{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:37Z","timestamp":1766068117067,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601240"},{"type":"electronic","value":"9789819601257"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0125-7_21","type":"book-chapter","created":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T03:07:13Z","timestamp":1731812833000},"page":"256-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["S2A-Attention for\u00a0Multimodal 3D Semantic Segmentation Using LiDAR and\u00a0Cameras in\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Siyu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yifu","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yuquan","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Chao","family":"He","sequence":"additional","affiliation":[]},{"given":"Lihua","family":"Cai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Charles, R.Q., Su, H., Kaichun, M., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.16"},{"issue":"1","key":"21_CR4","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/TIV.2021.3085827","volume":"7","author":"TH Chen","year":"2021","unstructured":"Chen, T.H., Chang, T.S.: Rangeseg: range-aware real time segmentation of 3D lidar point clouds. IEEE Trans. Intell. Veh. 7(1), 93\u2013101 (2021)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"21_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016","author":"\u00d6 \u00c7i\u00e7ek","year":"2016","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424\u2013432. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Cortinhal, T., Tzelepis, G., Aksoy, E.: Salsanext: fast semantic segmentation of lidar point clouds for autonomous driving (2020)","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Song, S., Huang, G.: Agent attention: on the integration of softmax and linear attention. arXiv preprint arXiv:2312.08874 (2023)","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Hu, Q., et al.: Randla-net: efficient semantic segmentation of large-scale point clouds. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Krispel, G., Opitz, M., Waltner, G., Possegger, H., Bischof, H.: Fuseseg: Lidar point cloud segmentation fusing multi-modal data. Cornell University - arXiv (2019)","DOI":"10.1109\/WACV45572.2020.9093584"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., Dai, H., Han, H., Ding, Y.: MSeg3D: multi-modal 3D semantic segmentation for autonomous driving (2023)","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Uniseg: a unified multi-modal lidar segmentation network and the openpcseg codebase. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21662\u201321673 (2023)","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet++: fast and accurate lidar semantic segmentation. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4213\u20134220. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"21_CR14","first-page":"14200","volume":"34","author":"A Nagrani","year":"2021","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. Adv. Neural. Inf. Process. Syst. 34, 14200\u201314213 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118815","volume":"212","author":"J Park","year":"2023","unstructured":"Park, J., Kim, C., Kim, S., Jo, K.: Pcscnet: fast 3D semantic segmentation of lidar point cloud for autonomous car using point convolution and sparse convolution network. Expert Syst. Appl. 212, 118815 (2023)","journal-title":"Expert Syst. Appl."},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"21_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"21_CR19","unstructured":"Wang, Y., Shi, T., Yun, P., Tai, L., Liu, M.: Pointseg: real-time semantic segmentation based on 3D lidar point cloud. arXiv preprint arXiv:1807.06288 (2018)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Xu, C., et al.: SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation, pp. 1\u201319 (2020)","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-Contextual Representations for Semantic Segmentation, pp. 173\u2013190 (2020)","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zermas, D., Izzat, I., Papanikolopoulos, N.: Fast segmentation of 3D point clouds: a paradigm on lidar data for autonomous vehicle applications. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5067\u20135073. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989591"},{"key":"21_CR25","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)","DOI":"10.1109\/CVPR.2017.660"},{"key":"21_CR26","unstructured":"Zhou, H., et al.: Cylinder3d: an effective 3D framework for driving-scene lidar semantic segmentation. arXiv, Computer Vision and Pattern Recognition (2020)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0125-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T04:30:21Z","timestamp":1731817821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0125-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601240","9789819601257"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0125-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}