{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:29:24Z","timestamp":1783034964597,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543779","type":"print"},{"value":"9789819543786","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4378-6_4","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T15:52:36Z","timestamp":1762789956000},"page":"48-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Collaborative Perceiver: Elevating Vision-Based 3D Object Detection via\u00a0Local Density-Aware Dense Spatial Occupancy"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4448-2809","authenticated-orcid":false,"given":"Jicheng","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9668-4974","authenticated-orcid":false,"given":"Manh","family":"Nguyen-Duc","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3706-5823","authenticated-orcid":false,"given":"Qian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1839-0372","authenticated-orcid":false,"given":"Manfred","family":"Hauswirth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2480-9261","authenticated-orcid":false,"given":"Danh","family":"Le-Phuoc","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, S.M., Chew, C.M.: Density-based clustering for 3d object detection in point clouds. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01062"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., et\u00a0al.: nuscenes: A multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Chi, X., Liu, J., Lu, M., et\u00a0al.: Bev-san: Accurate bev 3d object detection via slice attention networks. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01675"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Feng, C., Jie, Z., Zhong, Y., et\u00a0al.: Aedet: Azimuth-invariant multi-view 3d object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Hauer, F., Schmidt, T., Holzm\u00fcller, B., Pretschner, A.: Did we test all scenarios for automated and autonomous driving systems? In: ITSC (2019)","DOI":"10.1109\/ITSC.2019.8917326"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"4_CR8","unstructured":"Huang, J., Huang, G.: Bevdet4d: Exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"4_CR9","unstructured":"Huang, J., Huang, G., Zhu, Z., et\u00a0al.: Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., et\u00a0al.: Tri-perspective view for vision-based 3d semantic occupancy prediction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Jie, Z., Chen, S., et\u00a0al.: Instance-aware multi-camera 3d object detection with structural priors mining and self-boosting learning. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i3.28037"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Keetha, N., Mishra, A., Karhade, J., et\u00a0al.: Anyloc: Towards universal visual place recognition. RAL (2023)","DOI":"10.1109\/LRA.2023.3343602"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Klingner, M., Borse, S., Kumar, V.R., et\u00a0al.: X3kd: Knowledge distillation across modalities, tasks and stages for multi-camera 3d object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01282"},{"key":"4_CR14","unstructured":"Li, P., Shen, W., Huang, Q., Cui, D.: Dualbev: Cnn is all you need in view transformation. In: ECCV (2024)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Ge, Z., Yu, G., et\u00a0al.: Bevdepth: Acquisition of reliable depth for multi-view 3d object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., et\u00a0al.: Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for multi-view 3d object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, J., Jia, F., et\u00a0al.: Petrv2: A unified framework for 3d perception from multi-camera images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tang, H., Amini, A., et\u00a0al.: Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"4_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Lu, J., Zhou, Z., Zhu, X., et\u00a0al.: Learning ego 3d representation as ray tracing. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Mao, J., Shi, S., Wang, X., Li, H.: 3d object detection for autonomous driving: A comprehensive survey. IJCV (2023)","DOI":"10.1007\/s11263-023-01790-1"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Shi, H., Pang, C., Zhang, J., Yang, K., Wu, Y., Ni, H., Lin, Y., Stiefelhagen, R., Wang, K.: Cobev: Elevating roadside 3d object detection with depth and height complementarity. IEEE Transactions on Image Processing (2024)","DOI":"10.1109\/TIP.2024.3463409"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Tang, P., Wang, Z., Wang, G., et\u00a0al.: Sparseocc: Rethinking sparse latent representation for vision-based semantic occupancy prediction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"4_CR26","unstructured":"Tian, X., Jiang, T., Yun, L., et\u00a0al.: Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving. NeurIPS (2024)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: Fully convolutional one-stage monocular 3d object detection. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"4_CR28","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., et\u00a0al.: Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: CoRL (2022)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., et\u00a0al.: Surroundocc: Multi-camera 3d occupancy prediction for autonomous driving. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Yan, J., Liu, Y., Sun, J., et\u00a0al.: Cross modal transformer: Towards fast and robust 3d object detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., et\u00a0al.: Std: Sparse-to-dense 3d object detector for point cloud. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"4_CR32","unstructured":"Yu, Z., Shu, C., Deng, J., et\u00a0al.: Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin. arXiv preprint arXiv:2311.12058 (2023)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Cao, J., Leng, H., et\u00a0al.: Sogdet: Semantic-occupancy guided multi-view 3d object detection. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i7.28600"},{"key":"4_CR34","unstructured":"Zhu, B., Jiang, Z., Zhou, X., et\u00a0al.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4378-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T05:58:51Z","timestamp":1767938331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4378-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819543779","9789819543786"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4378-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 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"}}]}}