Baoyuan Liu (刘宝渊)

I am an applied scientist at Amazon Dex Robotics. I received my PhD from University of Central Florida in 2016, and Bachelor from Shanghai Jiao Tong University in 2010. My research interests are in computer vision and deep neural networks.

Publications

• Min Wang, Baoyuan Liu, and Hassan Foroosh. "Wide Hidden Expansion Layer for Deep Convolutional Neural Networks." The IEEE Winter Conference on Applications of Computer Vision (WACV). 2020. [pdf]
• Min Wang, Baoyuan Liu and Hassan Foroosh, "Look-Up Table Unit Activation Function for Deep Convolutional Neural Networks," 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, 2018, pp. 1225-1233. [pdf] [poster]
• Min Wang, Baoyuan Liu and Hassan Foroosh, "Factorized Convolutional Neural Networks," 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, 2017, pp. 545-553. [pdf]
• Baoyuan Liu, Min Wang, H. Foroosh, M. Tappen and M. Penksy, "Sparse Convolutional Neural Networks," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 806-814. [pdf] [poster]
• Hakan Boyraz, Syed Zain Masood, Baoyuan Liu, Marshall Tappen and Hassan Foroosh. Action Recognition by Weakly-Supervised Discriminative Region Localization. Proceedings of the British Machine Vision Conference (BMVC). BMVA Press, September 2014. [pdf]
• Baoyuan Liu, Fereshteh Sadeghi, Marshall Tappen, Ohad Shamir, Ce Liu, "Probabilistic Label Trees for Efficient Large Scale Image Classification," 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, 2013, pp. 843-850. [pdf] [poster]