Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many machine learning problems [4, 16]. However, the exten...
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
Using different algorithms to segment different images is a quite straightforward strategy for automated image segmentation. But the difficulty of the optimal algorithm selection ...
Interactive synthetic environments are currently used in a wide variety of applications, including video games, exposure therapy, education, and training. Their success in such do...
Humans continuously assess one another's situational context, modify their own affective state, and then respond based on these outcomes through empathetic expression. Virtua...
Scott W. McQuiggan, Jennifer L. Robison, Robert Ph...