Teaching & theses

In the fall term 2025, we are teaching the following courses:

• Human-Computer Interaction 2025 bachelor course
• Mixed Reality 2025 master course

Available student thesis projects

Please submit your CV and transcripts through SiROP. In case of questions, please contact us via SiROP.

• Multimodal Egocentric Computer Vision Understanding of Human Interaction

  Next-generation Computer Vision goes beyond recognizing actions to understand interactions. In this project, two participants with Project Aria glasses will be recorded during natural activities. Building on our recent work on egoPPG (ICCV'25) and egoEMOTION (NeurIPS'25), you will explore how multimodal egocentric signals, video, gaze, motion, and context, can be fused to model human interaction, coordination, and behavioral dynamics. All hardware (Project Aria glasses + extensions) will be provided.

  more...
  
  • contact: Christian Holz, Björn Braun
  • master's thesis

  • egocentric vision
  • human interaction
  • multimodal learning
  • behavioral AI
  • gaze
  • attention
  • human understanding

• Multimodal Deep Learning for Emotion Recognition from Egocentric and Physiological Data

  This project investigates how deep learning models can leverage egocentric vision and physiological signals to predict human emotions in real-world scenarios. By combining first-person visual data from smart glasses with concurrent physiological signals such as heart rate, respiration, and skin conductance, the goal is to model the underlying human affective states, including distinct emotions, personality types, and continuous affect. The project builds on egoEMOTION, a dataset we recently recorded that explores how wearable and camera-based sensing can be used to capture subtle cues of emotion and personality during naturalistic activities.

  more...
  
  • contact: Björn Braun
  • master's thesis

  • deep learning
  • affective computing
  • neural networks
  • health
  • mobile health

• Understanding LLM shortcuts in multiple-choice question answers

  This project aims to investigate shortcut behavior in LLMs when answering multiple-choice questions. We will programmatically generate multiple variants of the same dataset by introducing stylistic and structural variations, such as differences in tone and number of options, to identify and quantify the extent to which LLMs rely on unintended heuristics to achieve higher accuracy.

  more...
  
  • contact: Tommaso Bendinelli
  • semester's thesis

  • LLMs
  • Benchmarking
  • Machine Learning

• Multi-Camera Egocentric Hand Pose Estimation

  In this project, we aim to develop a new method for multi-camera egocentric hand pose estimation. Using cameras mounted on the head, wrists, and pelvis, the project explores how multiple egocentric viewpoints can be combined to overcome occlusions and achieve more accurate 3D hand tracking.

  more...
  
  • contact: Dominik Hollidt
  • semester's thesis
  • bachelor's thesis
  • master's thesis

  • Computer Vision
  • Deep Learning
  • Machine Learning
  • Hand Pose
  • Estimation

Current thesis students

• Ruizhe Zhu master's ETH Computer Science, D-INFK
• Liuxin Qing master's ETH Electrical Engineering, D-ITET
• Philipp Braune master's ETH Computer Science, D-INFK

• Tim Goppelsroeder semester ETH Computer Science, D-INFK

• Sebastian Hubold bachelor's ETH Computer Science, D-INFK

Past Courses and Seminars

• Mobile Health and Activity Monitoring master course
  • 2025
  • 2024
  • 2023
  • 2022
• Human-Computer Interaction bachelor course
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
• Mixed Reality master course
  • 2024
  • 2023
• Ubiquitous Computing master course
  • 2021
  • 2020
• Adaptive User Interfaces through Machine Learning bachelor seminar
  • 2025
• Egocentric Perception for Human-World Understanding master seminar
  • 2025
• Reinforcement Learning for Understanding and Modeling Human Behavior master seminar
  • 2025
• Advanced Topics in Mixed Reality bachelor seminar
  • 2024
  • 2023
  • 2022
• Advanced Topics in Technical Human-Computer Interaction bachelor seminar
  • 2021
  • 2020