{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:49:02Z","timestamp":1780526942000,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"This work was supported in part by NSFC, Shaanxi Project, and the program of the Ministry of Education.","award":["No.6212500145, No.62088102, No.61973246, No.91748208, No.2018ZDCXLGY0607."],"award-info":[{"award-number":["No.6212500145, No.62088102, No.61973246, No.91748208, No.2018ZDCXLGY0607."]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,20]]},"DOI":"10.1145\/3475721.3484311","type":"proceedings-article","created":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T16:08:24Z","timestamp":1634918904000},"page":"9-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["MBDF-Net"],"prefix":"10.1145","author":[{"given":"Xun","family":"Tan","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guowei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jishiyu","family":"Ding","sequence":"additional","affiliation":[{"name":"the Second Academy of CASIC, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01062"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_4_1","volume-title":"Point Clouds: A Survey","author":"Guo Yulan","year":"2020","unstructured":"Yulan Guo , H. Wang , Q. Hu , Hao Liu , Li Liu , and M. Bennamoun . 2020 . Deep Learning for 3D Point Clouds: A Survey . IEEE transactions on pattern analysis and machine intelligence , Vol. PP (2020). Yulan Guo, H. Wang, Q. Hu, Hao Liu, Li Liu, and M. Bennamoun. 2020. Deep Learning for 3D Point Clouds: A Survey. IEEE transactions on pattern analysis and machine intelligence , Vol. PP (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Tengteng Huang Zhe Liu Xiwu Chen and X. Bai. 2020. EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection. In ECCV .  Tengteng Huang Zhe Liu Xiwu Chen and X. Bai. 2020. EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection. In ECCV .","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"e_1_3_2_1_7_1","volume-title":"Adam: A Method for Stochastic Optimization. Computer Science","author":"Kingma D.","year":"2014","unstructured":"D. Kingma and J. Ba . 2014 . Adam: A Method for Stochastic Optimization. Computer Science (2014). D. Kingma and J. Ba. 2014. Adam: A Method for Stochastic Optimization. Computer Science (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS","author":"Ku Jason","year":"2018","unstructured":"Jason Ku , Melissa Mozifian , Jungwook Lee , Ali Harakeh , and Steven Waslander . 2018a. Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS ( 2018 ). Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, and Steven Waslander. 2018a. Joint 3D Proposal Generation and Object Detection from View Aggregation. IROS (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Hongwu Kuang B. Wang J. An M. Zhang and Z. Zhang. 2020. Voxel-FPN: Multi-Scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds. Sensors (Basel Switzerland) Vol. 20 (2020).  Hongwu Kuang B. Wang J. An M. Zhang and Z. Zhang. 2020. Voxel-FPN: Multi-Scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds. Sensors (Basel Switzerland) Vol. 20 (2020).","DOI":"10.3390\/s20030704"},{"key":"e_1_3_2_1_11_1","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV) .","author":"Lahoud J.","unstructured":"J. Lahoud and B. Ghanem . 2017. 2D-Driven 3D Object Detection in RGB-D Images . In 2017 IEEE International Conference on Computer Vision (ICCV) . J. Lahoud and B. Ghanem. 2017. 2D-Driven 3D Object Detection in RGB-D Images. In 2017 IEEE International Conference on Computer Vision (ICCV) ."},{"key":"e_1_3_2_1_12_1","volume-title":"PointPillars: Fast Encoders for Object Detection From Point Clouds. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Lang Alex H.","year":"2019","unstructured":"Alex H. Lang , Sourabh Vora , Holger Caesar , Lubing Zhou , and Oscar Beijbom . 2019 . PointPillars: Fast Encoders for Object Detection From Point Clouds. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Alex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, and Oscar Beijbom. 2019. PointPillars: Fast Encoders for Object Detection From Point Clouds. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_13_1","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7337--7345","author":"Liang M.","unstructured":"M. Liang , B. Yang , Y. Chen , R. Hu , and R. Urtasun . 2019. Multi-Task Multi-Sensor Fusion for 3D Object Detection . 