—The non-data components of a visualization, such as axes and legends, can often be just as important as the data itself. They provide contextual information essential to interpr...
Abstract-- Visual data comprise of multi-scale and inhomogeneous signals. In this paper, we exploit these characteristics and develop a compact data representation technique based ...
Qing Wu, Tian Xia, Chun Chen, Hsueh-Yi Sean Lin, H...
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
Behavioral Signal Processing aims at automating behavioral coding schemes such as those prevalent in psychology and mental health research. This paper describes methods to quantif...
Viktor Rozgic, Bo Xiao, Athanasios Katsamanis, Bri...
Parse-tree paths are commonly used to incorporate information from syntactic parses into NLP systems. These systems typically treat the paths as atomic (or nearly atomic) features...