{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:34:40Z","timestamp":1783226080830,"version":"3.54.6"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"9-10","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876002"],"award-info":[{"award-number":["61876002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076005"],"award-info":[{"award-number":["62076005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Anhui Natural Science Foundation Anhui energy Internet joint fund","award":["2008085UD07"],"award-info":[{"award-number":["2008085UD07"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s00371-022-02559-2","type":"journal-article","created":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T11:02:34Z","timestamp":1656673354000},"page":"3243-3252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["CGFNet: cross-guided fusion network for RGB-thermal semantic segmentation"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4191-4779","authenticated-orcid":false,"given":"Yanping","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaoqiao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,1]]},"reference":[{"key":"2559_CR1","first-page":"1","volume":"66","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder\u2013decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Machine Intell. 66, 1 (2017)","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"2559_CR2","unstructured":"Bojarski, M., Del\u00a0Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L.D., Monfort, M., Muller, U., Zhang, J., et\u00a0al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"2559_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., Xiao, J.: Deepdriving: learning affordance for direct perception in autonomous driving. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2722\u20132730 (2015)","DOI":"10.1109\/ICCV.2015.312"},{"issue":"4","key":"2559_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC 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":"2559_CR5","unstructured":"Chen, S., Zhu, X., Liu, W., He, X., Liu, J.: Global\u2013local propagation network for rgb-d semantic segmentation. arXiv preprint arXiv:2101.10801 (2021)"},{"key":"2559_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Wang, J., Wu, W., Qian, C., Li, H., Zeng, G.: Bi-directional cross-modality feature propagation with separation-and-aggregation gate for rgb-d semantic segmentation. In: European Conference on Computer Vision, pp. 561\u2013577 (2020)","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"2559_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Sun, Y., Meng, Q.H.: A dense semantic mapping system based on crf-rnn network. In: International Conference on Advanced Robotics, pp. 589\u2013594 (2017)","DOI":"10.1109\/ICAR.2017.8023671"},{"key":"2559_CR8","doi-asserted-by":"crossref","unstructured":"Deng, F., Feng, H., Liang, M., Wang, H., Yang, Y., Gao, Y., Chen, J., Hu, J., Guo, X., Lam, T.L.: 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)","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"2559_CR9","unstructured":"Fridman, L., Brown, D.E., Glazer, M., Angell, W., Dodd, S., Jenik, B., Terwilliger, J., Kindelsberger, J., Ding, L., Seaman, S., et\u00a0al.: Mit autonomous vehicle technology study: large-scale deep learning based analysis of driver behavior and interaction with automation. arXiv preprint arXiv:1711.06976 (2017)"},{"key":"2559_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2559_CR11","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) (2017)","DOI":"10.1109\/IROS.2017.8206396"},{"key":"2559_CR12","doi-asserted-by":"crossref","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: Fusenet: incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Asian Conference on Computer Vision, pp. 213\u2013228 (2016)","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"2559_CR13","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"},{"key":"2559_CR14","doi-asserted-by":"publisher","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: Acnet: attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1440\u20131444 (2019). https:\/\/doi.org\/10.1109\/ICIP.2019.8803025","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"2559_CR15","doi-asserted-by":"crossref","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: Acnet: attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1440\u20131444 (2019)","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"2559_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"2559_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Sun, Z., He, Z., Zhu, Q., Liu, D.: A practical trajectory planning framework for autonomous ground vehicles driving in urban environments. In: Intelligent Vehicles Symposium, pp. 1160\u20131166 (2015)","DOI":"10.1109\/IVS.2015.7225840"},{"key":"2559_CR18","doi-asserted-by":"crossref","unstructured":"Liu, J., He, J., Zhang, J., Ren, J.S., Li, H.: Efficientfcn: holistically-guided decoding for semantic segmentation. In: European Conference on Computer Vision, pp. 1\u201317 (2020)","DOI":"10.1007\/978-3-030-58574-7_1"},{"issue":"4","key":"2559_CR19","first-page":"640","volume":"39","author":"J Long","year":"2015","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(4), 640\u2013651 (2015)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"18","key":"2559_CR20","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1049\/el.2020.1635","volume":"56","author":"Y Lyu","year":"2020","unstructured":"Lyu, Y., Schiopu, I., Munteanu, A.: Multi-modal neural networks with multi-scale rgb-t fusion for semantic segmentation. Electron. Lett. 56(18), 920\u2013923 (2020)","journal-title":"Electron. Lett."