{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:14:21Z","timestamp":1777493661218,"version":"3.51.4"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031441943","type":"print"},{"value":"9783031441950","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44195-0_12","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"136-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["MLF-DET: Multi-Level Fusion for\u00a0Cross-Modal 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Zewei","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanqing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shitao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"12_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":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, Y., Zhang, X., Sun, J., Jia, J.: Focal sparse convolutional networks for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5428\u20135437 (2022)","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"12_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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"12_CR6","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":"12_CR7","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":"12_CR8","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":"12_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/978-3-030-58580-8_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Li","year":"2020","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3d\u00a0detection from object keypoints for\u00a0autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 644\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_38"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Li, X., et al.: Homogeneous multi-modal feature fusion and interaction for 3D object detection. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVIII, pp. 691\u2013707. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_40","DOI":"10.1007\/978-3-031-19839-7_40"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Voxel field fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1120\u20131129 (2022)","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"12_CR12","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":"12_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: Single-stage monocular 3D object detection via keypoint estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, T., Li, B., Chen, X., Wang, X., Bai, X.: Epnet++: Cascade bi-directional fusion for multi-modal 3D object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Mahmoud, A., Hu, J.S., Waslander, S.L.: Dense voxel fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 663\u2013672 (2023)","DOI":"10.1109\/WACV56688.2023.00073"},{"key":"12_CR16","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 (IROS), pp. 10386\u201310393. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: Fast-clocs: fast camera-lidar object candidates fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 187\u2013196 (2022)","DOI":"10.1109\/WACV51458.2022.00380"},{"key":"12_CR18","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":"12_CR19","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 652\u2013660 (2017)"},{"key":"12_CR20","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"12_CR21","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inform. Process. Syst. 28 (2015)"},{"key":"12_CR22","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":"12_CR23","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 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"},{"issue":"8","key":"12_CR24","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. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2647\u20132664 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR25","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":"12_CR26","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":"12_CR27","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Sparse fuse dense: Towards high quality 3D detection with depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5418\u20135427 (2022)","DOI":"10.1109\/CVPR52688.2022.00534"},{"issue":"10","key":"12_CR28","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":"12_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, J., Huang, D.: Cat-det: Contrastively augmented transformer for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 908\u2013917 (2022)","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: Learning highly efficient point-based detectors for 3D lidar point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18953\u201318962 (2022)","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"12_CR31","unstructured":"Zhang, Y., Zhang, Q., Hou, J., Yuan, Y., Xing, G.: Bidirectional propagation for cross-modal 3d object detection. arXiv preprint arXiv:2301.09077 (2023)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133298 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: Vpfnet: Improving 3d object detection with virtual point based lidar and stereo data fusion. IEEE Transactions on Multimedia (2022)","DOI":"10.1109\/TMM.2022.3189778"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44195-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:05:38Z","timestamp":1695297938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","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":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted  : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}