We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input prov...
In many scientific and engineering applications, detecting and understanding differences between two groups of examples can be reduced to a classical problem of training a classif...
Multimodal dialogue systems allow users to input information in multiple modalities. These systems can handle simultaneous or sequential composite multimodal input. Different coor...
Spiking neurons model a type of biological neural system where information is encoded with spike times. In this paper, a new method for decoding input spikes according to their abs...
This paper presents a word support model (WSM). The WSM can effectively perform homophone selection and syllable-word segmentation to improve Chinese input systems. The experiment...
Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the ra...
: Models of the association between input accuracy and output accuracy imply that, for any given application, the effect of input errors on the output error rate generally varies i...
Previous efforts involving picture-based passwords have not focused on maintaining a measurably high level of entropy. Since password systems usually allow user selection of passw...
We present various adaptations of the EdgeWrite unistroke text entry method that work on multiple computer input devices: styluses, touchpads, displacement and isometric joysticks...
We present a method for parameterizing irregularly triangulated input models over polyhedral domains with quadrilateral faces. A combination of center-based clustering techniques ...
Ioana M. Boier-Martin, Holly E. Rushmeier, Jingyi ...