{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T10:57:37Z","timestamp":1778324257034,"version":"3.51.4"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"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":["No. 52175112"],"award-info":[{"award-number":["No. 52175112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06411-7","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T05:46:16Z","timestamp":1741585576000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["NTFNet: Narrowing-Then-Fusing network for RGB-TIR semantic segmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Yichen","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3978-7587","authenticated-orcid":false,"given":"Junjie","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangpeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoxuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"issue":"12","key":"6411_CR1","doi-asserted-by":"publisher","first-page":"14775","DOI":"10.1007\/s10489-022-04107-w","volume":"53","author":"D Wang","year":"2023","unstructured":"Wang D, Yuan Z, Ouyang W et al (2023) Adversarial learning based intermediate feature refinement for semantic segmentation. Appl Intell 53(12):14775\u201314791","journal-title":"Appl Intell"},{"key":"6411_CR2","doi-asserted-by":"crossref","unstructured":"Ha Q, Watanabe K, Karasawa T et\u00a0al (2017) Mfnet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: Proc IEEE Int Conf Intell Rob Syst, pp 5108\u20135115","DOI":"10.1109\/IROS.2017.8206396"},{"key":"6411_CR3","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","volume":"24","author":"W Zhou","year":"2021","unstructured":"Zhou W, Lin X, Lei J et al (2021) Mffenet: Multiscale feature fusion and enhancement network for rgb-thermal urban road scene parsing. IEEE Trans Multimed 24:2526\u20132538","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"6411_CR4","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10489-019-01587-1","volume":"50","author":"J Wang","year":"2020","unstructured":"Wang J, Xiong H, Wang H et al (2020) Adscnet: asymmetric depthwise separable convolution for semantic segmentation in real-time. Appl Intell 50(4):1045\u20131056","journal-title":"Appl Intell"},{"key":"6411_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108420","volume":"124","author":"J Wei","year":"2022","unstructured":"Wei J, Wu Z, Wang L et al (2022) A cascaded nested network for 3t brain mr image segmentation guided by 7t labeling. Patt Recognit 124:108420","journal-title":"Patt Recognit"},{"key":"6411_CR6","doi-asserted-by":"crossref","unstructured":"Ma M, Xia H, Tan Y et\u00a0al (2022) Ht-net: hierarchical context-attention transformer network for medical ct image segmentation. Appl Intell 1\u201314","DOI":"10.1007\/s10489-021-03010-0"},{"key":"6411_CR7","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Proc MICCAI, Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"6411_CR8","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1007\/s10489-022-03642-w","volume":"53","author":"T Dhamija","year":"2023","unstructured":"Dhamija T, Gupta A, Gupta S et al (2023) Semantic segmentation in medical images through transfused convolution and transformer networks. Appl Intell 53(1):1132\u20131148","journal-title":"Appl Intell"},{"issue":"6","key":"6411_CR9","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.3390\/rs14061367","volume":"14","author":"W Zhao","year":"2022","unstructured":"Zhao W, Dong Q, Zuo Z (2022) A method combining line detection and semantic segmentation for power line extraction from unmanned aerial vehicle images. Remote Sens 14(6):1367","journal-title":"Remote Sens"},{"key":"6411_CR10","doi-asserted-by":"crossref","unstructured":"An D, Zhang Q, Chao J et\u00a0al (2023) Duformer: Solving power line detection task in aerial images using semantic segmentation. In: Chin Conf Patt Recognit Comput Vis (PRCV), Springer, pp 54\u201366","DOI":"10.1007\/978-981-99-8543-2_5"},{"key":"6411_CR11","doi-asserted-by":"crossref","unstructured":"Abdelfattah R, Wang X, Wang S (2023) Plgan: Generative adversarial networks for power-line segmentation in aerial images. IEEE Trans Image Process","DOI":"10.1109\/TIP.2023.3321465"},{"key":"6411_CR12","doi-asserted-by":"crossref","unstructured":"Ma L, Xie H, Liu C et\u00a0al (2022) Learning cross-channel representations for semantic segmentation. IEEE Trans Multimed","DOI":"10.1109\/TMM.2022.3151145"},{"key":"6411_CR13","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proc