{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T10:36:29Z","timestamp":1769510189445,"version":"3.49.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031262838","type":"print"},{"value":"9783031262845","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\/978-3-031-26284-5_16","type":"book-chapter","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:02:59Z","timestamp":1677052979000},"page":"256-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RGB Road Scene Material Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5446-5618","authenticated-orcid":false,"given":"Sudong","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3917-9012","authenticated-orcid":false,"given":"Ryosuke","family":"Wakaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3204-8696","authenticated-orcid":false,"given":"Shohei","family":"Nobuhara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3534-3447","authenticated-orcid":false,"given":"Ko","family":"Nishino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Bell, S., Upchurch, P., Snavely, N., Bala, K.: Material recognition in the wild with the materials in context database. In: Proceedings of the CVPR, pp. 3479\u20133487 (2015)","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Brown, M., et al.: Large-scale public LiDAR and satellite image data set for urban semantic labeling. In: Laser Radar Technology and Applications XXIII, vol. 10636 (2018)","DOI":"10.1117\/12.2304403"},{"issue":"4","key":"16_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","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. TPAMI 40(4), 834\u2013848 (2018)","journal-title":"TPAMI"},{"key":"16_CR4","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the CVPR, pp. 3640\u20133649 (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"16_CR6","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":"16_CR7","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, J.T., Choo, J.: Cars can\u2019t fly up in the sky: improving urban-scene segmentation via height-driven attention networks. In: Proceedings of the CVPR, pp. 9373\u20139383 (2020)","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Demir, I., et al.: DeepGlobe 2018: a challenge to parse the earth through satellite images. In: Proceedings of the CVPR Workshop, pp. 172\u201317209 (2018)","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"16_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the ICLR (2021)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of the CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in ConvNet\u2019s clothing for faster inference. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"16_CR14","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. In: Proceedings of the NeurIPS (2021)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR16","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: Proceedings of the ICCV, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"16_CR19","unstructured":"Kraehenbuehl, P., Koltun, V.: Parameter learning and convergent inference for dense random fields. In: Proceedings of the ICML, pp. 513\u2013521 (2013)"},{"key":"16_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the NeurIPS, pp. 1097\u20131105 (2012)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the CVPR, pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wakaki, R., Nobuhara, S., Nishino, K.: Multimodal material segmentation. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01918"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bulo, S.R., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: Proceedings of the ICCV, pp. 5000\u20135009 (2017)","DOI":"10.1109\/ICCV.2017.534"},{"key":"16_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_11"},{"key":"16_CR26","unstructured":"Purri, M., et al.: Material segmentation of multi-view satellite imagery. arXiv preprint arXiv:1904.08537 (2019)"},{"key":"16_CR27","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. In: Proceedings of the NeurIPS, vol. 32, pp. 68\u201380 (2019)"},{"key":"16_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/978-3-030-01234-2_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"FA Reda","year":"2018","unstructured":"Reda, F.A., et al.: SDC-Net: video prediction using spatially-displaced convolution. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 747\u2013763. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_44"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Schwartz, G., Nishino, K.: Visual material traits: recognizing per-pixel material context. In: IEEE Color and Photometry in Computer Vision Workshop (2013)","DOI":"10.1109\/ICCVW.2013.121"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Schwartz, G., Nishino, K.: Automatically discovering local visual material attributes. In: Proceedings of the CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298979"},{"key":"16_CR31","unstructured":"Schwartz, G., Nishino, K.: Integrating local material recognition with large-scale perceptual attribute discovery. arXiv preprint arXiv:1604.01345 (2016)"},{"key":"16_CR32","unstructured":"Schwartz, G., Nishino, K.: Material recognition from local appearance in global context. arXiv preprint arXiv:1611.09394 (2016)"},{"issue":"8","key":"16_CR33","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1109\/TPAMI.2019.2907850","volume":"42","author":"G Schwartz","year":"2020","unstructured":"Schwartz, G., Nishino, K.: Recognizing material properties from images. TPAMI 42(8), 1981\u20131995 (2020)","journal-title":"TPAMI"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"16_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the NeurIPS, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"16_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing convolutions to vision transformers. In: Proceedings of the ICCV, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"16_CR40","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Proceedings of the NeurIPS (2021)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Xue, J., Purri, M., Dana, K.: Angular luminance for material segmentation. In: IGARSS 2020\u20132020 IEEE International Geoscience and Remote Sensing Symposium (2020)","DOI":"10.1109\/IGARSS39084.2020.9324625"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Xue, J., Zhang, H., Dana, K., Nishino, K.: Differential angular imaging for material recognition. In: Proceedings of the CVPR, pp. 6940\u20136949 (2017)","DOI":"10.1109\/CVPR.2017.734"},{"key":"16_CR43","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1109\/TPAMI.2020.3025121","volume":"44","author":"J Xue","year":"2020","unstructured":"Xue, J., Zhang, H., Nishino, K., Dana, K.: Differential viewpoints for ground terrain material recognition. TPAMI 44, 1205\u20131218 (2020)","journal-title":"TPAMI"},{"key":"16_CR44","unstructured":"Yang, T.J., et al.: DeeperLab: single-shot image parser. arXiv preprint arXiv:1902.05093 (2019)"},{"key":"16_CR45","unstructured":"Zhang, H., Goodfellow, I.J., Metaxas, D.N., Odena, A.: Self-attention generative adversarial networks. In: Proceedings of the ICML, pp. 7354\u20137363 (2018)"},{"key":"16_CR46","unstructured":"Zhang, H., Dana, K., Nishino, K.: Reflectance hashing for material recognition. In: Proceedings of the CVPR, pp. 3071\u20133080 (2015)"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: Proceedings of the CVPR, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xue, J., Dana, K.: Deep TEN: texture encoding network. In: Proceedings of the CVPR, pp. 2896\u20132905 (2017)","DOI":"10.1109\/CVPR.2017.309"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, H., Wang, C., Xie, J.: Co-occurrent features in semantic segmentation. In: Proceedings of the CVPR, pp. 548\u2013557 (2019)","DOI":"10.1109\/CVPR.2019.00064"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, J., Jampani, V., Pi, Z., Liu, Q., Yang, M.H.: Decoupled dynamic filter networks. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00658"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: Proceedings of the CVPR, pp. 8856\u20138865 (2019)","DOI":"10.1109\/CVPR.2019.00906"}],"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\/978-3-031-26284-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:12:35Z","timestamp":1677053555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26284-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262838","9783031262845"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26284-5_16","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":"23 February 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)"}}]}}