I am a Professor of Computer Science at KTH, Sweden, and the Head of the Computer Vision and Active Perception Lab.
My research concerns learning models of perception and production of non-verbal communicative behavior. Such models can be used to create richer human-robot and human-avatar interaction, for medical diagnosis systems, and for contextual synthesis of different kinds of human behaviors, e.g., guiding synthesis of hand motion from body motion.
I will be visiting the Perceiving Systems Department on a regular, bi-weekly basis until March 2017.
computer vision robotics machine learning human motion non-verbal communication
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017, IEEE, Piscataway, NJ, USA, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)
Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems