10.2018: Our interdisciplinary paper on pupil-based assesment of human cognitive load using Bayesian methods was presented at the ACM ICMI Modeling Cognitive Processes from Multimodal Data Workshop (ICMI-MCPMD).
08.2018: Two papers accepted at BMVC and ECCV Workshop! One paper about identifying previously unseen classes for action recognition in open-set scenario is accepted at the BMVC and one paper on assessing the performance of zero-shot action recognition algorithms when using external datasets was accepted at the ECCV Workshop on Shortcomings in Vision and Language.
07.2018: I participated in the International Computer Vision Summer School and presented our poster "Human Activity Recognition in Autonomous Vehicles"
My main research focus is deep learning-based recognition of human activities and interactions from video streams. I am especially interested in open-set, zero- and few-shot recognition as well as applying the developed models for driver monitoring in intelligent vehicles.
I am involved in the BMBF Project PAKoS (Personalisierte, adaptive kooperative Systeme für automatisierte Fahrzeuge), working on scene understanding inside autonomous cars. The goal of CV:HCI is real-time activity recognition under realistic driving conditions (e.g. varying or low illumination).
Bachelor/Master Thesis
If you are passionate about one of {machine learning, deep learning, computer vision} and want to apply what you have learned in the area of activity recognition / video comprehension in your thesis - please send me an email with a few sentences about yourself.
Supervised Theses
- Chaoxiang Ma, "Reliability of Deep Convolutional Neural Networks for Activity Recognition", Bachelor Thesis (running)
- Patrick Gebert, "Vehicle Maneuver Prediction with 3D Convolutional Neural Networks Based on Driver Observation", Master Thesis, 07.2018
- Tim Pollert, "Fusion Methods for Multimodal Gesture Recognition with Convolutional Neural Networks", Master Thesis, 06.2018
