78 citations · 196 across the 15 of their papers we have counts for
15 papers
PGrad: Learning Principal Gradients For Domain Generalization
Zhe Wang, Jake Grigsby, Yanjun Qi
Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG t…
PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation
Haoyu Ma, Zhe Wang, Yifei Chen +6
Recently, the vision transformer and its variants have played an increasingly important role in both monocular and multi-view human pose estimation. Considering image patches as to…
The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation
Zhe Wang, Jimei Yang, Charless Fowlkes
Nonparametric based methods have recently shown promising results in reconstructing human bodies from monocular images while model-based methods can help correct these estimates an…
Deep self-consistent learning of local volatility
Zhe Wang, Ameir Shaa, Nicolas Privault +1
We present an algorithm for the calibration of local volatility from market option prices through deep self-consistent learning, by approximating both market option prices and loca…
Online Adversarial Knowledge Distillation for Graph Neural Networks
Can Wang, Zhe Wang, Defang Chen +3
Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both…
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
Zhe Wang, Jake Grigsby, Arshdeep Sekhon +1
Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning…
Long-Range Transformers for Dynamic Spatiotemporal Forecasting
Jake Grigsby, Zhe Wang, Nam Nguyen +1
Multivariate time series forecasting focuses on predicting future values based on historical context. State-of-the-art sequence-to-sequence models rely on neural attention between…
Reconstructing a dynamical system and forecasting time series by self-consistent deep learning
Zhe Wang, Claude Guet
We introduce a self-consistent deep-learning framework which, for a noisy deterministic time series, provides unsupervised filtering, state-space reconstruction, identification of…
Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy
Shuang Xu, Lizhen Ji, Zhe Wang +4
Multi-focus image fusion (MFF) is a popular technique to generate an all-in-focus image, where all objects in the scene are sharp. However, existing methods pay little attention to…
Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge
Arshdeep Sekhon, Zhe Wang, Yanjun Qi
Learning the differential statistical dependency network between two contexts is essential for many real-life applications, mostly in the high dimensional low sample regime. In thi…
Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Zhe Wang, Liyan Chen, Shaurya Rathore +2
Full 3D estimation of human pose from a single image remains a challenging task despite many recent advances. In this paper, we explore the hypothesis that strong prior information…
Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization
Yi Zhou, Zhe Wang, Kaiyi Ji +2
Two new stochastic variance-reduced algorithms named SARAH and SPIDER have been recently proposed, and SPIDER has been shown to achieve a near-optimal gradient oracle complexity fo…
Variational Disparity Estimation Framework for Plenoptic Image
Trung-Hieu Tran, Zhe Wang, Sven Simon
This paper presents a computational framework for accurately estimating the disparity map of plenoptic images. The proposed framework is based on the variational principle and prov…
Internet Traffic Matrix Structural Analysis Based on Multi-Resolution RPCA
Zhe Wang, Kai Hu, Baolin Yin
The Internet traffic matrix plays a significant roll in network operation and management, therefore, the structural analysis of traffic matrix, which decomposes different traffic c…
Baselining Network-Wide Traffic by Time-Frequency Constrained Stable Principal Component Pursuit
Kai Hu, Zhe Wang, Baolin Yin
The Internet traffic analysis is important to network management,and extracting the baseline traffic patterns is especially helpful for some significant network applications.In thi…