Andreas Savakis
Papers
2
Total Citations
22
H-Index
2
About
Andreas Savakis is a leading researcher in computer vision and robotics, with a focus on object detection, pose estimation, and feature engineering. His work has significantly advanced the reliability of vision-based systems for real-world applications. Notably, his 2015 paper on "Lean histogram of oriented gradients features for effective eye detection" (18 citations) improved the efficiency of the classic HOG descriptor, making object detection more practical for robotics and human-computer interaction. More recently, his 2023 work "DeepRM: Deep Recurrent Matching for 6D Pose Refinement" (4 citations) introduces a novel recurrent network architecture that refines coarse 6D pose estimates from RGB images—a critical capability for augmented reality and robotic manipulation. Savakis’s contributions bridge traditional hand-crafted features with modern deep learning, demonstrating a sustained impact on both foundational and cutting-edge problems. His research continues to shape how machines perceive and interact with their environment, making his work essential reading for students and researchers in computer vision.
Research Focus
Key Achievements
Top Papers
- 1Lean histogram of oriented gradients features for effective eye detection18 citations · 2015
- 2DeepRM: Deep Recurrent Matching for 6D Pose Refinement4 citations · 2023