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7337--7345 . M. Liang, B. Yang, Y. Chen, R. Hu, and R. Urtasun. 2019. Multi-Task Multi-Sensor Fusion for 3D Object Detection. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7337--7345."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"M. Liang B. Yang Shenlong Wang and R. Urtasun. 2018. Deep Continuous Fusion for Multi-sensor 3D Object Detection. In ECCV .  M. Liang B. Yang Shenlong Wang and R. Urtasun. 2018. Deep Continuous Fusion for Multi-sensor 3D Object Detection. In ECCV .","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"e_1_3_2_1_15_1","unstructured":"Zhidong Liang Ming Zhang Zehan Zhang Xian Zhao and S. Pu. 2020. RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation. ArXiv Vol. abs\/2009.00206 (2020).  Zhidong Liang Ming Zhang Zehan Zhang Xian Zhao and S. Pu. 2020. RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation. ArXiv Vol. abs\/2009.00206 (2020)."},{"key":"e_1_3_2_1_16_1","first-page":"2999","article-title":"Focal Loss for Dense Object Detection","volume":"99","author":"Lin Tsung Yi","year":"2017","unstructured":"Tsung Yi Lin , Priya Goyal , Ross Girshick , Kaiming He , and Piotr Doll\u00e1r . 2017 . Focal Loss for Dense Object Detection . IEEE Transactions on Pattern Analysis & Machine Intelligence , Vol. PP , 99 (2017), 2999 -- 3007 . Tsung Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Doll\u00e1r. 2017. Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis & Machine Intelligence , Vol. PP, 99 (2017), 2999--3007.","journal-title":"PP"},{"key":"e_1_3_2_1_17_1","volume-title":"SSD: Single Shot MultiBox Detector. In ECCV .","author":"Liu W.","year":"2016","unstructured":"W. Liu , Dragomir Anguelov , D. Erhan , Christian Szegedy , S. Reed , Cheng-Yang Fu , and A. Berg . 2016 . SSD: Single Shot MultiBox Detector. In ECCV . W. Liu, Dragomir Anguelov, D. Erhan, Christian Szegedy, S. Reed, Cheng-Yang Fu, and A. Berg. 2016. SSD: Single Shot MultiBox Detector. In ECCV ."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"e_1_3_2_1_19_1","unstructured":"C. R. Qi O. Litany K. He and L. J. Guibas. 2019. Deep Hough Voting for 3D Object Detection in Point Clouds. IEEE (2019).  C. R. Qi O. Litany K. He and L. J. Guibas. 2019. Deep Hough Voting for 3D Object Detection in Point Clouds. IEEE (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"e_1_3_2_1_21_1","unstructured":"C. R. Qi L. Yi H. Su and L. Guibas. 2017. PointNet  C. R. Qi L. Yi H. Su and L. Guibas. 2017. PointNet"},{"key":"e_1_3_2_1_22_1","unstructured":": Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In NIPS .  : Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In NIPS ."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_25_1","volume-title":"Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients. In IEEE Conference on Computer Vision & Pattern Recognition .","author":"Ren Z.","unstructured":"Z. Ren and E. B. Sudderth . 2016 . Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients. In IEEE Conference on Computer Vision & Pattern Recognition . Z. Ren and E. B. Sudderth. 2016. Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients. In IEEE Conference on Computer Vision & Pattern Recognition ."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"e_1_3_2_1_28_1","volume-title":"2020 c. From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. (2020). arxiv","author":"Shi Shaoshuai","year":"1907","unstructured":"Shaoshuai Shi , Zhe Wang , Jianping Shi , Xiaogang Wang , and Hongsheng Li . 2020 c. From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. (2020). arxiv : 1907 .03670 [cs.CV] Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, and Hongsheng Li. 2020 c. From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network. (2020). arxiv: 1907.03670 [cs.CV]"},{"key":"e_1_3_2_1_29_1","unstructured":"Weijing Shi Ragunathan and Rajkumar. 2020 b. Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud. (2020).  Weijing Shi Ragunathan and Rajkumar. 2020 b. Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud. (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"IEEE Conference on Computer Vision & Pattern Recognition. 567--576","author":"Song S.","unstructured":"S. Song , S. P. Lichtenberg , and J. Xiao . 2015. SUN RGB-D: A RGB-D scene understanding benchmark suite . In IEEE Conference on Computer Vision & Pattern Recognition. 567--576 . S. Song, S. P. Lichtenberg, and J. Xiao. 2015. SUN RGB-D: A RGB-D scene understanding benchmark suite. In IEEE Conference on Computer Vision & Pattern Recognition. 