Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud …
Physical Unclonable Function (PUF) serves as a physical security primitive that cannot be feasibly duplicated and has diversified applications in the field of hardware security. Although optical PU…
This paper is concerned with causal mediation analysis with varying indirect and direct effects. We propose a varying coefficient mediation model, which can also be viewed as an extension of modera…
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation with spatially-va…
Estimations and applications of factor models often rely on the crucial condition that the number of latent factors is consistently estimated, which in turn also requires that factors be relatively…
Microwave photonic interrogation of a high-speed and high-resolution multipoint refractive index (RI) sensor based on an Au-coated tilted fiber grating (Au-TFBG) array is proposed and experimentall…
Terahertz (THz) technology offers multifaceted capabilities and disruptive applications in line-of-sight wireless communication, highly sensitive (bio)sensing, imaging and so on. However, the sever…
Recently, in a series of papers [Y. Rahimi, C. Wang, H. Dong, and Y. Lou, SIAM J. Sci. Comput., 41 (2019), pp. A3649--A3672; C. Wang, M. Tao, J. Nagy, and Y. Lou, SIAM J. Imaging Sci., 14 (2021), p…
Estimating depth from multi-view images captured by a localized monocular camera is an essential task in computer vision and robotics. In this study, we demonstrate that learning a convolutional ne…