{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:08:31Z","timestamp":1772039311403,"version":"3.50.1"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"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":["61973066"],"award-info":[{"award-number":["61973066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Projects of Liaoning Province","award":["2021JH1\/10400049"],"award-info":[{"award-number":["2021JH1\/10400049"]}]},{"name":"Fundation of Key Laboratory of Equipment Reliability","award":["WD2C20205500306"],"award-info":[{"award-number":["WD2C20205500306"]}]},{"name":"Fundation of Key Laboratory of Aerospace System Simulation","award":["6142002200301"],"award-info":[{"award-number":["6142002200301"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s00521-023-08235-3","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T21:15:33Z","timestamp":1677618933000},"page":"10297-10310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MMPL-Net: multi-modal prototype learning for one-shot RGB-D segmentation"],"prefix":"10.1007","volume":"35","author":[{"given":"Dexing","family":"Shan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0610-3732","authenticated-orcid":false,"given":"Yunzhou","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaozheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shitong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonya A.","family":"Coleman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dermot","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"8235_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103306","volume":"80","author":"Y Bao","year":"2021","unstructured":"Bao Y et al (2021) Visible and thermal images fusion architecture for few-shot semantic segmentation. J Vis Commun Image Represent 80:103306. https:\/\/doi.org\/10.1016\/j.jvcir.2021.103306","journal-title":"J Vis Commun Image Represent"},{"key":"8235_CR2","doi-asserted-by":"crossref","unstructured":"Bachmann R, Mizrahi D, Atanov A, Zamir A (2022) Multimae: Multi-modal multi-task masked autoencoders. arXiv preprint arXiv:2204.01678","DOI":"10.1007\/978-3-031-19836-6_20"},{"issue":"12","key":"8235_CR3","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 Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8235_CR4","doi-asserted-by":"crossref","unstructured":"Cai Z, Shao L (2017) Rgb-d data fusion in complex space. In: 2017 IEEE International Conference on Image Processing (ICIP), pp 1965\u20131969","DOI":"10.1109\/ICIP.2017.8296625"},{"key":"8235_CR5","doi-asserted-by":"crossref","unstructured":"Cao J, Leng H, Lischinski D, Cohen-Or D, Tu C, Li Y (2021) Shapeconv: shape-aware convolutional layer for indoor rgb-d semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 7088\u20137097","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"8235_CR6","doi-asserted-by":"publisher","first-page":"8407","DOI":"10.1109\/TIP.2020.3014734","volume":"29","author":"H Chen","year":"2020","unstructured":"Chen H, Deng Y, Li Y, Hung TY, Lin G (2020) Rgbd salient object detection via disentangled cross-modal fusion. IEEE Trans Image Process 29:8407\u20138416","journal-title":"IEEE Trans Image Process"},{"key":"8235_CR7","doi-asserted-by":"crossref","unstructured":"Chen LC, 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 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"8235_CR8","doi-asserted-by":"crossref","unstructured":"Chen X, Lin KY, Wang J, Wu W, Qian C, Li H, Zeng G (2020) Bi-directional cross-modality feature propagation with separation-and-aggregation gate for rgb-d semantic segmentation. In: ECCV","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"8235_CR9","unstructured":"Dong N, Xing EP (2018) Few-shot semantic segmentation with prototype learning. In: British Machine Vision Conference vol 3"},{"key":"8235_CR10","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"8235_CR11","doi-asserted-by":"publisher","unstructured":"El\u00a0Madawi K, Rashed H, El\u00a0Sallab A, Nasr O, Kamel H, Yogamani S (2019) Rgb and lidar fusion based 3d semantic segmentation for autonomous driving. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp 7\u201312 https:\/\/doi.org\/10.1109\/ITSC.2019.8917447","DOI":"10.1109\/ITSC.2019.8917447"},{"key":"8235_CR12","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (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"},{"key":"8235_CR13","doi-asserted-by":"crossref","unstructured":"Hazirbas C, Ma L, Domokos C, Cremers D (2016) Fusenet: incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Asian conference on computer vision, Springer, pp 213\u2013228","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"8235_CR14","doi-asserted-by":"crossref","unstructured":"Hazirbas C, Ma L, Domokos C, Cremers D (2016) Fusenet: incorporating depth into semantic segmentation via fusion-based cnn architecture. In: ACCV","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"8235_CR15","doi-asserted-by":"crossref","unstructured":"He J, Deng Z, Zhou L, Wang Y, Qiao Y (2019) Adaptive pyramid context network for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp 7511\u20137520","DOI":"10.1109\/CVPR.2019.00770"},{"key":"8235_CR16","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, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8235_CR17","doi-asserted-by":"publisher","unstructured":"Hu X, Yang K, Fei L, Wang K (2019) Acnet: attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp 1440\u20131444. https:\/\/doi.org\/10.1109\/ICIP.2019.8803025","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"8235_CR18","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448\u2013456"},{"key":"8235_CR19","doi-asserted-by":"crossref","unstructured":"Ju R, Ge L, Geng W, Ren T, Wu G (2014) Depth saliency based on anisotropic center-surround difference. In: 2014 IEEE international conference on image processing (ICIP), pp 1115\u20131119","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"8235_CR20","doi-asserted-by":"publisher","unstructured":"Krispel G, Opitz M, Waltner G, Possegger H, Bischof H (2020) Fuseseg: lidar point cloud segmentation fusing multi-modal data. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1863\u20131872. https:\/\/doi.org\/10.1109\/WACV45572.2020.9093584","DOI":"10.1109\/WACV45572.2020.9093584"},{"key":"8235_CR21","doi-asserted-by":"crossref","unstructured":"Levin A, Lischinski D, Weiss Y (2004) Colorization using optimization. In: ACM SIGGRAPH 2004, pp 689\u2013694","DOI":"10.1145\/1186562.1015780"},{"key":"8235_CR22","doi-asserted-by":"crossref","unstructured":"Li G, Jampani V, Sevilla-Lara L, Sun D, Kim J, Kim J (2021) Adaptive prototype learning and allocation for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8334\u20138343","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"8235_CR23","doi-asserted-by":"crossref","unstructured":"Li X, Zhong Z, Wu J, Yang Y, Lin Z, Liu H (2019) Expectation-maximization attention networks for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9167\u20139176","DOI":"10.1109\/ICCV.2019.00926"},{"key":"8235_CR24","doi-asserted-by":"crossref","unstructured":"Lin D, Chen G, Cohen-Or D, Heng PA, Huang H (2017) Cascaded feature network for semantic segmentation of rgb-d images. In: Proceedings of the IEEE international conference on computer vision, pp 1311\u20131319","DOI":"10.1109\/ICCV.2017.147"},{"key":"8235_CR25","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2021.3058512","volume":"30","author":"B Liu","year":"2021","unstructured":"Liu B, Jiao J, Ye Q (2021) Harmonic feature activation for few-shot semantic segmentation. IEEE Trans Image Process 30:3142\u20133153","journal-title":"IEEE Trans Image Process"},{"key":"8235_CR26","unstructured":"Liu H, Zhang J, Yang K, Hu X, Stiefelhagen R (2022) Cmx: cross-modal fusion for rgb-x semantic segmentation with transformers. arXiv preprint arXiv:abs\/2203.04838"},{"key":"8235_CR27","doi-asserted-by":"crossref","unstructured":"Liu N, Zhang N, Shao L, Han J (2020) Learning selective mutual attention and contrast for rgb-d saliency detection. arXiv preprint arXiv:2010.05537","DOI":"10.1109\/CVPR42600.2020.01377"},{"key":"8235_CR28","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, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"8235_CR29","doi-asserted-by":"crossref","unstructured":"Ma L, St\u00fcckler J, Kerl C, Cremers D (2017) Multi-view deep learning for consistent semantic mapping with rgb-d cameras. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 598\u2013605","DOI":"10.1109\/IROS.2017.8202213"},{"key":"8235_CR30","doi-asserted-by":"crossref","unstructured":"Min J, Kang D, Cho M (2021) Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"8235_CR31","unstructured":"Park SJ, Hong KS, Lee S (2017) 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"},{"key":"8235_CR32","doi-asserted-by":"crossref","unstructured":"Pei J, Cheng T, Fan DP, Tang H, Chen C, Van\u00a0Gool L (2022) Osformer: one-stage camouflaged instance segmentation with transformers. arXiv preprint arXiv:2207.02255","DOI":"10.1007\/978-3-031-19797-0_2"},{"key":"8235_CR33","doi-asserted-by":"crossref","unstructured":"Peng H, Li B, Xiong W, Hu W, Ji R (2014) Rgbd salient object detection: a benchmark and algorithms. In: European conference on computer vision, Springer, pp 