no code implementations • 2 Apr 2024 • Jiaming Liang, Yongxin Chen
Finally, we combine this proximal sampling oracle and ASF to obtain a Markov chain Monte Carlo method with non-asymptotic complexity bounds for sampling in semi-smooth and composite settings.
1 code implementation • 29 Mar 2024 • Runhao Zeng, Xiaoyong Chen, Jiaming Liang, Huisi Wu, Guangzhong Cao, Yong Guo
In this paper, we extensively analyze the robustness of seven leading TAD methods and obtain some interesting findings: 1) Existing methods are particularly vulnerable to temporal corruptions, and end-to-end methods are often more susceptible than those with a pre-trained feature extractor; 2) Vulnerability mainly comes from localization error rather than classification error; 3) When corruptions occur in the middle of an action instance, TAD models tend to yield the largest performance drop.
no code implementations • 26 Feb 2024 • Jiaming Liang, Siddharth Mitra, Andre Wibisono
We study the rate at which the initial and current random variables become independent along a Markov chain, focusing on the Langevin diffusion in continuous time and the Unadjusted Langevin Algorithm (ULA) in discrete time.
no code implementations • 14 Feb 2024 • Jiaming Liang
This paper proposes a stochastic proximal point method to solve a stochastic convex composite optimization problem.
no code implementations • 16 Oct 2023 • Xiuli Bi, Jiaming Liang
In existing splicing forgery datasets, the insufficient semantic varieties of spliced regions cause a problem that trained detection models overfit semantic features rather than splicing traces.
no code implementations • 2 Jun 2023 • Jiaming Liang, Lei Cao, Samuel Madden, Zachary Ives, Guoliang Li
Timeseries analytics is of great importance in many real-world applications.
no code implementations • 26 Mar 2023 • Nermin Caber, Bashar I. Ahmad, Jiaming Liang, Simon Godsill, Alexandra Bremers, Philip Thomas, David Oxtoby, Lee Skrypchuk
Monitoring drivers' mental workload facilitates initiating and maintaining safe interactions with in-vehicle information systems, and thus delivers adaptive human machine interaction with reduced impact on the primary task of driving.
no code implementations • 16 Mar 2023 • Jiaming Liang, Meiqin Liu, Chao Yao, Chunyu Lin, Yao Zhao
Variable-rate mechanism has improved the flexibility and efficiency of learning-based image compression that trains multiple models for different rate-distortion tradeoffs.
no code implementations • 31 Oct 2022 • Jiaming Liang, Chao Xu, Shengze Cai
By introducing a novel deep neural network based on recurrent Graph Optimal Transport, called GotFlow3D, we present an end-to-end solution to learn the 3D fluid flow motion from double-frame particle sets.
no code implementations • 20 May 2022 • Jiaming Liang, Yongxin Chen
This work extends the recent algorithm in \cite{LiaChe21, LiaChe22} for non-smooth/semi-smooth log-concave distribution to the setting with non-convex potentials.
no code implementations • 10 May 2022 • Xiaochun Lei, Linjun Lu, Zetao Jiang, Zhaoting Gong, Chang Lu, Jiaming Liang
Through this relationship, regions receiving much attention are integrated into the segmentation results, thereby reducing the unfocused regions of the input image and improving the effective utilization of multiscale features.
no code implementations • 28 Feb 2022 • Jiaming Liang, Yongxin Chen
Departing from the standard smooth setting, the potentials are only assumed to be weakly smooth or non-smooth, or the summation of multiple such functions.
no code implementations • 9 Oct 2021 • Jiaming Liang, Yongxin Chen
One key contribution of this work is a fast algorithm that realizes the restricted Gaussian oracle for any convex non-smooth potential with bounded Lipschitz constant.
1 code implementation • ACL 2021 • Yilin Niu, Fei Huang, Jiaming Liang, Wenkai Chen, Xiaoyan Zhu, Minlie Huang
In this paper, we present a novel SEmantic-based Question Answering method (SEQA) for unsupervised commonsense question answering.