{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:30:26Z","timestamp":1778693426444,"version":"3.51.4"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695248","type":"print"},{"value":"9783030695255","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69525-5_31","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T16:21:16Z","timestamp":1614356476000},"page":"519-536","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["RGB-D Co-attention Network for Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoliang","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"31_CR2","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, 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Qi, L., Jiang, L., Liu, S., Shen, X., Jia, J.: Amodal instance segmentation with kins dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3014\u20133023 (2019)","DOI":"10.1109\/CVPR.2019.00313"},{"key":"31_CR4","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"31_CR5","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, 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925\u20131934 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"31_CR7","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4353\u20134361 (2017)","DOI":"10.1109\/CVPR.2017.189"},{"key":"31_CR8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"31_CR9","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":"31_CR10","doi-asserted-by":"crossref","unstructured":"He, Y., Chiu, W.C., Keuper, M., Fritz, M.: RGBD semantic segmentation using spatio-temporal data-driven pooling. arXiv preprint arXiv:1604.02388 (2016)","DOI":"10.1109\/CVPR.2017.757"},{"key":"31_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-319-46454-1_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wang","year":"2016","unstructured":"Wang, J., Wang, Z., Tao, D., See, S., Wang, G.: Learning common and specific features for RGB-D semantic segmentation with deconvolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 664\u2013679. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_40"},{"key":"31_CR12","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/LRA.2016.2532927","volume":"2","author":"F Husain","year":"2016","unstructured":"Husain, F., Schulz, H., Dellen, B., Torras, C., Behnke, S.: Combining semantic and geometric features for object class segmentation of indoor scenes. IEEE Robot. Autom. Lett. 2, 49\u201355 (2016)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"31_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":"31_CR14","unstructured":"Jiang, J., Zheng, L., Luo, F., Zhang, Z.: RedNet: residual encoder-decoder network for indoor RGB-D semantic segmentation. arXiv preprint arXiv:1806.01054 (2018)"},{"key":"31_CR15","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":"31_CR16","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3029\u20133037 (2017)","DOI":"10.1109\/CVPR.2017.161"},{"key":"31_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-01252-6_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Wang","year":"2018","unstructured":"Wang, W., Neumann, U.: Depth-aware CNN for RGB-D segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 144\u2013161. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_9"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Lin, D., Chen, G., Cohen-Or, D., Heng, P.A., Huang, H.: Cascaded feature network for semantic segmentation of RGB-D images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1311\u20131319 (2017)","DOI":"10.1109\/ICCV.2017.147"},{"issue":"3","key":"31_CR19","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1109\/TCYB.2018.2885062","volume":"50","author":"D Lin","year":"2018","unstructured":"Lin, D., Zhang, R., Ji, Y., Li, P., Huang, H.: SCN: switchable context network for semantic segmentation of RGB-D images. IEEE Trans. Cybern. 50(3), 1120\u20131131 (2018)","journal-title":"IEEE Trans. Cybern."},{"key":"31_CR20","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. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"31_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"31_CR22","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":"31_CR23","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"31_CR24","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"31_CR25","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"31_CR27","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. arXiv preprint arXiv:1502.04623 (2015)"},{"key":"31_CR28","unstructured":"Chen, X., Mishra, N., Rohaninejad, M., Abbeel, P.: Pixelsnail: an improved autoregressive generative model. arXiv preprint arXiv:1712.09763 (2017)"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. arXiv preprint arXiv:1601.06733 (2016)","DOI":"10.18653\/v1\/D16-1053"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Parikh, A.P., T\u00e4ckstr\u00f6m, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. arXiv preprint arXiv:1606.01933 (2016)","DOI":"10.18653\/v1\/D16-1244"},{"key":"31_CR31","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1109\/TMM.2015.2476660","volume":"17","author":"J Tang","year":"2015","unstructured":"Tang, J., Jin, L., Li, Z., Gao, S.: RGB-D object recognition via incorporating latent data structure and prior knowledge. IEEE Trans. Multimedia 17, 1899\u20131908 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Van Den Hengel, A., Reid, I.: Efficient piecewise training of deep structured models for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3194\u20133203 (2016)","DOI":"10.1109\/CVPR.2016.348"},{"key":"31_CR33","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Shen, T., Zhou, T., Long, G., Jiang, J., Pan, S., Zhang, C.: DISAN: directional self-attention network for RNN\/CNN-free language understanding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11941"},{"key":"31_CR35","unstructured":"Qi, L., Liu, S., Shi, J., Jia, J.: Sequential context encoding for duplicate removal. In: Advances in Neural Information Processing Systems, pp. 2049\u20132058 (2018)"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, J., Xie, L., Zheng, L.: Attention-based pyramid aggregation network for visual place recognition. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 99\u2013107 (2018)","DOI":"10.1145\/3240508.3240525"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Song, X., Zhang, S., Hua, Y., Jiang, S.: Aberrance-aware gradient-sensitive attentions for scene recognition with RGB-D videos. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1286\u20131294 (2019)","DOI":"10.1145\/3343031.3351051"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Li, W., Tao, X., Guo, T., Qi, L., Lu, J., Jia, J.: MUCAN: multi-correspondence aggregation network for video super-resolution. arXiv preprint arXiv:2007.11803 (2020)","DOI":"10.1007\/978-3-030-58607-2_20"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNET: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"31_CR42","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: ABD-NET: attentive but diverse person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8351\u20138361 (2019)","DOI":"10.1109\/ICCV.2019.00844"},{"key":"31_CR46","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, pp. 289\u2013297 (2016)"},{"key":"31_CR47","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen, D.K., Okatani, T.: Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6087\u20136096 (2018)","DOI":"10.1109\/CVPR.2018.00637"},{"key":"31_CR49","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"31_CR50","unstructured":"Ren, X., Bo, L., Fox, D.: RGB-(D) scene labeling: features and algorithms. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2759\u20132766. IEEE (2012)"},{"key":"31_CR51","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 564\u2013571 (2013)","DOI":"10.1109\/CVPR.2013.79"},{"key":"31_CR52","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":"31_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"31_CR54","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"31_CR55","doi-asserted-by":"crossref","unstructured":"Deng, Z., Todorovic, S., Jan Latecki, L.: Semantic segmentation of RGBD images with mutex constraints. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1733\u20131741 (2015)","DOI":"10.1109\/ICCV.2015.202"},{"key":"31_CR56","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"31_CR57","doi-asserted-by":"crossref","unstructured":"He, Y., Chiu, W.C., Keuper, M., Fritz, M.: STD2P: RGBD semantic segmentation using spatio-temporal data-driven pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4837\u20134846 (2017)","DOI":"10.1109\/CVPR.2017.757"},{"key":"31_CR58","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3D graph neural networks for RGBD semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5199\u20135208 (2017)","DOI":"10.1109\/ICCV.2017.556"},{"key":"31_CR59","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhang, Z., Huang, Y., Zheng, L.: Incorporating depth into both CNN and CRF for indoor semantic segmentation. In: 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp. 525\u2013530. IEEE (2017)","DOI":"10.1109\/ICSESS.2017.8342970"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69525-5_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T04:34:32Z","timestamp":1671424472000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69525-5_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695248","9783030695255"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69525-5_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","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":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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","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":"3","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":"The conference was held virtually.","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)"}}]}}