University of Oxford

About: University of Oxford is a education organization based out in Oxford, Oxfordshire, United Kingdom. It is known for research contribution in the topics: Population & Context (language use). The organization has 99713 authors who have published 258108 publications receiving 12972806 citations. The organization is also known as: Oxford University & Oxon..

Fully-Convolutional Siamese Networks for Object Tracking

Abstract: The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.

Convolutional Two-Stream Network Fusion for Video Action Recognition

Abstract: Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse such networks spatially at the last convolutional layer than earlier, and that additionally fusing at the class prediction layer can boost accuracy; finally (iii) that pooling of abstract convolutional features over spatiotemporal neighbourhoods further boosts performance. Based on these studies we propose a new ConvNet architecture for spatiotemporal fusion of video snippets, and evaluate its performance on standard benchmarks where this architecture achieves state-of-the-art results.

Competition when Consumers have Switching Costs: An Overview with Applications to Industrial Organization, Macroeconomics, and International Trade

Abstract: We survey recent work on competition in markets in which consumers have costs of switching between competing firms' products, even when all firms' products are functionally identical We address issues in macroeconomics and international trade, as well as industrial organization: In a market with switching costs (or 'brand loyalty'), a firm's current market share is an important determinant of its future profitability We examine how the firm's choice between setting a low price to capture market share, and setting a high price to Harvest profits by exploiting its current locked-in customers, is affected by the threat of new entry interest rates, exchange rate expectations, the state of the business cycle, etc We also discuss the causes of switching costs, explain introductory offers and price wars, and examine industry profits, firms' product choices, and implications for multi-product competition

Power and Bipower Variation with Stochastic Volatility and Jumps

Abstract: This article shows that realized power variation and its extension, realized bipower variation, which we introduce here, are somewhat robust to rare jumps. We demonstrate that in special cases, realized bipower variation estimates integrated variance in stochastic volatility models, thus providing a model-free and consistent alternative to realized variance. Its robustness property means that if we have a stochastic volatility plus infrequent jumps process, then the difference between realized variance and realized bipower variation estimates the quadratic variation of the jump component. This seems to be the first method that can separate quadratic variation into its continuous and jump components. Various extensions are given, together with proofs of special cases of these results. Detailed mathematical results are reported in Barndorff-Nielsen and Shephard (2003a).