This paper studies the use of discrete-time recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the c...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
Abstract--In this paper we propose a probabilistic classification algorithm with a novel Dynamic Time Warping (DTW) kernel to automatically recognize flight calls of different spec...
Theodoros Damoulas, Samuel Henry, Andrew Farnswort...
Many existing systems for human body tracking are based on dynamic model-based tracking that is driven by local image features. Alternatively, within a view-based approach, tracki...
Abstract. Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to le...