Search Results - "Bai, Qinxun"

Moment Matching for Multi-Source Domain Adaptation by Peng, Xingchao, Bai, Qinxun, Xia, Xide, Huang, Zijun, Saenko, Kate, Wang, Bo

“…Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where…”
Get full text

Randomized Ensemble Tracking by Qinxun Bai, Zheng Wu, Sclaroff, Stan, Betke, Margrit, Monnier, Camille

“…We propose a randomized ensemble algorithm to model the time-varying appearance of an object for visual tracking. In contrast with previous online methods for…”
Get full text

PCA-based structure refinement for reconstruction of urban scene by Qinxun Bai, Yihong Wu, Lixin Fan

“…There is plenty of structured information (such as lines and planes) in urban scenes. Considering this, we propose a new method for making use of this…”
Get full text

Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers by Feng, Qi, Ablavsky, Vitaly, Bai, Qinxun, Sclaroff, Stan

“…We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL)…”
Get full text

Real-time Visual Object Tracking with Natural Language Description by Feng, Qi, Ablavsky, Vitaly, Bai, Qinxun, Li, Guorong, Sclaroff, Stan

“…In this work, we argue that conditioning on the natural language (NL) description of a target provides information for longer-term invariance, and thus helps…”
Get full text

The Differential Geometric Structure in Supervised Learning of Classifiers by Bai, Qinxun

“…In this thesis, we study the overfitting problem in supervised learning of classifiers from a geometric perspective. As with many inverse problems, learning a…”
Get full text

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA by Smerkous, David, Bai, Qinxun, Li, Fuxin

“…Particle-based Bayesian deep learning often requires a similarity metric to compare two networks. However, naive similarity metrics lack permutation invariance…”
Get full text

Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulations by Gasztowtt, Henry, Smith, Benjamin, Zhu, Vincent, Bai, Qinxun, Zhang, Edwin

“…The improvement of economic policymaking presents an opportunity for broad societal benefit, a notion that has inspired research towards AI-driven policymaking…”
Get full text

A Geometric Understanding of Natural Gradient by Bai, Qinxun, Rosenberg, Steven, Xu, Wei

“…While natural gradients have been widely studied from both theoretical and empirical perspectives, we argue that some fundamental theoretical issues regarding…”
Get full text

Offline Reinforcement Learning with Closed-Form Policy Improvement Operators by Li, Jiachen, Zhang, Edwin, Yin, Ming, Bai, Qinxun, Wang, Yu-Xiang, Wang, William Yang

“…Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting…”
Get full text

Generative Particle Variational Inference via Estimation of Functional Gradients by Ratzlaff, Neale, Bai, Qinxun, Fuxin, Li, Xu, Wei

“…Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in…”
Get full text

Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction by Li, Jiachen, Cheng, Shuo, Liao, Zhenyu, Wang, Huayan, Wang, William Yang, Bai, Qinxun

“…Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face…”
Get full text

Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers by Feng, Qi, Ablavsky, Vitaly, Bai, Qinxun, Sclaroff, Stan

“…We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL)…”
Get full text

Implicit Generative Modeling for Efficient Exploration by Ratzlaff, Neale, Bai, Qinxun, Fuxin, Li, Xu, Wei

“…Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A…”
Get full text

Real-time Visual Object Tracking with Natural Language Description by Feng, Qi, Ablavsky, Vitaly, Bai, Qinxun, Li, Guorong, Sclaroff, Stan

“…In recent years, deep-learning-based visual object trackers have been studied thoroughly, but handling occlusions and/or rapid motion of the target remains…”
Get full text

A Topological Regularizer for Classifiers via Persistent Homology by Chen, Chao, Ni, Xiuyan, Bai, Qinxun, Wang, Yusu

“…Regularization plays a crucial role in supervised learning. Most existing methods enforce a global regularization in a structure agnostic manner. In this…”
Get full text

A Bayesian Approach for Online Classifier Ensemble by Bai, Qinxun, Lam, Henry, Sclaroff, Stan

“…We propose a Bayesian approach for recursively estimating the classifier weights in online learning of a classifier ensemble. In contrast with past methods,…”
Get full text

Moment Matching for Multi-Source Domain Adaptation by Peng, Xingchao, Bai, Qinxun, Xia, Xide, Huang, Zijun, Saenko, Kate, Wang, Bo

“…Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where…”
Get full text

Class Probability Estimation via Differential Geometric Regularization by Bai, Qinxun, Rosenberg, Steven, Wu, Zheng, Sclaroff, Stan

“…We study the problem of supervised learning for both binary and multiclass classification from a unified geometric perspective. In particular, we propose a…”
Get full text