In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D …
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design …
Stochastic optimization algorithms have been popular for training deep neural networks. Recently, there emerges a new approach of learning-based optimizer, which has achieved promising performance …
This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of…
We propose and experimentally demonstrate a slit beam shaping method for femtosecond laser Point-by-Point (PbP) inscription of highly localized Fiber Bragg Gratings (FBGs). The influence of slit wi…
Multicore fibers (MCFs) have attracted intense attention to overcome the capacity limit of single-core optical fiber communication system. However, as indispensable connection devices between the M…
We theoretically and experimentally investigate broadband manipulation of Stokes frequency comb generation in a silica microbottle resonator. We realize selective excitation of spectrally trapped S…
Visible light communication (VLC) based on light-emitting diodes (LEDs) is supposed as a candidate in 6G networks because it can provide illumination and wireless communication simultaneously. As t…
Based on the Nd: YVO 4 microchip laser frequency-shifted feedback system, we carry out the detection of ultra-weak light signals, and verify that the response limit of the proposed system can reach…
InGaN-based orange-red resonant cavity light-emitting diodes (RCLEDs), were fabricated by using an AlN current-confinement aperture and double dielectric distributed Bragg reflectors (DBRs). For re…