ARPNET: attention region proposal network for 3D object detection

This is a preview of subscription content, access via your institution.


  1. 1

    Baluch F, Itti L. Mechanisms of top-down attention. Trends Neurosci, 2011, 34: 210–224

    Article  Google Scholar 

  2. 2

    Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, Long Beach, 2017. 5998–6008

  3. 3

    Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of IEEE International Conference on Computer Vision, Providence, 2012. 3354–3361

  4. 4

    Zhou Y, Tuzel O. Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 2018. 4490–4499

  5. 5

    Graham B, van der Maaten L. Submanifold sparse convolutional networks. 2017. ArXiv:1706.01307

  6. 6

    Yan Y, Mao Y X, Li B. Second: sparsely embedded convolutional detection. Sensors, 2018, 18: 3337

    Article  Google Scholar 

Download references


This work was supported in part by National Key R&D Program of China (Grant No. 2018YFB1004600), Beijing Municipal Natural Science Foundation (Grant No. Z181100008918010), National Natural Science Foundation of China (Grant Nos. 61836014, 61761146004, 61602481, 61773375), Fundamental Research Funds of BJTU (Grant No. 2017JBZ002), and in part by Microsoft Collaborative Research Project.

Author information



Corresponding author

Correspondence to Xiaoli Hao.

Electronic supplementary material

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ye, Y., Zhang, C. & Hao, X. ARPNET: attention region proposal network for 3D object detection. Sci. China Inf. Sci. 62, 220104 (2019).

Download citation