{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:38:45Z","timestamp":1769186325472,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5567-3_9","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:25Z","timestamp":1769116405000},"page":"121-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Modal Supervised Contrastive Learning for\u00a0RGB-T Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Chuanjiang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhangyong","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Cali\u0144ski, T., and, J.H.: A dendrite method for cluster analysis. Commun. Stat. 3(1), 1\u201327 (1974)","DOI":"10.1080\/03610917408548446"},{"key":"9_CR2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: 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":"9_CR4","doi-asserted-by":"publisher","first-page":"111588","DOI":"10.1016\/j.knosys.2024.111588","volume":"292","author":"X Guo","year":"2024","unstructured":"Guo, X., Zhou, W., Liu, T.: Contrastive learning-based knowledge distillation for RGB-thermal urban scene semantic segmentation. Knowl.-Based Syst. 292, 111588 (2024)","journal-title":"Knowl.-Based Syst."},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Ha, Q., Watanabe, K., Karasawa, T., Ushiku, Y., Harada, T.: MFNet: towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5108\u20135115. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206396"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"9_CR7","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/TCSVT.2022.3208833","volume":"33","author":"G Li","year":"2022","unstructured":"Li, G., Wang, Y., Liu, Z., Zhang, X., Zeng, D.: RGB-T semantic segmentation with location, activation, and sharpening. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1223\u20131235 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"9_CR8","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1109\/TNNLS.2020.2995319","volume":"32","author":"X Li","year":"2020","unstructured":"Li, X., Yu, L., Chen, H., Fu, C.W., Xing, L., Heng, P.A.: Transformation-consistent self-ensembling model for semisupervised medical image segmentation. IEEE Trans. Neural Netw. Learn. Syst. 32(2), 523\u2013534 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"7","key":"9_CR9","doi-asserted-by":"publisher","first-page":"4060","DOI":"10.1109\/LRA.2023.3272269","volume":"8","author":"M Liang","year":"2023","unstructured":"Liang, M., Hu, J., Bao, C., Feng, H., Deng, F., Lam, T.L.: Explicit attention-enhanced fusion for RGB-thermal perception tasks. IEEE Robot. Autom. Lett. 8(7), 4060\u20134067 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"7","key":"9_CR10","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/s10489-025-06411-7","volume":"55","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Ye, J., He, W., Qu, Z., Xu, R.: NTFNet: narrowing-then-fusing network for RGB-TIR semantic segmentation. Appl. Intell. 55(7), 520 (2025)","journal-title":"Appl. Intell."},{"issue":"86","key":"9_CR11","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(86), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR12","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2019)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Pissas, T., Ravasio, C.S., Cruz, L.D., Bergeles, C.: Multi-scale and cross-scale contrastive learning for semantic segmentation. In: European Conference on Computer Vision, pp. 413\u2013429. Springer (2022)","DOI":"10.1007\/978-3-031-19818-2_24"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Rojas\u00a0Thomas, J.C., Pe\u00f1as, M.S., Mora, M.: New version of davies-bouldin index for clustering validation based on cylindrical distance. In: 2013 32nd International Conference of the Chilean Computer Science Society (SCCC), pp. 49\u201353 (2013)","DOI":"10.1109\/SCCC.2013.29"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Shahapure, K.R., Nicholas, C.: Cluster quality analysis using silhouette score. In: 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), pp. 747\u2013748. IEEE (2020)","DOI":"10.1109\/DSAA49011.2020.00096"},{"issue":"4","key":"9_CR16","first-page":"81","volume":"5","author":"H Shi","year":"2021","unstructured":"Shi, H., Xu, D., He, K., Zhang, H., Yue, Y.: Contrastive learning for a single historical painting\u2019s blind super-resolution. Vis. Inf. 5(4), 81\u201388 (2021)","journal-title":"Vis. Inf."},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Shivakumar, S.S., Rodrigues, N., Zhou, A., Miller, I.D., Kumar, V., Taylor, C.J.: PST900: RGB-thermal calibration, dataset and segmentation network. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 9441\u20139447. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196831"},{"issue":"3","key":"9_CR18","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. Automa. Lett. 4(3), 2576\u20132583 (2019)","journal-title":"IEEE Robot. Automa. Lett."},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Tang, Z., et\u00a0al.: Revisiting rgbt tracking benchmarks from the perspective of modality validity: a new benchmark, problem, and method. arXiv preprint arXiv:2405.00168 (2024)","DOI":"10.1109\/TIP.2025.3611687"},{"key":"9_CR20","doi-asserted-by":"publisher","first-page":"101881","DOI":"10.1016\/j.inffus.2023.101881","volume":"99","author":"Z Tang","year":"2023","unstructured":"Tang, Z., Xu, T., Li, H., Wu, X.J., Zhu, X., Kittler, J.: Exploring fusion strategies for accurate rgbt visual object tracking. Information Fusion 99, 101881 (2023)","journal-title":"Information Fusion"},{"issue":"10","key":"9_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3678176","volume":"20","author":"Z Tang","year":"2024","unstructured":"Tang, Z., Xu, T., Wu, X.J., Kittler, J.: Multi-level fusion for robust RGBT tracking via enhanced thermal representation. ACM Trans. Multimed. Comput. Commun. Appl. 20(10), 1\u201324 (2024)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Serial over parallel: learning continual unification for multi-modal visual object tracking and benchmarking (2025)","DOI":"10.1145\/3746027.3754879"},{"key":"9_CR23","unstructured":"Tang, Z., et al.: Omni survey for multimodality analysis in visual object tracking (2025)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., Gool, L.V.: Exploring cross-image pixel contrast for semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7283\u20137293 (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"issue":"1","key":"9_CR25","first-page":"30","volume":"7","author":"X Wang","year":"2023","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T.: Densecl: a simple framework for self-supervised dense visual pre-training. Vis. Inf. 7(1), 30\u201340 (2023)","journal-title":"Vis. Inf."},{"key":"9_CR26","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and Efficient Design for Semantic Segmentation with Transformers. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 12077\u201312090. Curran Associates, Inc. (2021)"},{"issue":"12","key":"9_CR27","doi-asserted-by":"publisher","first-page":"14679","DOI":"10.1109\/TITS.2023.3300537","volume":"24","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., Stiefelhagen, R.: CMX: cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Trans. Intell. Transp. Syst. 24(12), 14679\u201314694 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhao, S., Luo, Y., Zhang, D., Huang, N., Han, J.: ABMDRNet: adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2633\u20132642 (2021)","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"9_CR29","first-page":"16579","volume":"33","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Maire, M.: Self-supervised visual representation learning from hierarchical grouping. Adv. Neural. Inf. Process. Syst. 33, 16579\u201316590 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR30","doi-asserted-by":"publisher","first-page":"111398","DOI":"10.1016\/j.patcog.2025.111398","volume":"162","author":"S Zhao","year":"2025","unstructured":"Zhao, S., Jin, Z., Jiao, Q., Zhang, Q., Han, J.: Resolving semantic conflicts in RGB-T semantic segmentation. Pattern Recogn. 162, 111398 (2025)","journal-title":"Pattern Recogn."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, S., Liu, Y., Jiao, Q., Zhang, Q., Han, J.: Mitigating modality discrepancies for RGB-T semantic segmentation. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"103282","DOI":"10.1016\/j.inffus.2025.103282","volume":"123","author":"S Zhao","year":"2025","unstructured":"Zhao, S., Wang, J., Zhang, Q., Han, J.: Towards efficient RGB-T semantic segmentation via feature generative distillation strategy. Inf. Fusion 123, 103282 (2025)","journal-title":"Inf. Fusion"},{"issue":"5","key":"9_CR33","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., Yin, H., Jiang, Q., Zhang, J.: AGFNet: adaptive gated fusion network for RGB-T semantic segmentation. IEEE Trans. Intell. Transp. Syst. 26(5), 6477\u20136492 (2025)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5567-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:30Z","timestamp":1769116410000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}