},{"key":"2559_CR21","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571 (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"2559_CR22","unstructured":"Park, S.J., Hong, K.S., Lee, S.: Rdfnet: Rgb-d multi-level residual feature fusion for indoor semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4980\u20134989 (2017)"},{"key":"2559_CR23","doi-asserted-by":"crossref","unstructured":"Pohlen, T., Hermans, A., Mathias, M., Leibe, B.: Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes (2016)","DOI":"10.1109\/CVPR.2017.353"},{"key":"2559_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2559_CR25","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.robot.2018.07.002","volume":"108","author":"Y Sun","year":"2018","unstructured":"Sun, Y., Liu, M., Meng, M.Q.: Motion removal for reliable rgb-d slam in dynamic environments. Robot. Auton. Syst. 108, 115\u2013128 (2018)","journal-title":"Robot. Auton. Syst."},{"key":"2559_CR26","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 (2020)","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"2559_CR27","first-page":"66","volume":"6","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. 6, 66 (2014)","journal-title":"Comput. Sci."},{"key":"2559_CR28","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.robot.2016.11.012","volume":"89","author":"Y Sun","year":"2017","unstructured":"Sun, Y., Liu, M., Meng, M.Q.H.: Improving rgb-d slam in dynamic environments: a motion removal approach. Robot. Auton. Syst. 89, 110\u2013122 (2017)","journal-title":"Robot. Auton. Syst."},{"key":"2559_CR29","doi-asserted-by":"publisher","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","volume":"66","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. 66, 2576\u20132583 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2559_CR30","first-page":"1","volume":"99","author":"Y Sun","year":"2020","unstructured":"Sun, Y., Zuo, W., Yun, P., Wang, H., Liu, M.: Fuseseg: semantic segmentation of urban scenes based on rgb and thermal data fusion. IEEE Trans. Autom. Sci. Eng. 99, 1\u201312 (2020)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"2559_CR31","first-page":"1","volume":"99","author":"Z Tu","year":"2021","unstructured":"Tu, Z., Li, Z., Li, C., Lang, Y., Tang, J.: Multi-interactive dual-decoder for rgb-thermal salient object detection. IEEE Trans. Image Process. 99, 1\u20131 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2559_CR32","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., Cottrell, G.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451\u20131460 (2018)","DOI":"10.1109\/WACV.2018.00163"},{"key":"2559_CR33","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857\u20131866 (2018)","DOI":"10.1109\/CVPR.2018.00199"},{"key":"2559_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., Agrawal, A.: Context encoding for semantic segmentation. In: Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"2559_CR35","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":"2559_CR36","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":"2559_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, W., Dong, S., Xu, C., Qian, Y.: Edge-aware guidance fusion network for rgb thermal scene parsing. arXiv preprint arXiv:2112.05144 (2021)","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"2559_CR38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMM.2021.3132156","volume":"99","author":"W Zhou","year":"2021","unstructured":"Zhou, W., Lin, X., Lei, J., Yu, L., Hwang, J.N.: Mffenet: multiscale feature fusion and enhancement network for rgbthermal urban road scene parsing. IEEE Trans. Multimed. 99, 1 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"2559_CR39","doi-asserted-by":"publisher","first-page":"7790","DOI":"10.1109\/TIP.2021.3109518","volume":"30","author":"W Zhou","year":"2021","unstructured":"Zhou, W., Liu, J., Lei, J., Yu, L., Hwang, J.N.: Gmnet: graded-feature multilabel-learning network for rgb-thermal urban scene semantic segmentation. IEEE Trans. Image Process. 30, 7790\u20137802 (2021)","journal-title":"IEEE Trans. Image Process."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02559-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02559-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02559-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T13:04:04Z","timestamp":1676034244000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02559-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,1]]},"references-count":39,"journal-issue":{"issue":"9-10","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["2559"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02559-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,1]]},"assertion":[{"value":"26 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2022","order":2,"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"}}]}}