83 citations · 457 across the 62 of their papers we have counts for
17 papers · 1 filter
Orthogonal SVD Covariance Conditioning and Latent Disentanglement
Yue Song, Nicu Sebe, Wei Wang
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities.…
Numerical investigations on the resonance errors of multiscale discontinuous Galerkin methods for one-dimensional stationary Schrödinger equation
Bo Dong, Wei Wang
In this paper, numerical experiments are carried out to investigate the impact of penalty parameters in the numerical traces on the resonance errors of high order multiscale discon…
Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer
Leyuan Qu, Wei Wang, Cornelius Weber +3
Humans can effortlessly modify various prosodic attributes, such as the placement of stress and the intensity of sentiment, to convey a specific emotion while maintaining consisten…
Deflection of charged signals in a dipole magnetic field in Schwarzschild background using Gauss-Bonnet theorem
Zonghai Li, Wei Wang, Junji Jia
This paper studies the deflection of charged particles in a dipole magnetic field in Schwarzschild spacetime background in the weak field approximation. To calculate the deflection…
Neural network facilitated ab initio derivation of linear formula: A case study on formulating the relationship between DNA motifs and gene expression
Chengyu Liu, Wei Wang
Developing models with high interpretability and even deriving formulas to quantify relationships between biological data is an emerging need. We propose here a framework for ab in…
Check on the features of potted 20-inch PMTs with 1F3 electronics prototype at Pan-Asia
Caimei Liu, Min Li, Zhimin Wang +34
The Jiangmen underground neutrino observatory (JUNO) is a neutrino project with a 20-kton liquid scintillator detector located at 700-m underground. The large 20-inch PMTs are one…
Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation
Jichao Zhang, Aliaksandr Siarohin, Yahui Liu +3
Generative Neural Radiance Fields (GNeRF)-based 3D-aware GANs have showcased remarkable prowess in crafting high-fidelity images while upholding robust 3D consistency, particularly…
Transverse-momentum-dependent wave functions and Soft functions at one-loop in Large Momentum Effective Theory
Zhi-Fu Deng, Wei Wang, Jun Zeng
In large-momentum effective theory (LaMET), the transverse-momentum-dependent (TMD) light-front wave functions and soft functions can be extracted from the simulation of a four-qua…
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
Yue Song, Nicu Sebe, Wei Wang
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities.…
Unsupervised High-Resolution Portrait Gaze Correction and Animation
Jichao Zhang, Jingjing Chen, Hao Tang +5
This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotat…
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
Yue Song, Nicu Sebe, Wei Wang
The Fine-Grained Visual Categorization (FGVC) is challenging because the subtle inter-class variations are difficult to be captured. One notable research line uses the Global Covar…
Deep-learning-based prediction of nanoparticle phase transitions during in situ transmission electron microscopy
Wenkai Fu, Steven R. Spurgeon, Chongmin Wang +3
We develop the machine learning capability to predict a time sequence of in-situ transmission electron microscopy (TEM) video frames based on the combined long-short-term-memory (L…
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
Bin Ren, Yahui Liu, Yue Song +4
Position Embeddings (PEs), an arguably indispensable component in Vision Transformers (ViTs), have been shown to improve the performance of ViTs on many vision tasks. However, PEs…
Generalized common index jump theorem with applications to closed characteristics on star-shaped hypersurfaces and beyond
Huagui Duan, Hui Liu, Yiming Long +1
In this paper, we first generalize the common index jump theorem of Long-Zhu in 2002 and Duan-Long-Wang in 2016 to the case where the mean indices of symplectic paths are not requi…
The early stage of the interaction between a planar shock and a cylindrical droplet considering cavitation effects: theoretical analysis and numerical simulation
Sheng Xu, Wenqi Fan, Wangxia Wu +2
The interaction between planar shock waves and droplets, involved the evolution of high transient unsteady wave structures and the induced cavitation process, occurs widely in natu…
Efficient Distinction between Quantum Direct and Common Causes and its Experimental Verification
Feixiang Xu, Jia-Yi Lin, Ben Wang +4
Identifying the causal structures between two statistically correlated events has been widely investigated in many fields of science. While some of the well-studied classical metho…
A Two-Level Block Preconditioned Jacobi-Davidson Method for Multiple and Clustered Eigenvalues of Elliptic Operators
Qigang Liang, Wei Wang, Xuejun Xu
In this paper, we propose a two-level block preconditioned Jacobi-Davidson (BPJD) method for efficiently solving discrete eigenvalue problems resulting from finite element approxim…