IEEE Conf Comput Vis Patt Recognit, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"6411_CR14","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 Trans Patt Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6411_CR15","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X et\u00a0al (2017) Pyramid scene parsing network. In: Proc IEEE Conf Comput Vis Pattern Recognit, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"6411_CR16","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Patt Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6411_CR17","doi-asserted-by":"crossref","unstructured":"He J, Deng Z, Qiao Y (2019) Dynamic multi-scale filters for semantic segmentation. In: Proc Int Conf Comput Vis, pp 3562\u20133572","DOI":"10.1109\/ICCV.2019.00366"},{"key":"6411_CR18","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H et\u00a0al (2019) Dual attention network for scene segmentation. In: Proc IEEE Conf Comput Vis Patt Recognit, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"6411_CR19","doi-asserted-by":"crossref","unstructured":"Strudel R, Garcia R, Laptev I et\u00a0al (2021) Segmenter: Transformer for semantic segmentation. In: Proc Int Conf Comput Vis, pp 7262\u20137272","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"6411_CR20","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H et\u00a0al (2021) Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proc IEEE Conf Comput Vis Patt Recognit, pp 6881\u20136890","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"6411_CR21","unstructured":"Xie E, Wang W, Yu Z et\u00a0al (2021) Segformer: Simple and efficient design for semantic segmentation with transformers. Adv Neural Inform Process Syst 34"},{"issue":"3","key":"6411_CR22","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 (2019) Rtfnet: Rgb-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot Autom Lett 4(3):2576\u20132583","journal-title":"IEEE Robot Autom Lett"},{"issue":"3","key":"6411_CR23","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","volume":"18","author":"Y Sun","year":"2020","unstructured":"Sun Y, Zuo W, Yun P et al (2020) Fuseseg: semantic segmentation of urban scenes based on rgb and thermal data fusion. IEEE Trans Autom Sci Eng 18(3):1000\u20131011","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"6411_CR24","doi-asserted-by":"crossref","unstructured":"Deng F, Feng H, Liang M et\u00a0al (2021) Feanet: Feature-enhanced attention network for rgb-thermal real-time semantic segmentation. In: Proc IEEE Int Conf Intell Rob Syst, pp 4467\u20134473","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"6411_CR25","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 et al (2021) Gmnet: graded-feature multilabel-learning network for rgb-thermal urban scene semantic segmentation. IEEE Trans Image Process 30:7790\u20137802","journal-title":"IEEE Trans Image Process"},{"issue":"8","key":"6411_CR26","doi-asserted-by":"publisher","first-page":"9038","DOI":"10.1007\/s10489-022-03950-1","volume":"53","author":"S Ma","year":"2023","unstructured":"Ma S, Song K, Dong H et al (2023) Modal complementary fusion network for rgb-t salient object detection. Appl Intell 53(8):9038\u20139055","journal-title":"Appl Intell"},{"issue":"5","key":"6411_CR27","doi-asserted-by":"publisher","first-page":"5817","DOI":"10.1007\/s10489-021-02687-7","volume":"52","author":"X Lan","year":"2022","unstructured":"Lan X, Gu X, Gu X (2022) Mmnet: Multi-modal multi-stage network for rgb-t image semantic segmentation. Appl Intell 52(5):5817\u20135829","journal-title":"Appl Intell"},{"issue":"3","key":"6411_CR28","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","volume":"18","author":"Y Sun","year":"2021","unstructured":"Sun Y, Zuo W, Yun P et al (2021) Fuseseg: Semantic segmentation of urban scenes based on rgb and thermal data fusion. IEEE Trans Autom Sci Eng 18(3):1000\u20131011","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"6411_CR29","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","volume":"24","author":"W Zhou","year":"2021","unstructured":"Zhou W, Lin X, Lei J et al (2021) Mffenet: Multiscale feature fusion and enhancement network for rgb-thermal urban road scene parsing. IEEE Trans Multimed 24:2526\u20132538","journal-title":"IEEE Trans Multimed"},{"key":"6411_CR30","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","volume":"24","author":"W Zhou","year":"2022","unstructured":"Zhou W, Lin X, Lei J et al (2022) Mffenet: Multiscale feature fusion