IEEE

A Semi-Supervised Data Center Network Traffic Classification Method Based on Multi-Source Domain Adaptation

Abstract: To address the issue of insufficient generalization ability in traffic classification models caused by distribution discrepancies between domains and the scarcity of labels in the target ...
IEEE

Semi-Supervised Triple-GAN With Similarity Constraint for Automatic Underground Object Classification Using Ground Penetrating Radar Data

Abstract: Automatic underground object classification based on deep learning (DL) has been widely used in ground penetrating radar (GPR) fields. However, its excellent performance heavily depends on ...
GitHub

Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

SHeaP learns to predict head geometry (FLAME parameters) from a single image, by predicting and rendering 2D Gaussians. This repository contains code and models for the FLAME parameter inference only.
Morningstar

AmberSemi Announces Silicon Tape-Out of PowerTile™ Vertical Power Solution for AI Data Centers

DUBLIN, Calif., Jan. 27, 2026 /PRNewswire/ -- Amber Semiconductor, Inc. (AmberSemi™), a fabless semiconductor company pioneering the next generation of power management for data centers, today ...
siliconera

Code Vein II Character Customization Appearance Data Disappearing

The problem with Character Customization save data disappearing happens if someone resumes a Code Vein II file by choosing to either load a save or hitting continue. If they do that and then enter ...
GitHub

orange-data-mining

This project combines machine learning with data science implemented in a python environment. Completed as my Master's degree practicum, it displays skills in data analytics as well as intermediate ...