{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T17:27:59Z","timestamp":1787246879576,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540969","type":"print"},{"value":"9789819540976","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4097-6_33","type":"book-chapter","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T05:00:55Z","timestamp":1763010055000},"page":"488-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["JP-Occ: 3D Occupancy Prediction with\u00a0View Transformation Based on\u00a0Joint Projection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0901-7518","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3273-1844","authenticated-orcid":false,"given":"Guixing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3114-2784","authenticated-orcid":false,"given":"Zuotao","family":"Ning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2784-1415","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7656-4382","authenticated-orcid":false,"given":"Biao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5871-6572","authenticated-orcid":false,"given":"Shuai","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5183-0251","authenticated-orcid":false,"given":"Liuyu","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"33_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European Conference on Computer Vision, pp. 1\u201318. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Tian, X., Jiang, T., Yun, L., Wang, Y., Wang, Y., Zhao, H.: Occ3d: a large-scale 3d occupancy prediction benchmark for autonomous driving. arXiv preprint arXiv:2304.14365 (2023)","DOI":"10.52202\/075280-2809"},{"key":"33_CR4","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: high-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"33_CR5","unstructured":"Zhang, Y., et al.: Beverse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)"},{"key":"33_CR6","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"33_CR8","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., De\u00a0Charette, R.: Monoscene: monocular 3d semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3991\u20134001 (2022)","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"33_CR10","unstructured":"Miao, R., et al.: Occdepth: a depth-aware method for 3d semantic scene completion. arXiv preprint arXiv:2302.13540 (2023)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Voxformer: sparse voxel transformer for camera-based 3d semantic scene completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9087\u20139098 (2023)","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: Not all voxels are equal: Hardness-aware semantic scene completion with self-distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14792\u201314801 (2024)","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., Du, D.: Occformer: dual-path transformer for vision-based 3d semantic occupancy prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9433\u20139443 (2023)","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Hou, J., et al.: Fastocc: accelerating 3d occupancy prediction by fusing the 2d bird\u2019s-eye view and perspective view. arXiv preprint arXiv:2403.02710 (2024)","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"33_CR15","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Fast-bev: a fast and strong bird\u2019s-eye view perception baseline. IEEE Trans. Patt. Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., Lu, J.: Surroundocc: multi-camera 3d occupancy prediction for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21729\u201321740 (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"33_CR20","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9268\u20139277 (2019)","DOI":"10.1109\/CVPR.2019.00949"},{"key":"33_CR22","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":"33_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., Lu, J.: Tri-perspective view for vision-based 3d semantic occupancy prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9223\u20139232 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4097-6_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T16:53:05Z","timestamp":1787244785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4097-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"ISBN":["9789819540969","9789819540976"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4097-6_33","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"14 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}