I am a first year PhD student at the Computer Vision and Active Perception Lab, CSC, at KTH in Stockholm, Sweden. My research focuses on human-human and human-robot interaction and computational models thereof.
In more detail, I am interested in how low-level action-perception loops can give rise to high-level social cognition, see the EU project socSMCs (social Sensorimotor Contingencies).
From mid April to mid Juli 2016 I am doing an internship at the Perceiving Systems Department. My focus during this time will lie on the application of Deep Gaussian Processes to interaction scenarios.
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