{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T16:04:15Z","timestamp":1787241855537,"version":"build-2736575974"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Science and Technology Program of Guangdong Province","award":["2022B0701180001"],"award-info":[{"award-number":["2022B0701180001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,1,31]]},"abstract":"<jats:p>Pillar-based method is significant in the field of LiDAR-based 3D object detection which could directly make use of efficient 2D backbone and save computational resources during reference. Existing methods usually sequentially project the original point clouds into the cylindrical view or the bird-eye view for feature extraction. However, the former suffers from obscured problems and the scales of instances vary greatly with distance, while the latter leads to considerable confusion problems due to the loss of semantic information caused by the sparsity of the projected point cloud. In this article, we present a novel and efficient two-stage point-pillar hybrid architecture named Attentive Multi-View Fusion Network (AMVFNet), in which we abstract features from all cylindrical view, bird-eye view, and raw point clouds. Rather than designing more complex modules to solve the problems inherent in the single-view approach, our multi-view fusion architecture effectively combines the strengths of multiple perspectives to improve performance at a more fundamental level. Besides, to compensate for quantization distortion caused by projection operations, we propose attentive feature enhancement layers to further improve the capability of contextual information capturing. Extensive experiments on the KITTI detection benchmark illustrate that our proposed AMVFNet achieves competitive performance compared with other SOTA 3D object detectors.<\/jats:p>","DOI":"10.1145\/3689639","type":"journal-article","created":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T10:40:27Z","timestamp":1728988827000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["AMVFNet: Attentive Multi-View Fusion Network for 3D Object Detection"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0194-4421","authenticated-orcid":false,"given":"Yuxiao","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4947-1589","authenticated-orcid":false,"given":"Zhicong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9448-3554","authenticated-orcid":false,"given":"Jingwen","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5432-8149","authenticated-orcid":false,"given":"Dihu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-Sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,25]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"e_1_3_1_3_2","unstructured":"Joan Bruna Wojciech Zaremba Arthur Szlam and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv:1312.6203. Retrieved from https:\/\/arxiv.org\/abs\/1312.6203"},{"key":"e_1_3_1_4_2","first-page":"18067","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Cai Qi","year":"2023","unstructured":"Qi Cai, Yingwei Pan, Ting Yao, Chong-Wah Ngo, and Tao Mei. 2023. Objectfusion: Multi-modal 3D object detection with object-centric fusion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 18067\u201318076."},{"key":"e_1_3_1_5_2","first-page":"21224","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"33","author":"Chen Qi","year":"2020","unstructured":"Qi Chen, Lin Sun, Ernest Cheung, and Alan L. Yuille. 2020. Every view counts: Cross-view consistency in 3d object detection with hybrid-cylindrical-spherical voxelization. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 21224\u201321235."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023541"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100848"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243316"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_1_12_2","first-page":"772","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Guan Tianrui","year":"2022","unstructured":"Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu, Larry Davis, and Dinesh Manocha. 2022. M3detr: Multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 772\u2013782."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"e_1_3_1_16_2","first-page":"1","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS \u201918).","author":"Ku Jason","year":"2018","unstructured":"Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, and Steven L. Waslander. 2018. Joint 3D proposal generation and object detection from view aggregation. In Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS \u201918). IEEE, 1\u20138."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"2","key":"e_1_3_1_18_2","first-page":"1159","article-title":"Accurate and real-time 3D pedestrian detection using an efficient attentive pillar network","volume":"8","author":"Le Duy Tho","year":"2022","unstructured":"Duy Tho Le, Hengcan Shi, Hamid Rezatofighi, and Jianfei Cai. 2022. Accurate and real-time 3D pedestrian detection using an efficient attentive pillar network. IEEE Robotics and Automation Letters 8, 2 (2022), 1159\u20131166.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475208"},{"key":"e_1_3_1_21_2","first-page":"10421","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Liang Tingting","year":"2022","unstructured":"Tingting Liang, Hongwei Xie, Kaicheng Yu, Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Tao Tang, Bing Wang, and Zhi Tang. 2022. Bevfusion: A simple and robust LiDAR-camera fusion framework. In Proceedings of the Advances in Neural Information Processing Systems 35 (2022), 10421\u201310434."},{"key":"e_1_3_1_22_2","first-page":"2774","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA \u201923)","author":"Liu Zhijian","year":"2023","unstructured":"Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela L. Rus, and Song Han. 2023. Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA \u201923). IEEE, 2774\u20132781."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"e_1_3_1_25_2","first-page":"12677","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Meyer Gregory P.","year":"2019","unstructured":"Gregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, and Carl K. Wellington. 2019. Lasernet: An efficient probabilistic 3D object detector for autonomous driving. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12677\u201312686."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410439"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"e_1_3_1_28_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. Pointnet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652\u2013660."},{"key":"e_1_3_1_29_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"30","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. Pointnet \\(++\\) : Deep hierarchical feature learning on point sets in a metric space. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"e_1_3_1_32_2","unstructured":"Shaoshuai Shi Zhe Wang Xiaogang Wang and Hongsheng Li. 2019. Part-a \\({}^{\\wedge}\\) 2 net: 3D part-aware and aggregation neural network for object detection from point cloud. arXiv:1907.03670. Retrieved from https:\/\/arxiv.org\/abs\/1907.03670"},{"key":"e_1_3_1_33_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV \u201918) Workshops","author":"Simony Martin","year":"2018","unstructured":"Martin Simony, Stefan Milzy, Karl Amendey, and Horst-Michael Gross. 2018. Complex-YOLO: An euler-region-proposal for real-time 3d object detection on point clouds. In Proceedings of the European Conference on Computer Vision (ECCV \u201918) Workshops. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:53512298"},{"key":"e_1_3_1_34_2","first-page":"369","volume-title":"Proceedings of the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications","volume":"11006","author":"Smith Leslie N.","year":"2019","unstructured":"Leslie N. Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Proceedings of the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, Vol. 11006. SPIE, 369\u2013386."},{"key":"e_1_3_1_35_2","article-title":"OpenPCDet: An open-source toolbox for 3D object detection from point clouds","author":"OD Team","year":"2020","unstructured":"OD Team. 2020. OpenPCDet: An open-source toolbox for 3D object detection from point clouds. OD Team (2020).","journal-title":"OD Team"},{"issue":"1","key":"e_1_3_1_36_2","doi-asserted-by":"crossref","first-page":"3\u2013es","DOI":"10.1145\/1198302.1198305","article-title":"Video abstraction: A systematic review and classification","volume":"3","author":"Truong Ba Tu","year":"2007","unstructured":"Ba Tu Truong and Svetha Venkatesh. 2007. Video abstraction: A systematic review and classification. ACM Transactions on Multimedia Computing, Communications, and Applications 3, 1 (2007), 3\u2013es.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_37_2","first-page":"1","volume-title":"Proceedings of the International Joint Conference on Neural Networks (IJCNN \u201921).","author":"Tu Jiayin","year":"2021","unstructured":"Jiayin Tu, Ping Wang, and Fuqiang Liu. 2021. PP-RCNN: Point-pillars feature set abstraction for 3d real-time object detection. In Proceedings of the International Joint Conference on Neural Networks (IJCNN \u201921). IEEE, 1\u20138."},{"key":"e_1_3_1_38_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30."},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_1_40_2","first-page":"18","volume-title":"Proceedings of the 16th European Conference on Computer Vision (ECCV \u201920)","author":"Wang Yue","year":"2020","unstructured":"Yue Wang, Alireza Fathi, Abhijit Kundu, David A Ross, Caroline Pantofaru, Tom Funkhouser, and Justin Solomon. 2020. Pillar-based object detection for autonomous driving. In Proceedings of the 16th European Conference on Computer Vision (ECCV \u201920). Springer, 18\u201334."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466780"},{"issue":"4","key":"e_1_3_1_42_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3506708","article-title":"An end-to-end heterogeneous restraint network for RGB-D cross-modal person re-identification","volume":"18","author":"Wu Jingjing","year":"2022","unstructured":"Jingjing Wu, Jianguo Jiang, Meibin Qi, Cuiqun Chen, and Jingjing Zhang. 2022. An end-to-end heterogeneous restraint network for RGB-D cross-modal person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications 18, 4 (2022), 1\u201322.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"e_1_3_1_48_2","first-page":"11495","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yin Junbo","year":"2020","unstructured":"Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou, and Ruigang Yang. 2020. LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11495\u201311504."},{"key":"e_1_3_1_49_2","first-page":"21361","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu Haibao","year":"2022","unstructured":"Haibao Yu, Yizhen Luo, Mao Shu, Yiyi Huo, Zebang Yang, Yifeng Shi, Zhenglong Guo, Hanyu Li, Xing Hu, Jirui Yuan, et al. 2022. Dair-v2x: A large-scale dataset for vehicle-infrastructure cooperative 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 21361\u201321370."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570166"},{"key":"e_1_3_1_53_2","first-page":"923","volume-title":"Proceedings of the Conference on Robot Learning.","author":"Zhou Yin","year":"2020","unstructured":"Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, and Vijay Vasudevan. 2020. End-to-end multi-view fusion for 3D object detection in LiDAR point clouds. In Proceedings of the Conference on Robot Learning. PMLR, 923\u2013932."},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689639","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:09:47Z","timestamp":1750280987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,25]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,31]]}},"alternative-id":["10.1145\/3689639"],"URL":"https:\/\/doi.org\/10.1145\/3689639","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,25]]},"assertion":[{"value":"2023-12-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}