Deep Face Recognition
- O. Parkhi, A. Vedaldi, Andrew Zisserman
- Computer ScienceBritish Machine Vision Conference
- 2015
It is shown how a very large scale dataset can be assembled by a combination of automation and human in the loop, and the trade off between data purity and time is discussed.
Fully-Convolutional Siamese Networks for Object Tracking
- Luca Bertinetto, Jack Valmadre, João F. Henriques, A. Vedaldi, Philip H. S. Torr
- Computer ScienceECCV Workshops
- 30 June 2016
A basic tracking algorithm is equipped with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video and achieves state-of-the-art performance in multiple benchmarks.
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- K. Simonyan, A. Vedaldi, Andrew Zisserman
- Computer ScienceInternational Conference on Learning…
- 20 December 2013
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks.
Return of the Devil in the Details: Delving Deep into Convolutional Nets
- K. Chatfield, K. Simonyan, A. Vedaldi, Andrew Zisserman
- Computer ScienceBritish Machine Vision Conference
- 14 May 2014
It is shown that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost, and it is identified that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance.
Deep Image Prior
- Dmitry Ulyanov, A. Vedaldi, V. Lempitsky
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 29 November 2017
It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, and inpainting.
Describing Textures in the Wild
- Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, S. Mohamed, A. Vedaldi
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 14 November 2013
This work identifies a vocabulary of forty-seven texture terms and uses them to describe a large dataset of patterns collected "in the wild", and shows that they both outperform specialized texture descriptors not only on this problem, but also in established material recognition datasets.
Fine-Grained Visual Classification of Aircraft
- Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew B. Blaschko, A. Vedaldi
- Computer ScienceArXiv
- 21 June 2013
Compared to the domains usually considered in fine-grained visual classification (FGVC), for example animals, aircraft are rigid and hence less deformable, however, they present other interesting modes of variation, including purpose, size, designation, structure, historical style, and branding.
End-to-End Representation Learning for Correlation Filter Based Tracking
- Jack Valmadre, Luca Bertinetto, João F. Henriques, A. Vedaldi, Philip H. S. Torr
- Computer ScienceComputer Vision and Pattern Recognition
- 20 April 2017
This work is the first to overcome this limitation by interpreting the Correlation Filter learner, which has a closed-form solution, as a differentiable layer in a deep neural network, which enables learning deep features that are tightly coupled to the Cor correlation filter.
MatConvNet: Convolutional Neural Networks for MATLAB
- A. Vedaldi, Karel Lenc
- Computer ScienceACM Multimedia
- 15 December 2014
MatConvNet exposes the building blocks of CNNs as easy-to-use MATLAB functions, providing routines for computing convolutions with filter banks, feature pooling, normalisation, and much more.
The Visual Object Tracking VOT2016 Challenge Results
- M. Kristan, A. Leonardis, Zhizhen Chi
- Computer ScienceECCV Workshops
- 8 October 2016
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
...
...