{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:51:45Z","timestamp":1782406305456,"version":"3.54.5"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031262920","type":"print"},{"value":"9783031262937","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26293-7_23","type":"book-chapter","created":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T20:02:47Z","timestamp":1678478567000},"page":"378-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Application of\u00a0Multi-modal Fusion Attention Mechanism in\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0545-7985","authenticated-orcid":false,"given":"Yunlong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4192-554X","authenticated-orcid":false,"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9306-688X","authenticated-orcid":false,"given":"Hiroshi","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,11]]},"reference":[{"key":"23_CR1","unstructured":"Thoma, M.: A survey of semantic segmentation. arXiv preprint arXiv:1602.06541 (2016)"},{"key":"23_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417","volume":"169","author":"X Yuan","year":"2021","unstructured":"Yuan, X., Shi, J., Gu, L.: A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst. Appl. 169, 114417 (2021)","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"23_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.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA. pp. 413\u2013420. IEEE Computer Society (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Silberman, N., Fergus, R.: Indoor scene segmentation using a structured light sensor. In: IEEE International Conference on Computer Vision Workshops, ICCV 2011 Workshops, Barcelona, Spain, November 6\u201313, 2011, pp. 601\u2013608. IEEE Computer Society (2011)","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Webb, J., Ashley, J.: Depth Image Processing, pp. 49\u201383. Apress, Berkeley (2012)","DOI":"10.1007\/978-1-4302-4105-8_3"},{"issue":"3","key":"23_CR8","doi-asserted-by":"publisher","first-page":"4313","DOI":"10.1007\/s11042-016-3374-6","volume":"76","author":"Z Cai","year":"2017","unstructured":"Cai, Z., Han, J., Liu, L., Shao, L.: RGB-D datasets using microsoft kinect or similar sensors: a survey. Multim. Tools Appl. 76(3), 4313\u20134355 (2017)","journal-title":"Multim. Tools Appl."},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Firman, M.: RGBD datasets: Past, present and future. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2016, Las Vegas, NV, USA, June 26 - July 1, 2016. pp. 661\u2013673. IEEE Computer Society (2016)","DOI":"10.1109\/CVPRW.2016.88"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Funkhouser, T.A.: Deep depth completion of a single RGB-D image. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322, 2018. pp. 175\u2013185. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00026"},{"key":"23_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D Images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, June 23\u201328, 2013. pp. 564\u2013571. IEEE Computer Society (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"23_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-54181-5_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"C Hazirbas","year":"2017","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213\u2013228. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14"},{"key":"23_CR14","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. In: Bengio, Y., LeCun, Y. (eds.) 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2\u20134, 2013, Conference Track Proceedings (2013)"},{"issue":"11","key":"23_CR15","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"23_CR16","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015. pp. 3431\u20133440. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"23_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Bartlett, P.L., Pereira, F.C.N., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) 26th Annual Conference on Neural Information Processing Systems 2012. 3\u20136 December 2012, Lake Tahoe, Nevada, United States, pp. 1106\u20131114 (2012)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015. pp. 1\u20139. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"23_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016. pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR22","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322, 2018, pp. 6848\u20136856. Computer Vision Foundation\/IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"23_CR24","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6\u201311 July 2015. JMLR Workshop and Conference Proceedings, vol. 37, pp. 448\u2013456. JMLR.org (2015)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016. pp. 2818\u20132826. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Singh, S., Markovitch, S. (eds.) Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4\u20139 February 2017, San Francisco, California, USA, pp. 4278\u20134284. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017, pp. 2261\u20132269. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"23_CR28","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA. Proceedings of Machine Learning Research, vol. 97, pp. 6105\u20136114. PMLR (2019)"},{"key":"23_CR29","unstructured":"Tan, M., Le, Q.V.: Efficientnetv2: Smaller models and faster training. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 10096\u201310106. PMLR (2021)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Cai, R., Li, Z., Zhao, X., Huang, K.: Locality-sensitive deconvolution networks with gated fusion for RGB-D indoor semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017. pp. 1475\u20131483. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.161"},{"key":"23_CR31","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2\u20134, 2016, Conference Track Proceedings (2016)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large kernel matters - improve semantic segmentation by global convolutional network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017. pp. 1743\u20131751. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.189"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017. pp. 1800\u20131807. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017. pp. 6230\u20136239. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"23_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K He","year":"2014","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., Yang, K.: Denseaspp for semantic segmentation in street scenes. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322, 2018. pp. 3684\u20133692. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"23_CR37","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"issue":"4","key":"23_CR38","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen, L., 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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR39","unstructured":"Chen, L., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"23_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Choi, M.J., Lim, J.J., Torralba, A., Willsky, A.S.: Exploiting hierarchical context on a large database of object categories. In: The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13\u201318 June 2010. pp. 129\u2013136. IEEE Computer Society (2010)","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23\u201328 June 2014. pp. 891\u2013898. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"23_CR43","unstructured":"Liu, W., Rabinovich, A., Berg, A.C.: Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Hung, W., et al.: Scene parsing with global context embedding. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017. pp. 2650\u20132658. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.287"},{"key":"23_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-01261-8_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yu","year":"2018","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334\u2013349. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_20"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Adaptive context network for scene parsing. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. pp. 6747\u20136756. