Michael Isard

Learn More
The problem of tracking curves in dense visual clutter is a challenging one. Trackers based on Kalman lters are of limited use; because they are based on Gaussian densities which are unimodal, they cannot represent simultaneous alternative hypotheses. Extensions to the Kalman lter to handle multiple data associations work satisfactorily in the simple case(More)
The analysis of visual motion against dense background clutter is a challenging problem. Uncertainty in the positions of visually sensed features and ambiguity of feature correspondence call for a probabilistic treatment, capable of maintaining not simply a single estimate of position and shape but an entire distribution. Exact representation of the(More)
Condensation, recently introduced in the computer vision literature, is a particle ltering algorithm which represents a tracked ob-ject's state using an entire probability distribution. Clutter can cause the distribution to split temporarily into multiple peaks, each representing a diierent hypothesis about the object connguration. When measurements become(More)
Standard, exact techniques, based on likelihood maximisation, are available for learning Auto-Regressive process models of dynamical processes. The uncertainty of observations obtained from real sensors means that dynamics can be observed only approximately. Learning can still be achieved via \EM-K" | Expectation-Maximisation (EM) based on Kalman Filtering.(More)
TensorFlow is a powerful, programmable system for machine learning. This paper aims to provide the basics of a conceptual framework for understanding the behavior of TensorFlow models during training and inference: it describes an operational semantics, of the kind common in the literature on programming languages. More broadly, the paper suggests that a(More)
  • 1