As service robots become more and more capable of performing useful tasks for us, there is
a growing need to teach robots how we expect them to carry out these tasks. However …

We present a noise resilient probabilistic model for active learning of a Gaussian process
classifier from crowds, ie, a set of noisy labelers. It explicitly models both the overall label …

Compared to machines, humans are extremely good at classifying images into categories,
especially when they possess prior knowledge of the categories at hand. If this prior …

The number of digital images is growing extremely rapidly, and so is the need for their
classification. But, as more images of pre-defined categories become available, they also …

For many problems in computer vision, human learners are considerably better than
machines. Humans possess highly accurate internal recognition and learning mechanisms …

Abstract Objects are usually organized in a hierarchical structure in which each coarse
category (eg, big cat) corresponds to a superclass of several fine categories (eg, cheetah …

We introduce a method to greatly reduce the amount of redundant annotations required
when crowdsourcing annotations such as bounding boxes, parts, and class labels. For …

Construction workplace hazard detection requires engineers to analyze scenes manually
against many safety rules, which is time-consuming, labor-intensive, and error-prone …

Fine-grained recognition concerns categorization at sub-ordinate levels, where the
distinction between object classes is highly local. Compared to basic level recognition, fine …

Abstract Although Deep Convolutional Networks (DCNs) are approaching the accuracy of
human observers at object recognition, it is unknown whether they leverage similar visual …