Machine Learning - HRI-US
This position focuses on developing learning framework for video saliency in driving scene utilizing a unique on-road driving data that includes scene videos, vehicle states as well as expert drivers' gaze information.
- Develop novel machine learning algorithm and evaluate the performance on video saliency estimation
- Develop meaningful metrics to evaluate the proposed approach
- PhD candidate in computer science, electrical engineering, or related field
- Strong familiarity and research experience in computer vision, machine learning, including sequential modeling, multimodal signal fusion, and deep learning
- Excellent programming skills in Python and C++
- Experience in TensorFlow (or Cafee) preferred