92\u2013109","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"8235_CR34","doi-asserted-by":"crossref","unstructured":"Piao Y, Ji W, Li J, Zhang M, Lu H (2019) Depth-induced multi-scale recurrent attention network for saliency detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 7254\u20137263","DOI":"10.1109\/ICCV.2019.00735"},{"key":"8235_CR35","doi-asserted-by":"crossref","unstructured":"Piao Y, Rong Z, Zhang M, Ren W, Lu H (2020) A2dele: adaptive and attentive depth distiller for efficient rgb-d salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9060\u20139069","DOI":"10.1109\/CVPR42600.2020.00908"},{"key":"8235_CR36","doi-asserted-by":"crossref","unstructured":"Prakash A, Chitta K, Geiger A (2021) Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7077\u20137087","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"8235_CR37","doi-asserted-by":"crossref","unstructured":"Ren L, Duan G, Huang T, Kang Z (2022) Multi-local feature relation network for few-shot learning. Neural Comput Appl 1\u201311","DOI":"10.1007\/s00521-021-06840-8"},{"key":"8235_CR38","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, Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"6","key":"8235_CR39","doi-asserted-by":"publisher","first-page":"4733","DOI":"10.1007\/s00521-021-06627-x","volume":"34","author":"L Sa","year":"2022","unstructured":"Sa L, Yu C, Ma X, Zhao X, Xie T (2022) Attentive fine-grained recognition for cross-domain few-shot classification. Neural Comput Appl 34(6):4733\u20134746","journal-title":"Neural Comput Appl"},{"key":"8235_CR40","unstructured":"Sankaran S, Yang D, Lim S (2021) Multimodal fusion refiner networks. CoRR abs\/2104.03435. arXiv:2104.03435"},{"key":"8235_CR41","doi-asserted-by":"crossref","unstructured":"Shaban A, Bansal S, Liu Z, Essa I, Boots B (2017) One-shot learning for semantic segmentation. arXiv preprint arXiv:abs\/1709.03410","DOI":"10.5244\/C.31.167"},{"key":"8235_CR42","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"issue":"2","key":"8235_CR43","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1109\/TIP.2018.2872629","volume":"28","author":"X Song","year":"2018","unstructured":"Song X, Jiang S, Herranz L, Chen C (2018) Learning effective rgb-d representations for scene recognition. IEEE Trans Image Process 28(2):980\u2013993","journal-title":"IEEE Trans Image Process"},{"issue":"4","key":"8235_CR44","doi-asserted-by":"publisher","first-page":"5558","DOI":"10.1109\/LRA.2020.3007457","volume":"5","author":"L Sun","year":"2020","unstructured":"Sun L, Yang K, Hu X, Hu W, Wang K (2020) Real-time fusion network for rgb-d semantic segmentation incorporating unexpected obstacle detection for road-driving images. IEEE Robot Autom Lett 5(4):5558\u20135565. https:\/\/doi.org\/10.1109\/LRA.2020.3007457","journal-title":"IEEE Robot Autom Lett"},{"key":"8235_CR45","unstructured":"Tao A, Sapra K, Catanzaro B (2020) Hierarchical multi-scale attention for semantic segmentation. arXiv preprint arXiv:2005.10821"},{"issue":"2","key":"8235_CR46","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian Z, Zhao H, Shu M, Yang Z, Li R, Jia J (2022) Prior guided feature enrichment network for few-shot segmentation. IEEE Trans Pattern Anal Mach Intell 44(2):1050\u20131065. https:\/\/doi.org\/10.1109\/TPAMI.2020.3013717","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8235_CR47","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"8235_CR48","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang X, Hu Y, Yang Y, Cao X, Zhen X (2020) Few-shot semantic segmentation with democratic attention networks. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIII 16, Springer, pp 730\u2013746","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"8235_CR49","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J (2019) Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9197\u20139206","DOI":"10.1109\/ICCV.2019.00929"},{"issue":"10","key":"8235_CR50","doi-asserted-by":"publisher","first-page":"5505","DOI":"10.1007\/s00521-019-04605-y","volume":"32","author":"P Wang","year":"2020","unstructured":"Wang P, Cheng J, Hao F, Wang L, Feng W (2020) Embedded adaptive cross-modulation neural network for few-shot learning. Neural Comput Appl 32(10):5505\u20135515","journal-title":"Neural Comput Appl"},{"key":"8235_CR51","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"8235_CR52","doi-asserted-by":"crossref","unstructured":"Wang Y, Chen X, Cao L, Huang W, Sun F, Wang Y (2022) Multimodal token fusion for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12186\u201312195","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"8235_CR53","doi-asserted-by":"crossref","unstructured":"Wang