Research

I was a PhD student in machine learning at KTH Royal Institute of Technology, 2017-2019, supervised by Hedvig Kjellström and Jana Tumova. My research was on probabilistic models, and on how prior knowledge could be used in model design.

My project was part of Wallenberg AI, Autonomous Systems and Software Program.

Publications

2018

• Murray, S. and Kjellström, H. Mixed Likelihood Gaussian Process Latent Variable Model (arXiv preprint arXiv:1811.07627)

2017

• Murray, S. Real-Time Multiple Object Tracking - A Study on the Importance of Speed (arXiv preprint arXiv:1709.03572)

• Barekatain, M., Martí, M., Shih, H. F., Murray, S., Nakayama, K., Matsuo, Y. and Prendinger, H. Okutama-Action: An aerial view video dataset for concurrent human action detection (In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 28-35))