Search Results for author:
Found 5 papers, 2 papers with code
Experiment-based deep learning approach for power allocation with a programmable metasurface
Enabled by the tunability of a programmable metasurface, large sets of experimental data in various configurations can be collected for DNN training.
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer.
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers
We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds.
Accurate and Compact Convolutional Neural Networks with Trained Binarization
Recently, binary convolutional neural networks are explored to help alleviate this issue by quantizing both weights and activations with only 1 single bit.
A Robust Background Initialization Algorithm with Superpixel Motion Detection
Scene background initialization allows the recovery of a clear image without foreground objects from a video sequence, which is generally the first step in many computer vision and video processing applications.
