Alexander C. Berg

TL;DR: This work proposes using the existing Active Vision Dataset to form a benchmark for problems in a real-world settings with real images, well suited for evaluating tasks of multiview active recognition, target driven navigation, and target search, and also can be effective for studying the transfer of strategies learned in simulation to real settings.

TL;DR: The rules of the competition and the rationale are explained, the rationale is summarized, the teams' scores are summarized, and the lessons learned in the first three years are described.

TL;DR: This work exploits skewed data in large training datasets to reduce the number of unlabeled examples considered in each selection round by only looking at the nearest neighbors to the labeled examples, and observes that learned representations effectively cluster unseen concepts, making active learning very effective and substantially reducing thenumber of viable unlabeling examples.

TL;DR: This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset and employs a combination of networks trained for specialized tasks such as scene recognition, person activity classification, and attribute prediction.

TL;DR: This paper looks at the problem of predicting category labels that mimic how human observers would name objects, related to the concept of entry-level categories first introduced by psychologists in the 1970s and 1980s.