Student Assistant to Support Social Interaction Dataset Capture

Studying human-scene and human-human interactions from visual input is important for understanding human behaviors, as well as many applications such as AR/VR. To that end, The VLG lab (Computer Vision and Learning Group) at ETH is currently working on data capture of a social interaction dataset to capture rich and complex interaction signals including body and hand poses, facial expression and gaze directions, and the goal is to capture 2 people interacting with each other in indoor rooms with 3 Azure Kinect cameras and a Hololens2 VR glasses. 

We are looking for students of ETH Zurich who can support the team up to 15 hrs/week (during semester) and up to 41 hrs/week (in semester break) as a student assistant for around 2 months, ​​from 10th May, 2022 or by arrangement.

Your responsibilities would include:

• help with the capture setup and during the capture: explain matters that need attention to participants, help to set up cameras
• process the captured data: examine the accuracy of Openpose 2D body joints detected from the captured videos

We are looking for students who:

• can speak fluent English
• are proficient with C++/Python, OpenCV, knowledge of computer vision

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit our to find out how we ensure a fair and open environment that allows everyone to grow and flourish.