Machine Learning & Data Analytics

In this work, we review autonomous camera systems developed over the past twenty years.

We introduce a set of Game Context Features extracted from noisy detections to describe the current state of the match, such as how the players are spatially distributed.

In this paper, we present an unimodal interface concept that allows one person to cover live sporting action by controlling multiple cameras and and determining which view to broadcast.

In this paper, we develop a new model for recognizing human actions.

In this paper, we propose a structured kernel machine approach to treat object detection and pose estimation jointly in a mutually beneficial way.

We propose a hierarchical generalization of the ddCRP which clusters data within groups based on distances between data items, and couples clusters across groups via distances based on aggregate properties of these local clusters.

We propose a new weakly-supervised structured learning approach for recognition and spatio-temporal localization of actions in video.

We present a hierarchical model for human activity recognition in entire multi-person scenes.

Automatic recovery of 3d pose of multiple interacting subjects from unconstrained monocular image sequence is a challenging and largely unaddressed problem.

We present a type of Temporal Restricted Boltzmann Machine that defines a probability distribution over an output sequence conditional on an input sequence.