Non-negative matrix factorization (NMF) is an excellent tool for unsupervised parts-based learning, but proves to be ineffective when parts of a whole follow a specific pattern. ...
In the context of the RESUME-project a scalable wavelet-based video decoder was built to demonstrate the benefits of reconfigurable hardware for scalable applications. Scalable v...
Harald Devos, Hendrik Eeckhaut, Mark Christiaens, ...
This article focusses on the problems of feature extraction and the recognition of handwritten digits. A trainable feature extractor based on the LeNet5 convolutional neural netwo...
We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike ...
In this paper, we consider the problem of how to represent the locations of Internet hosts in a Cartesian coordinate system to facilitate estimate of the network distance between ...