C Long, G Hua, A Kapoor - Proceedings of the IEEE …, 2013 - openaccess.thecvf.com
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 …
E Johns, O Mac Aodha… - Proceedings of the IEEE …, 2015 - openaccess.thecvf.com
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 …
WJ Scheirer, SE Anthony… - IEEE transactions on …, 2014 - ieeexplore.ieee.org
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 …
S Branson, G Van Horn… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
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 …