← Search

Iason Oikonomidis

2 accepted papers

2026

Y-MAP-Net: Learning from Foundation Models for Real-Time, Multi-Task Scene Perception

ICRA 2026poster

We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net simultaneously predicts depth, surface normals, human pose, semantic segmentation, and generates multi-label captions in a single forward pass. To achieve this, we adopt a…

Cited by 0Scholar
2018

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals

CVPR 2018poster

In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate the top 10 state-of-the-art methods o…

Cited by 277SourcePDFScholar