567--576."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"S. Song and J. Xiao. 2016. Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images. IEEE (2016).  S. Song and J. Xiao. 2016. Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images. IEEE (2016).","DOI":"10.1109\/CVPR.2016.94"},{"key":"e_1_3_2_1_32_1","volume-title":"FCOS: Fully Convolutional One-Stage Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Tian Zhi","year":"2019","unstructured":"Zhi Tian , Chunhua Shen , Hao Chen , and Tong He . 2019 . FCOS: Fully Convolutional One-Stage Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9626--9635. Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. FCOS: Fully Convolutional One-Stage Object Detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), 9626--9635."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"S. Vora A. H. Lang B. Helou and O. Beijbom. 2019. PointPainting: Sequential Fusion for 3D Object Detection. (2019).  S. Vora A. H. Lang B. Helou and O. Beijbom. 2019. PointPainting: Sequential Fusion for 3D Object Detection. (2019).","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_2_1_34_1","volume-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) .","author":"Wang Z.","unstructured":"Z. Wang and K. Jia . 2019. Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal . In 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) . Z. Wang and K. Jia. 2019. Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal. In 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) ."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"L. Xie C. Xiang Z. Yu G. Xu Z. Yang D. Cai and X. He. 2019. PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module. (2019).  L. Xie C. Xiang Z. Yu G. Xu Z. Yang D. Cai and X. He. 2019. PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module. (2019).","DOI":"10.1609\/aaai.v34i07.6933"},{"key":"e_1_3_2_1_36_1","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 244--253","author":"Xu D.","year":"2018","unstructured":"D. Xu , D. Anguelov , and A. Jain . 2018. PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation . 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 244--253 . https:\/\/doi.org\/10.1109\/CVPR. 2018 .00033 10.1109\/CVPR.2018.00033 D. Xu, D. Anguelov , and A. Jain. 2018. PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 244--253. https:\/\/doi.org\/10.1109\/CVPR.2018.00033"},{"key":"e_1_3_2_1_37_1","volume-title":"SECOND: Sparsely Embedded Convolutional Detection. Sensors (Basel, Switzerland)","author":"Yan Yan","year":"2018","unstructured":"Yan Yan , Yuxing Mao , and B. Li . 2018 . SECOND: Sparsely Embedded Convolutional Detection. Sensors (Basel, Switzerland) , Vol. 18 (2018). Yan Yan, Yuxing Mao, and B. Li. 2018. SECOND: Sparsely Embedded Convolutional Detection. Sensors (Basel, Switzerland) , Vol. 18 (2018)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"e_1_3_2_1_41_1","unstructured":"Jin Hyeok Yoo Yeocheol Kim J. Kim and J. W. Choi. 2020. 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection. In ECCV .  Jin Hyeok Yoo Yeocheol Kim J. Kim and J. W. Choi. 2020. 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection. In ECCV ."},{"key":"e_1_3_2_1_42_1","unstructured":"Benjin Zhu Zhengkai Jiang Xiangxin Zhou Zeming Li and G. Yu. 2019. Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection. ArXiv Vol. abs\/1908.09492 (2019).  Benjin Zhu Zhengkai Jiang Xiangxin Zhou Zeming Li and G. Yu. 2019. Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection. ArXiv Vol. abs\/1908.09492 (2019)."}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 1st International Workshop on Multimedia Computing for Urban Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3475721.3484311","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3475721.3484311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:18Z","timestamp":1750193298000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3475721.3484311"}},"subtitle":["Multi-Branch Deep Fusion Network for 3D Object Detection"],"short-title":[],"issued":{"date-parts":[[2021,10,20]]},"references-count":42,"alternative-id":["10.1145\/3475721.3484311","10.1145\/3475721"],"URL":"https:\/\/doi.org\/10.1145\/3475721.3484311","relation":{},"subject":[],"published":{"date-parts":[[2021,10,20]]},"assertion":[{"value":"2021-10-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}