., et al.: Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8115\u20138124 (2023) https:\/\/doi.org\/10.1109\/ICCV51070.2023.00745","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"1903_CR9","doi-asserted-by":"publisher","unstructured":"Shivakumar, S.S., Rodrigues, N., Zhou, A.: PST900: RGB-thermal calibration, dataset and segmentation network. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 9441\u20139447 (2020). https:\/\/doi.org\/10.1109\/ICRA40945.2020.9196831","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"1903_CR10","doi-asserted-by":"publisher","unstructured":"Yu, C., Wang, J., Peng, C., et al.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 325\u2013341 (2018) https:\/\/doi.org\/10.1007\/978-3-030-01261-8_20","DOI":"10.1007\/978-3-030-01261-8_20"},{"issue":"11","key":"1903_CR11","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(11), 3051\u20133068 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01515-2","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"1903_CR12","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.1109\/TITS.2022.3228042","volume":"24","author":"H Pan","year":"2023","unstructured":"Pan, H., Hong, Y., Sun, W., et al.: Deep dual-resolution networks for real-time and accurate semantic segmentation of traffic scenes. IEEE Trans. Intell. Transp. Syst. 24(3), 3448\u20133460 (2023). https:\/\/doi.org\/10.1109\/TITS.2022.3228042","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1903_CR13","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01871","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"1903_CR14","doi-asserted-by":"publisher","unstructured":"Fan, M., Lai, S., Huang, J.: Rethinking BiSeNet for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9716\u20139725 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00959","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"1903_CR15","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1903_CR16","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1903_CR17","doi-asserted-by":"publisher","unstructured":"Chen, Y., Dai, X., Liu, M.: Dynamic convolution: attention over convolution kernels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11027\u201311036 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01104","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"1903_CR18","unstructured":"Yang, B., Bender, G., Le, Q.V., Ngiam, J.: CondConv: conditionally parameterized convolutions for efficient inference. In: Advances in Neural Information Processing Systems, vol. 32 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/f2201f5191c4e92cc5af043eebfd0946-Abstract.html"},{"key":"1903_CR19","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, X., Ma, N.: RepVGG: making VGG-style ConvNets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13728\u201313737 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"1903_CR20","doi-asserted-by":"publisher","first-page":"91137","DOI":"10.1109\/ACCESS.2022.3202190","volume":"10","author":"SJ Park","year":"2022","unstructured":"Park, S.J., Park, H.J., Kang, E.S., Ngo, B.H., Lee, H.S., Cho, S.I.: Pseudo label rectification via co-teaching and decoupling for multisource domain adaptation in semantic segmentation. IEEE Access 10, 91137\u201391149 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3202190","journal-title":"IEEE Access"},{"key":"1903_CR21","doi-asserted-by":"publisher","unstructured":"Ngo, B.H., Chae, Y.J., Kwon, J.E., Park, J.H., Cho, S.I.: Improved knowledge transfer for semi-supervised domain adaptation via trico training strategy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19157\u201319166 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01760","DOI":"10.1109\/ICCV51070.2023.01760"},{"key":"1903_CR22","doi-asserted-by":"publisher","unstructured":"Xue, Y., Jin, G., Zhong, B., Shen, T., Tan, L., Xue, C., Zheng, Y.: FMTrack: frequency-aware interaction and multi-expert fusion for RGB-T tracking. IEEE Trans. Circuits Syst. Video Technol. (2025). https:\/\/doi.org\/10.1109\/TCSVT.2025.3601598","DOI":"10.1109\/TCSVT.2025.3601598"},{"key":"1903_CR23","doi-asserted-by":"crossref","unstructured":"Guo, X., Lin, Z., Hu, L., Deng, Z., Liu, T., Zhou, W.: Cross-modal state space modeling for real-time RGB-thermal wild scene semantic segmentation. arXiv preprint arXiv:2506.17869 (2025)","DOI":"10.1109\/IROS60139.2025.11247008"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01903-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-026-01903-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01903-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:38:57Z","timestamp":1782394737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-026-01903-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,31]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1903"],"URL":"https:\/\/doi.org\/10.1007\/s11554-026-01903-2","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,31]]},"assertion":[{"value":"28 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 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"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"108"}}