In this paper, we systematically study the effect of poorly registered faces on the training and inferring stages of traditional face recognition algorithms. We then propose a nov...
Recent work has shown impressive transform-invariant modeling and clustering for sets of images of objects with similar appearance. We seek to expand these capabilities to sets of...
Manually constructing an inventory of word senses has suffered from problems including high cost, arbitrary assignment of meaning to words, and mismatch to domains. To overcome th...
Background: Structural similarities among proteins can provide valuable insight into their functional mechanisms and relationships. As the number of available three-dimensional (3...
The newly emerging field of Network Science deals with the tasks of modelling, comparing and summarizing large data sets that describe complex interactions. Because pairwise affin...