Channel attention mechanisms have been commonly applied in many visual tasks for effective performance improvement. It is able to reinforce the informative channels as well as to suppress the usele…
Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works are mainly part-d…
By employing the mode decomposition method to study the relative mode evolution characteristics during the stimulated Raman scattering (SRS) process, a numerical model of the core-pumped Raman effe…
Orbital angular momentum (OAM) mode multiplexing provides a promising solution for enlarging communication capacity density. Although various OAM mode multiplexing technologies have been investigat…
Optical microresonators supported whispering gallery modes (WGMs) are one of the most cost-effective platforms for optical frequency comb generated due to their advantages of ultra-high quality ( Q…
In a chance constrained program (CCP), decision makers seek the best decision whose probability of violating the uncertainty constraints is within the prespecified risk level. As a CCP is often non…
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate overfitting and im…
In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering point clouds with disparity estimation…
Strategy-based equilibrium traffic assignment (SETA) problems define travel choice broadly as a strategy rather than a simple path. Travelers navigating through a network based on a strategy end up…
The achievement of cylindrical vector beam (CVB) multiplexing has shown advantages in enlarging communication capacities and all-optical interconnections. While various mode transformation technolo…