Y, Chen X, Cao L, Huang W, Sun F, Wang Y (2022) Multimodal token fusion for vision transformers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR52688.2022.01187"},{"issue":"1","key":"8235_CR54","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1109\/TITS.2020.3013234","volume":"23","author":"Y Xiao","year":"2022","unstructured":"Xiao Y, Codevilla F, Gurram A, Urfalioglu O, L\u00f3pez AM (2022) Multimodal end-to-end autonomous driving. IEEE Trans Intell Transp Syst 23(1):537\u2013547. https:\/\/doi.org\/10.1109\/TITS.2020.3013234","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"8235_CR55","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) Segformer: simple and efficient design for semantic segmentation with transformers. Adv Neural Inf Process Syst 34:12077\u201312090","journal-title":"Adv Neural Inf Process Syst"},{"key":"8235_CR56","doi-asserted-by":"crossref","unstructured":"Yang B, Liu C, Li B, Jiao J, Ye Q (2020) Prototype mixture models for few-shot semantic segmentation. In: European Conference on Computer Vision, Springer, pp 763\u2013778","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"8235_CR57","doi-asserted-by":"crossref","unstructured":"Zhang C, Lin G, Liu F, Guo J, Wu Q, Yao R (2019) Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9587\u20139595","DOI":"10.1109\/ICCV.2019.00968"},{"key":"8235_CR58","doi-asserted-by":"crossref","unstructured":"Zhang C, Lin G, Liu F, Yao R, Shen C (2019) Canet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5217\u20135226","DOI":"10.1109\/CVPR.2019.00536"},{"key":"8235_CR59","doi-asserted-by":"crossref","unstructured":"Zhang J, Yang K, Constantinescu A, Peng K, M\u00fcller K, Stiefelhagen R (2021) Trans4trans: efficient transformer for transparent object segmentation to help visually impaired people navigate in the real world. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1760\u20131770","DOI":"10.1109\/ICCVW54120.2021.00202"},{"issue":"9","key":"8235_CR60","doi-asserted-by":"publisher","first-page":"3855","DOI":"10.1109\/TCYB.2020.2992433","volume":"50","author":"X Zhang","year":"2020","unstructured":"Zhang X, Wei Y, Yang Y, Huang TS (2020) Sg-one: similarity guidance network for one-shot semantic segmentation. IEEE Trans Cybern 50(9):3855\u20133865","journal-title":"IEEE Trans Cybern"},{"key":"8235_CR61","doi-asserted-by":"publisher","unstructured":"Zhang Y, Sidib\u00e9 D, Morel O, Meriaudeau F (2021) Incorporating depth information into few-shot semantic segmentation. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp 3582\u20133588. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412921","DOI":"10.1109\/ICPR48806.2021.9412921"},{"key":"8235_CR62","doi-asserted-by":"crossref","unstructured":"Zhang Y, Sidib\u00e9 D, Morel O, Meriaudeau F (2021) Incorporating depth information into few-shot semantic segmentation. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp 3582\u20133588","DOI":"10.1109\/ICPR48806.2021.9412921"},{"key":"8235_CR63","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, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"8235_CR64","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H, Zhu X, Luo Z, Wang Y, Fu Y, Feng J, Xiang T, Torr PH, et\u00a0al (2021) Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6881\u20136890","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"8235_CR65","doi-asserted-by":"crossref","unstructured":"Zhu Z, Xu M, Bai S, Huang T, Bai X (2019) Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 593\u2013602","DOI":"10.1109\/ICCV.2019.00068"},{"key":"8235_CR66","doi-asserted-by":"publisher","unstructured":"Zhuang Z, Li R, Jia K, Wang Q, Li Y, Tan M (2021) Perception-aware multi-sensor fusion for 3d lidar semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 16260\u201316270. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01597","DOI":"10.1109\/ICCV48922.2021.01597"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08235-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08235-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08235-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T11:14:00Z","timestamp":1728990840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08235-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":66,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["8235"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08235-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]},"assertion":[{"value":"19 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2023","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 that they do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}