Research activities

Gesture recognition and pose estimation

We work on pose estimation (hand pose or full body pose) and recognition of hand and/or full body gestures from multiple modalities, in particular depth images, aiming intentional gestures bearing communicative function

Computer Vision for robotics

Computer vision for service robotics: human-robot interaction, vision for fleet coordination etc. VOIR - an intelligent vision plateform

Deep learning for computer vision

The goal is to automatically learn invariant and discriminative hierarchical representations for various applications from labelled and unlabelled data. A particular emphasis is put on integration structural information into learning machines through structured output learning or by structuring the prediction model itself.

Document image analysis

I am interested in models addressing fundamental problems in document image analysis: restoration, segmentation, and structure recognition. Machine learning plays a central role in this research, as do structured models and graphical models. One of our current goals concerns the integration of structured information and structured terms into deep networks.

Activity recognition

Recognition of simple and complex behavior in video sequences.

Image and video segmentation

Semantic scene labelling, i.e. semantic segmentation of natural images; segmentation of document images. Key methodologies are deep learning and graphical models.

Mesh analysis

Segmentation and semantic analysis of 3D meshes. Remeshing (mesh optimization).

Evaluation of computer vision algorithms