Andrea Vedaldi

Learn More
The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow(More)
The goal of this paper is face recognition – from either a single photograph or from a set of faces tracked in a video. Recent progress in this area has been due to two factors: (i) end to end learning for the task using convolutional neural networks (CNNs), and (ii) the availability of very large scale training datasets. We make two contributions: first,(More)
VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and students. It includes rigorous implementations of common building blocks such as feature detectors, feature extractors, (hierarchical) k-means clustering, randomized kd-tree matching, and(More)
Large scale nonlinear support vector machines (SVMs) can be approximated by linear ones using a suitable feature map. The linear SVMs are in general much faster to learn and evaluate (test) than the original nonlinear SVMs. This work introduces explicit feature maps for the additive class of kernels, such as the intersection, Hellinger's, and(More)
Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image sub-windows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential &#x03C7;<sup>2</sup> kernels, each of which captures a different(More)
[1] vgg/research/encoding eval. [2] J. Sivic and A. Zisserman. Proc. ICCV, 2003. [3] J. Philbin et al. Proc. CVPR, 2008. [4] J. C. van Gemert et al. Proc. ECCV, 2008. [5] J. Wang et al. Proc. CVPR, 2010. [6] F. Perronnin et al. Proc. ECCV, 2010. [7] X. Zhou et al. Proc. ECCV, 2010. Histogram (VQ) 8, 000 74.23± 0.65 Kernel Codebook (KCB)(More)
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [5], thus visualising the notion of the(More)
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by(More)
Patterns and textures are key characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly. Aiming at supporting this dimension in image understanding, we address the problem of describing textures with semantic attributes. We identify a vocabulary of forty-seven texture(More)