Zobrazeno 1 - 10
of 345
pro vyhledávání: '"Wang, Zipeng"'
Autor:
Han, Xumeng, Wei, Longhui, Dou, Zhiyang, Wang, Zipeng, Qiang, Chenhui, He, Xin, Sun, Yingfei, Han, Zhenjun, Tian, Qi
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure into the clas
Externí odkaz:
http://arxiv.org/abs/2410.15732
Reconfigurable Intelligent Surface (RIS) is a promising technology that may effectively improve the quality of signals in wireless communications. In practice, however, the ``double fading'' effect undermines the application of RIS and constitutes a
Externí odkaz:
http://arxiv.org/abs/2410.12355
Autor:
Wang, Zipeng
We study a family of convolution operators whose kernels have singularity on $\mathbb{S}^{N-1}$. By considering a generalized, multi-parameter variant of Sobolev spaces, we prove the regarding Sobolev $L^p$-norm inequalities. As an application, we gi
Externí odkaz:
http://arxiv.org/abs/2410.07781
We solve a long-standing open problem of determining the Fourier dimension of the Mandelbrot canonical cascade measure (MCCM). This problem of significant interest was raised by Mandelbrot in 1976 and reiterated by Kahane in 1993. Specifically, we de
Externí odkaz:
http://arxiv.org/abs/2409.13164
Autor:
Tan, Chaoqiang, Wang, Zipeng
We study a family of Fourier integral operators by allowing their symbols to satisfy a multi-parameter differential inequality on R^N. We show that these operators of order -(N-1)/2 are bounded from classical, atom decomposable H^1-Hardy space to L^1
Externí odkaz:
http://arxiv.org/abs/2408.09691
Autor:
Tan, Chaoqiang, Wang, Zipeng
We investigate a class of Fourier integral operators with weakened symbols, which satisfy a multi-parameter differential inequality in $\R^n$. We establish that these operators retain the classical $L^p$ boundedness and the $H^1$ to $L^1$ boundedness
Externí odkaz:
http://arxiv.org/abs/2408.03211
Publikováno v:
ECCV2024
Reconstructing intensity frames from event data while maintaining high temporal resolution and dynamic range is crucial for bridging the gap between event-based and frame-based computer vision. Previous approaches have depended on supervised learning
Externí odkaz:
http://arxiv.org/abs/2407.18500
Given any cancellative monoid $\mathcal{M}$, we study the Hankel system determined by its multiplication table. We prove that the Hankel system admits self-absorption property provided that the monoid $\mathcal{M}$ has the local algebraic structure:
Externí odkaz:
http://arxiv.org/abs/2407.01048
Autor:
Wang, Zipeng, Xu, Dan
Neural Radiance Fields (NeRFs) have demonstrated remarkable proficiency in synthesizing photorealistic images of large-scale scenes. However, they are often plagued by a loss of fine details and long rendering durations. 3D Gaussian Splatting has rec
Externí odkaz:
http://arxiv.org/abs/2405.16829
Continuous space-time video super-resolution (C-STVSR) aims to simultaneously enhance video resolution and frame rate at an arbitrary scale. Recently, implicit neural representation (INR) has been applied to video restoration, representing videos as
Externí odkaz:
http://arxiv.org/abs/2405.13389