{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:57:09Z","timestamp":1786114629282,"version":"3.56.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20074-8_36","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"628-644","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":134,"title":["Deformable Feature Aggregation for\u00a0Dynamic Multi-modal 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Zehui","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiquan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangji","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinhong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"36_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"36_CR4","unstructured":"Chen, Q., Sun, L., Cheung, E., Yuille, A.L.: Every view counts: cross-view consistency in 3D object detection with hybrid-cylindrical-spherical voxelization. Adv. Neural Inf. Process. Syst., 21224\u201321235 (2020)"},{"key":"36_CR5","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: AutoAlign: pixel-instance feature aggregation for multi-modal 3D object detection. IJCAI, pp. 1\u20137 (2022)","DOI":"10.24963\/ijcai.2022\/116"},{"key":"36_CR7","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https:\/\/github.com\/open-mmlab\/mmdetection3D (2020)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"36_CR9","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430, pp. 1\u20136 (2021)"},{"key":"36_CR10","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"36_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58555-6_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Huang","year":"2020","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3d object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 35\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3D proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1\u20138. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Fully convolutional networks for panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 214\u2013223 (2021)","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: DeepFusion: LiDAR-camera deep fusion for multi-modal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17182\u201317191 (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: SimIPU: simple 2D image and 3D point cloud unsupervised pre-training for spatial-aware visual representations. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 36, pp. 1500\u20131508 (2022)","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European Conference on Computer Vision, pp. 641\u2013656 (2018)","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. arXiv preprint arXiv:2205.13542 (2022)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: CLOCs: camera-LiDAR object candidates fusion for 3D object detection. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1\u201310. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"36_CR22","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"36_CR23","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Point RCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1\u201314 (2020)","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Zhou, Y., Tuzel, O.: MVX-Net: multimodal VoxelNet for 3D object detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7276\u20137282. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: PointPainting: sequential fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134612 (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., et al.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Wang, C., Ma, C., Zhu, M., Yang, X.: PointAugmenting: cross-modal augmentation for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11794\u201311803 (2021)","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"36_CR32","unstructured":"Wang, Y., Solomon, J.M.: Object DGCNN: 3D object detection using dynamic graphs. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"36_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18, 3337 (2018)","journal-title":"Sensors"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1951\u20131960 (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"36_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-030-58583-9_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JH Yoo","year":"2020","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 720\u2013736. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_43"},{"key":"36_CR38","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: MixUp: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, pp. 1\u201312 (2017)"},{"key":"36_CR39","unstructured":"Zhang, W., Wang, Z., Loy, C.C., Zhang, W.: Improving data augmentation for multi-modality 3D object detection. arXiv preprint arXiv:2012.12741, pp. 1\u201310 (2021)"},{"key":"36_CR40","unstructured":"Zhou, Y., et al.: End-to-end multi-view fusion for 3D object detection in LiDAR point clouds. In: Conference on Robot Learning, pp. 923\u2013932. PMLR (2020)"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"36_CR42","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492, pp. 1\u201310 (2019)"},{"key":"36_CR43","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations, pp. 1\u201312 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T17:58:49Z","timestamp":1701367129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"12 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}