and enhancement network for rgb-thermal urban road scene parsing. IEEE Trans Multimed 24:2526\u20132538","journal-title":"IEEE Trans Multimed"},{"key":"6411_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.110176","volume":"186","author":"Z Guo","year":"2021","unstructured":"Guo Z, Li X, Xu Q et al (2021) Robust semantic segmentation based on rgb-thermal in variable lighting scenes. Meas 186:110176","journal-title":"Meas"},{"key":"6411_CR32","doi-asserted-by":"crossref","unstructured":"Zhang Q, Zhao S, Luo Y et\u00a0al (2021) Abmdrnet: Adaptive-weighted bi-directional modality difference reduction network for rgb-t semantic segmentation. In: 2021 IEEE\/CVF conference on computer vision and patt recognit (CVPR), pp 2633\u20132642","DOI":"10.1109\/CVPR46437.2021.00266"},{"issue":"1","key":"6411_CR33","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/TIV.2022.3164899","volume":"8","author":"W Zhou","year":"2023","unstructured":"Zhou W, Dong S, Lei J et al (2023) Mtanet: Multitask-aware network with hierarchical multimodal fusion for rgb-t urban scene understanding. IEEE Trans Intell Veh 8(1):48\u201358","journal-title":"IEEE Trans Intell Veh"},{"key":"6411_CR34","doi-asserted-by":"crossref","unstructured":"Zhang J, Liu H, Yang K et\u00a0al (2023) Cmx: Cross-modal fusion for rgb-x semantic segmentation with transformers. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2023.3300537"},{"key":"6411_CR35","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/LSP.2021.3066071","volume":"28","author":"G Zhang","year":"2021","unstructured":"Zhang G, Xue JH, Xie P et al (2021) Non-local aggregation for rgb-d semantic segmentation. IEEE Signal Process Lett 28:658\u2013662","journal-title":"IEEE Signal Process Lett"},{"key":"6411_CR36","doi-asserted-by":"crossref","unstructured":"Shivakumar SS, Rodrigues N, Zhou A et\u00a0al (2020) Pst900: Rgb-thermal calibration, dataset and segmentation network. In: 2020 IEEE international conference on robotics and automation (ICRA), IEEE, pp 9441\u20139447","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"6411_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108881","volume":"131","author":"W Wu","year":"2022","unstructured":"Wu W, Chu T, Liu Q (2022) Complementarity-aware cross-modal feature fusion network for rgb-t semantic segmentation. Patt Recognit 131:108881","journal-title":"Patt Recognit"},{"key":"6411_CR38","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.patrec.2021.03.015","volume":"146","author":"J Xu","year":"2021","unstructured":"Xu J, Lu K, Wang H (2021) Attention fusion network for multi-spectral semantic segmentation. Patt Recognit Lett 146:179\u2013184","journal-title":"Patt Recognit Lett"},{"key":"6411_CR39","unstructured":"Vaswani A, Shazeer N, Parmar N et\u00a0al (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"6411_CR40","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang X, Huang L et\u00a0al (2019) Ccnet: Criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"6411_CR41","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et\u00a0al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010:11929"},{"key":"6411_CR42","doi-asserted-by":"crossref","unstructured":"Hu X, Yang K, Fei L et\u00a0al (2019) Acnet: Attention based network to exploit complementary features for rgbd semantic segmentation. In: IEEE Int Conf Image Process, pp 1440\u20131444","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"6411_CR43","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang J, Cheng Y et\u00a0al (2017) Semantics-guided multi-level rgb-d feature fusion for indoor semantic segmentation. In: 2017 IEEE international conference on image processing (ICIP), IEEE, pp 1262\u20131266","DOI":"10.1109\/ICIP.2017.8296484"},{"issue":"14","key":"6411_CR44","doi-asserted-by":"publisher","first-page":"3368","DOI":"10.3390\/rs14143368","volume":"14","author":"H Liu","year":"2022","unstructured":"Liu H, Chen F, Zeng Z et al (2022) Amfuse: Add-multiply-based cross-modal fusion network for multi-spectral semantic segmentation. Remote Sens 14(14):3368","journal-title":"Remote Sens"},{"issue":"4","key":"6411_CR45","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1109\/TCSVT.2022.3216313","volume":"33","author":"C Xu","year":"2022","unstructured":"Xu C, Li Q, Jiang X et al (2022) Dual-space graph-based interaction network for rgb-thermal semantic segmentation in electric power scene. IEEE Trans Circ Syst Video Technol 