Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...
In this paper we present a system that can synthesise novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from...
Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval syste...
Advances in data collection and storage have allowed organizations to create massive, complex and heterogeneous databases, which have stymied traditional methods of data analysis....
Stephen D. Bay, Dennis F. Kibler, Michael J. Pazza...
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a...
Raquel Urtasun, David J. Fleet, Aaron Hertzmann, P...