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00685"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18\u201322 June 2018. pp. 7151\u20137160. Computer Vision Foundation\/IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"issue":"2","key":"23_CR48","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2019","unstructured":"Baltrusaitis, T., Ahuja, C., Morency, L.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7\u20138","key":"23_CR49","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1007\/s11042-019-7684-3","volume":"79","author":"F Fooladgar","year":"2020","unstructured":"Fooladgar, F., Kasaei, S.: A survey on indoor RGB-D semantic segmentation: from hand-crafted features to deep convolutional neural networks. Multim. Tools Appl. 79(7\u20138), 4499\u20134524 (2020)","journal-title":"Multim. Tools Appl."},{"issue":"2","key":"23_CR50","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1016\/j.neuroimage.2010.09.018","volume":"54","author":"P Coup\u00e9","year":"2011","unstructured":"Coup\u00e9, P., Manj\u00f3n, J.V., Fonov, V.S., Pruessner, J.C., Robles, M., Collins, D.L.: Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation. Neuroimage 54(2), 940\u2013954 (2011)","journal-title":"Neuroimage"},{"key":"23_CR51","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.image.2017.04.007","volume":"56","author":"M Wang","year":"2017","unstructured":"Wang, M., Liu, X., Gao, Y., Ma, X., Soomro, N.Q.: Superpixel segmentation: a benchmark. Signal Process. Image Commun. 56, 28\u201339 (2017)","journal-title":"Signal Process. Image Commun."},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Kaganami, H.G., Zou, B.: Region-based segmentation versus edge detection. In: Pan, J., Chen, Y., Jain, L.C. (eds.) Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2009), Kyoto, Japan, 12\u201314 September 2009, pp. 1217\u20131221. IEEE Computer Society (2009)","DOI":"10.1109\/IIH-MSP.2009.13"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015. pp. 1529\u20131537. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Banica, D., Sminchisescu, C.: Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in RGB-D images. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June 2015. pp. 3517\u20133526. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298974"},{"key":"23_CR55","unstructured":"Bo, L., Ren, X., Fox, D.: Kernel descriptors for visual recognition. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held, 6\u20139 December 2010, Vancouver, British Columbia, Canada. pp. 244\u2013252. Curran Associates, Inc. (2010)"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3d semantic mapping of indoor scenes from RGB-D images. In: 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, May 31 - June 7, 2014. pp. 2631\u20132638. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"issue":"4\u20135","key":"23_CR57","first-page":"582","volume":"34","author":"CDC Lerma","year":"2015","unstructured":"Lerma, C.D.C., Koseck\u00e1, J.: Semantic parsing for priming object detection in indoors RGB-D scenes. Int. J. Robotics Res. 34(4\u20135), 582\u2013597 (2015)","journal-title":"Int. J. Robotics Res."},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: Features and algorithms. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16\u201321 June 2012. pp. 2759\u20132766. IEEE Computer Society (2012)","DOI":"10.1109\/CVPR.2012.6247999"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"M\u00fcller, A.C., Behnke, S.: Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images. In: 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, May 31 - June 7, 2014. pp. 6232\u20136237. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907778"},{"key":"23_CR60","unstructured":"Wang, S., Lokhande, V.S., Singh, M., K\u00f6rding, K.P., Yarkony, J.: End-to-end training of CNN-CRF via differentiable dual-decomposition. arXiv preprint arXiv:1912.02937 (2019)"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Leutenegger, S., Davison, A.J.: Scenenet RGB-D: can 5m synthetic images beat generic ImageNet pre-training on indoor segmentation? In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017. pp. 2697\u20132706. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.292"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Lee, S., Park, S., Hong, K.: Rdfnet: RGB-D multi-level residual feature fusion for indoor semantic segmentation. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017. pp. 4990\u20134999. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.533"},{"key":"23_CR63","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.D.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017. pp. 5168\u20135177. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"23_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-319-46475-6_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Li","year":"2016","unstructured":"Li, Z., Gan, Y., Liang, X., Yu, Y., Cheng, H., Lin, L.: LSTM-CF: unifying context modeling and fusion with LSTMs for RGB-d scene labeling. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 541\u2013557. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_34"},{"key":"23_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-030-58548-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Vandenhende","year":"2020","unstructured":"Vandenhende, S., Georgoulis, S., Van Gool, L.: MTI-Net: multi-scale task interaction networks for multi-task learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 527\u2013543. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_31"},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Shi, H., Li, H., Wu, Q., Song, Z.: Scene parsing via integrated classification model and variance-based regularization. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019. pp. 5307\u20135316. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00545"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Seichter, D., K\u00f6hler, M., Lewandowski, B., Wengefeld, T., Gross, H.: Efficient RGB-D semantic segmentation for indoor scene analysis. In: IEEE International Conference on Robotics and Automation, ICRA 2021, Xi\u2019an, China, May 30 - June 5, 2021. pp. 13525\u201313531. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Cao, J., Leng, H., Lischinski, D., Cohen-Or, D., Tu, C., Li, Y.: Shapeconv: shape-aware convolutional layer for indoor RGB-D semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021. pp. 7068\u20137077. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"23_CR69","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision - ECCV 2018\u201315th European Conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part VII. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16\u201320 June 2019. pp. 510\u2013519. Computer Vision Foundation\/IEEE (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18\u201322 June 2018. pp. 7132\u20137141. Computer Vision Foundation\/IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"23_CR72","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108468","volume":"124","author":"H Zhou","year":"2022","unstructured":"Zhou, H., Qi, L., Huang, H., Yang, X., Wan, Z., Wen, X.: Canet: co-attention network for RGB-D semantic segmentation. Pattern Recognit. 124, 108468 (2022)","journal-title":"Pattern Recognit."},{"key":"23_CR73","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/LSP.2021.3066071","volume":"28","author":"G Zhang","year":"2021","unstructured":"Zhang, G., Xue, J., Xie, P., Yang, S., Wang, G.: Non-local aggregation for RGB-D semantic segmentation. IEEE Signal Process. Lett. 28, 658\u2013662 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"23_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-58621-8_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 561\u2013577. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_33"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26293-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T04:47:45Z","timestamp":1729054065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26293-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262920","9783031262937"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26293-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}