33(4):1577\u20131592","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"6411_CR46","doi-asserted-by":"crossref","unstructured":"Liu SA, Xie H, Xu H et\u00a0al (2022) Partial class activation attention for semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and patter recognition, pp 16836\u201316845","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"6411_CR47","doi-asserted-by":"crossref","unstructured":"Fu Y, Chen Q, Zhao H (2022) Cgfnet: cross-guided fusion network for rgb-thermal semantic segmentation. Vis Comput 1\u201310","DOI":"10.1007\/s00371-022-02559-2"},{"key":"6411_CR48","doi-asserted-by":"crossref","unstructured":"Frigo O, Martin-Gaff\u00e9 L, Wacongne C (2022) Doodlenet: Double deeplab enhanced feature fusion for thermal-color semantic segmentation. In: Proc IEEE Conf Comput Vis Patt Recognit, pp 3021\u20133029","DOI":"10.1109\/CVPRW56347.2022.00341"},{"key":"6411_CR49","doi-asserted-by":"crossref","unstructured":"Zhou W, Dong S, Xu C et\u00a0al (2022) Edge-aware guidance fusion network for rgb thermal scene parsing. Proc AAAI Conf Artif Intell","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"6411_CR50","doi-asserted-by":"crossref","unstructured":"Deng F, Feng H, Liang M et\u00a0al (2021) Feanet: Feature-enhanced attention network for rgb-thermal real-time semantic segmentation. In: 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 4467\u20134473","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"6411_CR51","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neucom.2022.07.041","volume":"506","author":"J Liu","year":"2022","unstructured":"Liu J, Zhou W, Cui Y et al (2022) Gcnet: Grid-like context-aware network for rgb-thermal semantic segmentation. Neurocomputing 506:60\u201367","journal-title":"Neurocomputing"},{"issue":"3","key":"6411_CR52","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 et al (2022) Rgb-t semantic segmentation with location, activation, and sharpening. IEEE Trans Circ Syst Video Technol 33(3):1223\u20131235","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"6411_CR53","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","unstructured":"Tang L, Yuan J, Ma J (2022) Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network. Inf Fusion 82:28\u201342","journal-title":"Inf Fusion"},{"key":"6411_CR54","doi-asserted-by":"crossref","unstructured":"Liu J, Liu Z, Wu G et\u00a0al (2023) 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","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"6411_CR55","doi-asserted-by":"crossref","unstructured":"Tang L, Zhang H, Xu H et al (2023) Rethinking the necessity of image fusion in high-level vision tasks: A practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity. Inf Fusion 99","DOI":"10.1016\/j.inffus.2023.101870"},{"key":"6411_CR56","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6411_CR57","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, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"6411_CR58","unstructured":"Gu Y, Li C, Xie J (2018) Attention-aware generalized mean pooling for image retrieval. arXiv preprint arXiv:1811.00202"},{"key":"6411_CR59","doi-asserted-by":"crossref","unstructured":"Berman M, Triki AR, Blaschko MB (2018) The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4413\u20134421","DOI":"10.1109\/CVPR.2018.00464"},{"key":"6411_CR60","doi-asserted-by":"crossref","unstructured":"Wang P, Chen P, Yuan Y et\u00a0al (2018) Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV), IEEE, pp 1451\u20131460","DOI":"10.1109\/WACV.2018.00163"},{"key":"6411_CR61","doi-asserted-by":"crossref","unstructured":"Guo Z, Li X, Xu Q et al (2021) Robust semantic segmentation based on rgb-thermal in variable lighting scenes. Meas 186","DOI":"10.1016\/j.measurement.2021.110176"},{"issue":"5","key":"6411_CR62","doi-asserted-by":"publisher","first-page":"5817","DOI":"10.1007\/s10489-021-02687-7","volume":"52","author":"X Lan","year":"2022","unstructured":"Lan X, Gu X, Gu X (2022) Mmnet: Multi-modal multi-stage network for rgb-t image semantic segmentation. Appl Intell 52(5):5817\u20135829","journal-title":"Appl Intell"},{"key":"6411_CR63","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.neucom.2022.12.036","volume":"523","author":"W Liang","year":"2023","unstructured":"Liang W, Yang Y, Li F et al (2023) Mask-guided modality difference reduction network for rgb-t semantic segmentation. Neurocomputing 523:9\u201317","journal-title":"Neurocomputing"},{"key":"6411_CR64","doi-asserted-by":"crossref","unstructured":"Zhao S, Liu Y, Jiao Q et\u00a0al (2023) Mitigating modality discrepancies for rgb-t semantic segmentation. