{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:15:35Z","timestamp":1740147335459,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province of China","doi-asserted-by":"crossref","award":["No.LH2021F026","No.LH2021F026","No.LH2021F026"],"award-info":[{"award-number":["No.LH2021F026","No.LH2021F026","No.LH2021F026"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["No. HIT.NSRIF202243","No. HIT.NSRIF202243","No. HIT.NSRIF202243"],"award-info":[{"award-number":["No. HIT.NSRIF202243","No. HIT.NSRIF202243","No. HIT.NSRIF202243"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["No.2022Z071077002"],"award-info":[{"award-number":["No.2022Z071077002"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s11760-023-02772-z","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T19:01:56Z","timestamp":1695236516000},"page":"455-463","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DMFF: dual-way multimodal feature fusion for 3D object detection"],"prefix":"10.1007","volume":"18","author":[{"given":"Xiaopeng","family":"Dong","sequence":"first","affiliation":[]},{"given":"Xiaoguang","family":"Di","sequence":"additional","affiliation":[]},{"given":"Wenzhuang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"2772_CR1","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, Y., Chen, J., and Huang, D.: OcTr: Octree-based transformer for 3D object detection. arXiv preprint arXiv:2303.12621 (2023)","DOI":"10.1109\/CVPR52729.2023.00500"},{"key":"2772_CR2","doi-asserted-by":"crossref","unstructured":"Sheng, H., Cai, S., Liu, Y., Deng, B., Huang, J., Hua, X. S., Zhao, M. J.: Improving 3d object detection with channel-wise transformer. In: Proceedings of the IEEE\/cvf conference on computer vision and pattern recognition. pp. 2743-2752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"2772_CR3","unstructured":"Hu, J. S., Kuai, T., and Waslander, S. L.: Point density-aware voxels for lidar 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8469-8478 (2022)"},{"key":"2772_CR4","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: CVPR. pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2772_CR5","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"},{"key":"2772_CR6","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhong, Y., and Neumann, U.: Behind the curtain: learning occluded shapes for 3d object detection. In: Proceedings of the AAAI conference on artificial intelligence. pp. 2893-2901 (2022)","DOI":"10.1609\/aaai.v36i3.20194"},{"key":"2772_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, Y., Zhang, X., Sun, J., and Jia, J.: Focal sparse convolutional networks for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5428-5437 (2022)","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"2772_CR8","unstructured":"Zhu, H., Deng, J., Zhang, Y., Ji, J., Mao, Q., Li, H., and Zhang, Y.: Vpfnet: Improving 3d object detection with virtual point based lidar and stereo data fusion. arXiv preprint arXiv:2111.14382 (2021)"},{"key":"2772_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tang, H., Amini, A., Yang, X., Mao, H., Rus, D., and Han, S.: 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":"2772_CR10","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":"2772_CR11","unstructured":"Wang, Y., Mao, Q., Zhu, H., Deng, J., Zhang, Y., Ji, J., Zhang, Y.: Multi-modal 3d object detection in autonomous driving: a survey. arXiv preprint arXiv:2106.12735 (2021)"},{"key":"2772_CR12","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":"2772_CR13","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":"2772_CR14","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: IEEE\/RSJ international conference on intelligent robots and systems (IROS). pp. 1\u20138. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"2772_CR15","doi-asserted-by":"crossref","unstructured":"Wu, X., Peng, L., Yang, H., Xie, L., Huang, C., Deng, C., Cai, D.: 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. 5418-5427 (2022)","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"2772_CR16","doi-asserted-by":"crossref","unstructured":"Hu, M., Wang, S., Li, B., Ning, S., Fan, L., Gong, X.: Penet: Towards precise and efficient image guided depth completion. In 2021 IEEE international conference on robotics and automation (ICRA). pp. 13656-13662. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"2772_CR17","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":"2772_CR18","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":"2772_CR19","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. NeurIPS 30 (2017)"},{"key":"2772_CR20","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"},{"issue":"10","key":"2772_CR21","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":"2772_CR22","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":"2772_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W. L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K. Q.: Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8445-8453 (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"2772_CR24","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., and Fan, X.: Accurate monocular 3d object detection via color-embedded 3d reconstruction for autonomous driving. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6851-6860 (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"key":"2772_CR25","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3d object detection. arXiv preprint arXiv:1811.08188 (2018)"},{"key":"2772_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":"2772_CR27","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: Epnet: Enhancing point features with image semantics for 3d object detection. In: ECCV. pp. 35\u201352. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"2772_CR28","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. arXiv preprint arXiv:2112.11088 (2021)","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"2772_CR29","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":"2772_CR30","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":"2772_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems, 30 (2017)"},{"key":"2772_CR32","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7345-7353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"2772_CR33","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. 663-672 (2023)","DOI":"10.1109\/WACV56688.2023.00073"},{"key":"2772_CR34","doi-asserted-by":"crossref","unstructured":"Yang, H., Liu, Z., Wu, X., Wang, W., Qian, W., He, X., Cai, D.: Graph R-CNN: towards accurate 3D object detection with semantic-decorated local graph. In: ECCV. pp. 662-679. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_38"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02772-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-023-02772-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02772-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T15:41:34Z","timestamp":1706197294000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-023-02772-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["2772"],"URL":"https:\/\/doi.org\/10.1007\/s11760-023-02772-z","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"4 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}