FNA++ : Fast Network Adaptation via Parameter Remapping and Architecture Search
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectu…
A 1.4-kW Mode-Controllable Fiber Laser System
We demonstrated a mode-controllable fiber laser system with output power of 1.4 kW level. The system consists of a kilowatt-scale master oscillator power amplifier and an active feedback control sy…
Enhancing the Visibility of Vernier Effect in a Tri-Microfiber Coupler Fiber …
In this article a Vernier effect based sensor is analyzed and demonstrated experimentally in a tri-microfiber coupler (Tri-MFC) and polarization-maintaining fiber (PMF) loop interferometer (Tri-MFC…
Optimal Sparse Linear Prediction for Block-missing Multi-modality Data Withou…
In modern scientific research, data are often collected from multiple modalities. Since different modalities could provide complementary information, statistical prediction methods using multimodal…
Side-Polished Single-Mode-Multimode-Single-Mode Fiber Structure for the Vecto…
A vector magnetometer, composed of a side-polished single-mode-multimode-single-mode fiber structure coated with ferrofluids, is proposed and investigated. The side-polishing of the multimode fiber…
Object Detection from Scratch with Deep Supervision
In this paper, we propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-th…
Karya Umum 
Filsafat 
Agama 
Ilmu-ilmu Sosial 
Bahasa 
Ilmu-ilmu Murni 
Ilmu-ilmu Terapan 
Kesenian, Hiburan, dan Olahraga 
Kesusastraan 
Geografi dan Sejarah