no code implementations • 23 Dec 2023 • Lu Xia, Stefano Massei
Adaptive first-order optimizers are fundamental tools in deep learning, although they may suffer from poor generalization due to the nonuniform gradient scaling.
1 code implementation • 4 Aug 2023 • Xuefeng Hu, Ke Zhang, Lu Xia, Albert Chen, Jiajia Luo, Yuyin Sun, Ken Wang, Nan Qiao, Xiao Zeng, Min Sun, Cheng-Hao Kuo, Ram Nevatia
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e. g. achieving 76. 3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data.
no code implementations • 23 Jan 2023 • Lu Xia, Michiel E. Hochstenbach, Stefano Massei
When training neural networks with low-precision computation, rounding errors often cause stagnation or are detrimental to the convergence of the optimizers; in this paper we study the influence of rounding errors on the convergence of the gradient descent method for problems satisfying the Polyak-Lojasiewicz inequality.
no code implementations • 8 Jan 2023 • Cheng-Yen Yang, Jiajia Luo, Lu Xia, Yuyin Sun, Nan Qiao, Ke Zhang, Zhongyu Jiang, Jenq-Neng Hwang
By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D.
Ranked #68 on 3D Human Pose Estimation on Human3.6M
no code implementations • 24 Feb 2022 • Lu Xia, Stefano Massei, Michiel E. Hochstenbach, Barry Koren
When implementing the gradient descent method in low precision, the employment of stochastic rounding schemes helps to prevent stagnation of convergence caused by the vanishing gradient effect.
no code implementations • 24 Mar 2021 • Lu Xia, Martijn Anthonissen, Michiel Hochstenbach, Barry Koren
Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations.
no code implementations • 31 May 2020 • Lu Xia, Martijn Anthonissen, Michiel Hochstenbach, Barry Koren
When a sequence of computations is implemented, round-off errors may be magnified or accumulated.
no code implementations • 20 Jun 2014 • M. S. Ryoo, Thomas J. Fuchs, Lu Xia, J. K. Aggarwal, Larry Matthies
In this paper, we propose a methodology for early recognition of human activities from videos taken with a first-person viewpoint.
no code implementations • CVPR 2013 • Lu Xia, J. K. Aggarwal
Local spatio-temporal interest points (STIPs) and the resulting features from RGB videos have been proven successful at activity recognition that can handle cluttered backgrounds and partial occlusions.
no code implementations • 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2012 • Lu Xia, Chia-Chih Chen, J. K. Aggarwal
Our method is real-time and achieves superior results on the challenging 3D action dataset.
Ranked #3 on Skeleton Based Action Recognition on UWA3D