[Computer Vision] Video Captioning in Traffic Scenes - HRI-US
[Computer Vision] Video Captioning in Traffic Scenes
You are expected to:
- Use video inputs to generate natural language description of important or unstructured traffic scene events that impact the driver's decision making and motion planning strategies.
- Participate in creating a dataset to support activities in video-based captioning of traffic scenes.
- Develop and evaluate metrics to verify reliability of the proposed algorithms.
- Contribute to a portfolio of patents, academic publications, and prototypes to demonstrate research value.
- Ph.D. or highly qualified M.S. candidate in computer science, electrical engineering, or related field.
- Strong familiarity with computer vision and machine learning techniques pertaining to video captioning.
- Excellent programming skills in Python or C++.
- Familiarity with creating datasets for video captioning, including visual question and answering methods is preferred for one position.
Experience in open-source deep learning frameworks such as TensorFlow or PyTorch preferred.
Duration: 3 months