no code implementations • 29 Nov 2022 • Jiachen Li, Edwin Zhang, Ming Yin, Qinxun Bai, Yu-Xiang Wang, William Yang Wang
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning.
no code implementations • 13 Feb 2022 • Qinxun Bai, Steven Rosenberg, Wei Xu
While natural gradients have been widely studied from both theoretical and empirical perspectives, we argue that some fundamental theoretical issues regarding the existence of gradients in infinite dimensional function spaces remain underexplored.
no code implementations • 22 Oct 2021 • Jiachen Li, Shuo Cheng, Zhenyu Liao, Huayan Wang, William Yang Wang, Qinxun Bai
Improving the sample efficiency of reinforcement learning algorithms requires effective exploration.
no code implementations • 1 Mar 2021 • Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference.
1 code implementation • CVPR 2021 • Qi Feng, Vitaly Ablavsky, Qinxun Bai, Stan Sclaroff
We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL) descriptions task.
no code implementations • ICML 2020 • Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu
Each random draw from our generative model is a neural network that instantiates the dynamic function, hence multiple draws would approximate the posterior, and the variance in the future prediction based on this posterior is used as an intrinsic reward for exploration.
no code implementations • 26 Jul 2019 • Qi Feng, Vitaly Ablavsky, Qinxun Bai, Guorong Li, Stan Sclaroff
In benchmarks, our method is competitive with state of the art trackers, while it outperforms all other trackers on targets with unambiguous and precise language annotations.
3 code implementations • ICCV 2019 • Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo wang
Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain.
no code implementations • 27 Jun 2018 • Chao Chen, Xiuyan Ni, Qinxun Bai, Yusu Wang
In particular, our measurement of topological complexity incorporates the importance of topological features (e. g., connected components, handles, and so on) in a meaningful manner, and provides a direct control over spurious topological structures.
no code implementations • 8 Jul 2015 • Qinxun Bai, Henry Lam, Stan Sclaroff
We propose a Bayesian approach for recursively estimating the classifier weights in online learning of a classifier ensemble.
no code implementations • 4 Mar 2015 • Qinxun Bai, Steven Rosenberg, Zheng Wu, Stan Sclaroff
We study the problem of supervised learning for both binary and multiclass classification from a unified geometric perspective.