Motion is the strongest visual appeal to attention [2], yet it is rarely used in the visualization of large-scale quantitative information. Motion is complex; it can vary across n...
The ignorance on spatial information and semantics of visual words becomes main obstacles in the bag-of-visual-words (BoW) method for image classification. To address the obstacles...
Abstract. This paper explores techniques in the pipeline of image description based on visual codebooks suitable for video on-line processing. The pipeline components are (i) extra...
The paper describes a further development of the design of a motivational visualization encouraging participation in an online community. The new design overcomes shortcomings in p...
Online learning algorithms such as Winnow have received much attention in Machine Learning. Their performance degrades only logarithmically with the input dimension, making them us...