{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:10:41Z","timestamp":1767323441967,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557363","type":"print"},{"value":"9789819557370","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-5737-0_9","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:08:28Z","timestamp":1767323308000},"page":"119-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SliceSemOcc: Vertical Slice\u2013Based Multimodal 3D Semantic Occupancy Representation"],"prefix":"10.1007","author":[{"given":"Han","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ningzhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaquan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Bai, X., et al.: TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers. In: CVPR, pp. 1080\u20131089 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00116","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The Lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: CVPR, pp. 4413\u20134421 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00464","DOI":"10.1109\/CVPR.2018.00464"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11618\u201311628 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01164","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Cao, A., de\u00a0Charette, R.: MonoScene: monocular 3D semantic scene completion. In: CVPR, pp. 3981\u20133991 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00396","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Qian, C., Zeng, G., Li, H.: 3D sketch-aware semantic scene completion via semi-supervised structure prior. In: CVPR, pp. 4193\u20134202 (2020)","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: CVPR, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, T., Wang, Y., Wang, Y., Zhao, H.: FUTR3D: a unified sensor fusion framework for 3D detection. In: CVPR, pp. 172\u2013181 (2023)","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Chi, X., et al.: BEV-SAN: accurate BEV 3D object detection via slice attention networks. In: CVPR, pp. 17461\u201317470 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01675","DOI":"10.1109\/CVPR52729.2023.01675"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. CoRR abs\/2203.17054 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2203.17054","DOI":"10.48550\/ARXIV.2203.17054"},{"key":"9_CR11","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"9_CR12","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: CVPR, pp. 9223\u20139232 (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Jiang, Y., et al.: PolarFormer: multi-camera 3D object detection with polar transformer. In: AAAI (2023). https:\/\/doi.org\/10.1609\/aaai.v37i1.25185","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Khurana, T., Hu, P., Held, D., Ramanan, D.: Point cloud forecasting as a proxy for 4D occupancy forecasting. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: CVPR, pp. 3348\u20133356 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00341","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"9_CR17","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV, pp. 1\u201318 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: ECCV, pp. 641\u2013656 (2018)","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"9_CR19","unstructured":"Liang, T., et al.: BEVFusion: a simple and robust LiDAR-camera fusion framework. NeurIPS 35, 10421\u201310434 (2022)"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR, pp. 936\u2013944. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2999\u20133007. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: LiDAR-based 4D occupancy completion and forecasting. arXiv preprint arXiv:2310.11239 (2023)","DOI":"10.1109\/IROS58592.2024.10801302"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: ICRA, pp. 2774\u20132781 (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160968","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Ming, Z., Berrio, J.S., Shan, M., Worrall, S.: InverseMatrixVT3D: an efficient projection matrix-based approach for 3D occupancy prediction. arXiv preprint arXiv:2401.12422 (2024)","DOI":"10.1109\/IROS58592.2024.10802434"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Ming, Z., Berrio, J.S., Shan, M., Worrall, S.: OccFusion: multi-sensor fusion framework for 3D semantic occupancy prediction. In: TIV, pp. 1\u201313 (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3453293","DOI":"10.1109\/TIV.2024.3453293"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Nabati, R., Qi, H.: CenterFusion: center-based radar and camera fusion for 3D object detection. In: ICCV, pp. 1527\u20131536 (2021)","DOI":"10.1109\/IVWorkshops54471.2021.9669223"},{"issue":"6","key":"9_CR27","doi-asserted-by":"publisher","first-page":"5687","DOI":"10.1109\/LRA.2024.3396092","volume":"9","author":"J Pan","year":"2024","unstructured":"Pan, J., Wang, Z., Wang, L.: Co-occ: coupling explicit feature fusion with volume rendering regularization for multi-modal 3D semantic occupancy prediction. IEEE Robotics Autom. Lett. 9(6), 5687\u20135694 (2024). https:\/\/doi.org\/10.1109\/LRA.2024.3396092","journal-title":"IEEE Robotics Autom. Lett."},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Pan, M., et al.: RenderOcc: vision-centric 3D occupancy prediction with 2D rendering supervision. CoRR abs\/2309.09502 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2309.09502","DOI":"10.48550\/ARXIV.2309.09502"},{"key":"9_CR29","doi-asserted-by":"publisher","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: ECCV, pp. 194\u2013210 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds. In: ICCV, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum PointNets for 3D object detection from RGB-D data. In: CVPR, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"9_CR32","doi-asserted-by":"publisher","unstructured":"Rold\u00e3o, L., de\u00a0Charette, R., Verroust-Blondet, A.: LMSCNet: lightweight multiscale 3D semantic completion. In: 3DV, pp. 111\u2013119 (2020). https:\/\/doi.org\/10.1109\/3DV50981.2020.00021","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: CVPR, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"9_CR34","doi-asserted-by":"publisher","unstructured":"Wang, C., Ma, C., Zhu, M., Yang, X.: PointAugmenting: cross-modal augmentation for 3D object detection. In: CVPR, pp. 11789\u201311798 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01162","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"9_CR35","doi-asserted-by":"publisher","unstructured":"Wang, X.,et al.: OpenOccupancy: a large scale benchmark for surrounding semantic occupancy perception. In: ICCV, pp. 17804\u201317813 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01636","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"9_CR36","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":"9_CR37","doi-asserted-by":"publisher","unstructured":"Wang, Z., Jia, K.: Frustum ConvNet: sliding frustums to aggregate local point-wise features for amodal 3D object detection. In: IROS, pp. 1742\u20131749 (2019). https:\/\/doi.org\/10.1109\/IROS40897.2019.8968513","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"9_CR38","doi-asserted-by":"publisher","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., Lu, J.: SurroundOcc: multi-camera 3D occupancy prediction for autonomous driving. In: ICCV, pp. 21672\u201321683 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01986","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Yan, X., Gao, J., Li, J., Zhang, R., Li, Z., Huang, R., Cui, S.: Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion. In: AAAI. vol. 35, pp. 3101\u20133109 (2021)","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"9_CR40","doi-asserted-by":"publisher","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10), (2018). https:\/\/doi.org\/10.3390\/S18103337","DOI":"10.3390\/S18103337"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: CVPR, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: IPOD: intensive point-based object detector for point cloud. arXiv preprint arXiv:1812.05276 (2018)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"9_CR43","unstructured":"Ye, M., Wan, R., Xu, S., Cao, T., Chen, Q.: DRINet++: efficient voxel-as-point point cloud segmentation. arXiv preprint arXiv:2111.08318 (2021)"},{"key":"9_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, J., Ding, Y., Liu, Z.: OccLoff: learning optimized feature fusion for 3D occupancy prediction. In: WACV, pp. 3096\u20133106 (2025). https:\/\/doi.org\/10.1109\/WACV61041.2025.00306","DOI":"10.1109\/WACV61041.2025.00306"},{"key":"9_CR45","unstructured":"Zhou, H., et al.: Cylinder3D: an effective 3D framework for driving-scene LiDAR semantic segmentation. arXiv preprint arXiv:2008.01550 (2020)"},{"key":"9_CR46","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: CVPR, pp. 4490\u20134499 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5737-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:08:31Z","timestamp":1767323311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5737-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557363","9789819557370"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5737-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}