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"6411_CR65","first-page":"1","volume":"72","author":"X He","year":"2023","unstructured":"He X, Wang M, Liu T et al (2023) Sfaf-ma: Spatial feature aggregation and fusion with modality adaptation for rgb-thermal semantic segmentation. IEEE Trans Instrum Meas 72:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"key":"6411_CR66","unstructured":"Zhou Z, Wu S, Zhu G et\u00a0al (2023) Channel and spatial relation-propagation network for rgb-thermal semantic segmentation. arXiv preprint arXiv:2308.12534"},{"key":"6411_CR67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127913","volume":"595","author":"P Li","year":"2024","unstructured":"Li P, Chen J, Lin B et al (2024) Residual spatial fusion network for rgb-thermal semantic segmentation. Neurocomputing 595:127913","journal-title":"Neurocomputing"},{"key":"6411_CR68","first-page":"1","volume":"19","author":"H Zhou","year":"2022","unstructured":"Zhou H, Tian C, Zhang Z et al (2022) Multispectral fusion transformer network for rgb-thermal urban scene semantic segmentation. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"6411_CR69","doi-asserted-by":"crossref","unstructured":"Zhou W, Gong T, Lei J et\u00a0al (2023) Dbcnet: Dynamic bilateral cross-fusion network for rgb-t urban scene understanding in intelligent vehicles. IEEE Trans Syst Man Cybern Syst","DOI":"10.1109\/TSMC.2023.3298921"},{"key":"6411_CR70","doi-asserted-by":"crossref","unstructured":"Wang Y, Li G, Liu Z (2023) Sgfnet: semantic-guided fusion network for rgb-thermal semantic segmentation. IEEE Trans Circ Syst Video Technol 33(12):7737\u20137748","DOI":"10.1109\/TCSVT.2023.3281419"},{"key":"6411_CR71","doi-asserted-by":"crossref","unstructured":"Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 400\u2013407","DOI":"10.1214\/aoms\/1177729586"},{"key":"6411_CR72","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"6411_CR73","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 (2021) Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. Int J Comput Vis 129:3051\u20133068","journal-title":"Int J Comput Vis"},{"key":"6411_CR74","doi-asserted-by":"crossref","unstructured":"Zhao S, Zhang Q (2022) A feature divide-and-conquer network for rgb-t semantic segmentation. IEEE Trans Circ Syst Video Technol","DOI":"10.1109\/TCSVT.2022.3229359"},{"key":"6411_CR75","doi-asserted-by":"crossref","unstructured":"Liu J, Fan X, Huang Z et\u00a0al (2022) Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5802\u20135811","DOI":"10.1109\/CVPR52688.2022.00571"},{"issue":"1","key":"6411_CR76","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu H, Ma J, Jiang J et al (2020) U2fusion: A unified unsupervised image fusion network. IEEE Trans Patt Anal Mach Intell 44(1):502\u2013518","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6411_CR77","doi-asserted-by":"crossref","unstructured":"Huang Z, Liu J, Fan X et\u00a0al (2022) Reconet: Recurrent correction network for fast and efficient multi-modality image fusion. In: European conference on computer vision, Springer, pp 539\u2013555","DOI":"10.1007\/978-3-031-19797-0_31"},{"key":"6411_CR78","doi-asserted-by":"crossref","unstructured":"Zhao Z, Xu S, Zhang C et\u00a0al (2020) Didfuse: Deep image decomposition for infrared and visible image fusion. arXiv preprint arXiv:2003.09210","DOI":"10.24963\/ijcai.2020\/135"},{"key":"6411_CR79","doi-asserted-by":"crossref","unstructured":"Chen X, Lin KY, Wang J et\u00a0al (2020) Bi-directional cross-modality feature propagation with separation-and-aggregation gate for rgb-d semantic segmentation. In: Proc Eur Conf Comput Vis, pp 561\u2013577","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"6411_CR80","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H et\u00a0al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06411-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06411-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06411-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:37:23Z","timestamp":1758310643000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06411-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":80,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6411"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06411-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"23 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"520"}}