Thomas Plötz

Fine-grained Human Activity Recognition Using Virtual On-body Acceleration Data

Previous work has demonstrated that virtual accelerometry data, extracted from videos using cross-modality transfer approaches like IMUTube, is beneficial for training complex and effective human...

Detecting home locations from CDR data: introducing spatial uncertainty to the state-of-the-art

Non-continuous location traces inferred from Call Detail Records (CDR) at population scale are increasingly becoming available for research and show great potential for automated detection of...

Towards Using Unlabeled Data in a Sparse-coding Framework for Human Activity Recognition

We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It...

Occupancy monitoring using environmental & context sensors and a hierarchical analysis framework

Automated surgical OSATS prediction from videos

Segmentation of organs in pig offal using auto-context

Interactive Architecture: Exploring and Unwrapping the Potentials of Organic User Interfaces

On the Application of SVM-Ensembles Based on Adapted Random Subspace Sampling for Automatic Classification of NMR Data

Stacking for Ensembles of Local Experts in Metabonomic Applications

Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models

Emotion Recognition on the Go: Utilizing Wearable IMUs for Personalized Emotion Recognition

Solving the Sensor-Based Activity Recognition Problem (SOAR): Self-Supervised, Multi-Modal Recognition of Activities from Wearable Sensors

Robust time-synchronous environmental adaptation for continuous speech recognition systems

A Multi-modal Attention System for Smart Environments

Towards a pervasive kitchen infrastructure for measuring cooking competence

Measuring Self-Esteem with Passive Sensing

BlobSnake: gamification of feature extraction for 'plug and play' human activity recognition

Adding structural characteristics to distribution-based accelerometer representations for activity recognition using wearables