{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:52:40Z","timestamp":1783605160000,"version":"3.55.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198380","type":"print"},{"value":"9783031198397","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\/978-3-031-19839-7_40","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T11:40:06Z","timestamp":1666438806000},"page":"691-707","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Homogeneous Multi-modal Feature Fusion and\u00a0Interaction for\u00a03D Object Detection"],"prefix":"10.1007","author":[{"given":"Xin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Botian","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuenan","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"40_CR1","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":"40_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"40_CR3","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: AAAI, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Guan, T., Wang, J., Lan, S., Chandra, R., Wu, Z., Davis, L., Manocha, D.: M3detr: multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In: WACV, pp. 772\u2013782 (2022)","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Guo, X., Shi, S., Wang, X., Li, H.: Liga-stereo: learning lidar geometry aware representations for stereo-based 3D detector. In: CVPR, pp. 3153\u20133163 (2021)","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"40_CR8","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":"40_CR9","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":"40_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. ICLR (2015)"},{"key":"40_CR11","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: IROS, pp. 1\u20138. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"40_CR12","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: CVPR, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar R-CNN: an efficient and universal 3D object detector. In: CVPR, pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3D object detection. In: CVPR, pp. 7345\u20137353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"40_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/978-3-030-01270-0_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Liang","year":"2018","unstructured":"Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 663\u2013678. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_39"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: Single-stage monocular 3D object detection via keypoint estimation. In: CVPRW, pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: ICCV, pp. 3111\u20133121 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Mao, J., Niu, M., Bai, H., Liang, X., Xu, H., Xu, C.: Pyramid R-CNN: Towards better performance and adaptability for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2723\u20132732 (2021)","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: ICCV, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: Clocs: camera-lidar object candidates fusion for 3D object detection. In: IROS, pp. 10386\u201310393. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"40_CR22","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":"40_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: CVPR, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"40_CR24","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: CVPR, pp. 652\u2013660 (2017)"},{"key":"40_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS, vol. 30 (2017)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: CVPR, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"40_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, vol. 28 (2015)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Sheng, H., et al.: Improving 3D object detection with channel-wise transformer. In: ICCV, pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"40_CR29","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":"40_CR30","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointrCNN: 3D object proposal generation and detection from point cloud. In: CVPR, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"8","key":"40_CR31","first-page":"2647","volume":"43","author":"S Shi","year":"2020","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. PAMI 43(8), 2647\u20132664 (2020)","journal-title":"PAMI"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3D object detection in a point cloud. In: CVPR, pp. 1711\u20131719 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"40_CR33","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":"40_CR34","unstructured":"Smith, L.N.: A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820 (2018)"},{"key":"40_CR35","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":"40_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-030-71278-5_21","volume-title":"Pattern Recognition","author":"Y Tang","year":"2021","unstructured":"Tang, Y., Dorn, S., Savani, C.: Center3D: center-based monocular 3D object detection with joint depth understanding. In: Akata, Z., Geiger, A., Sattler, T. (eds.) DAGM GCPR 2020. LNCS, vol. 12544, pp. 289\u2013302. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-71278-5_21"},{"key":"40_CR37","unstructured":"Team, O.D.: Openpcdet: an open-source toolbox for 3D object detection from point clouds (2020). https:\/\/github.com\/open-mmlab\/OpenPCDet"},{"key":"40_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, vol. 30 (2017)"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: sequential fusion for 3D object detection. In: CVPR, pp. 4604\u20134612 (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Wang, C., Ma, C., Zhu, M., Yang, X.: Pointaugmenting: cross-modal augmentation for 3D object detection. In: CVPR, pp. 11794\u201311803 (2021)","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"40_CR41","unstructured":"Wang, Y., Mao, Q., Zhu, H., Zhang, Y., Ji, J., Zhang, Y.: Multi-modal 3D object detection in autonomous driving: a survey. CoRR (2021)"},{"key":"40_CR42","unstructured":"Wang, Y., Mao, Q., Zhu, H., Zhang, Y., Ji, J., Zhang, Y.: Multi-modal 3D object detection in autonomous driving: a survey. arXiv preprint arXiv:2106.12735 (2021)"},{"key":"40_CR43","doi-asserted-by":"crossref","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. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Xie, L., Xiang, C., Yu, Z., Xu, G., Yang, Z., Cai, D., He, X.: PI-RCNN: an efficient multi-sensor 3D object detector with point-based attentive cont-conv fusion module. In: AAAI, pp. 12460\u201312467 (2020)","DOI":"10.1609\/aaai.v34i07.6933"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Xu, D., Anguelov, D., Jain, A.: Pointfusion: deep sensor fusion for 3D bounding box estimation. In: CVPR, pp. 244\u2013253 (2018)","DOI":"10.1109\/CVPR.2018.00033"},{"issue":"10","key":"40_CR46","doi-asserted-by":"publisher","first-page":"3337","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(10), 3337 (2018)","journal-title":"Sensors"},{"key":"40_CR47","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":"40_CR48","unstructured":"You, Y., et al.: Pseudo-lidar++: accurate depth for 3D object detection in autonomous driving. In: ICLR (2020)"},{"key":"40_CR49","unstructured":"Zhang, Z., et al.: Maff-net: filter false positive for 3D vehicle detection with multi-modal adaptive feature fusion. arXiv preprint arXiv:2009.10945 (2020)"},{"key":"40_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: CVPR, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"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\/978-3-031-19839-7_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:47:31Z","timestamp":1709812051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19839-7_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198380","9783031198397"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19839-7_40","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":"23 October 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)"}}]}}