With the success of deep learning in the field of computer vision, object recognition has
made important breakthroughs, and its recognition accuracy has been drastically improved …

Recent results indicate that the generic descriptors extracted from the convolutional neural
networks are very powerful. This paper adds to the mounting evidence that this is indeed the …

This paper introduces WILDCAT, a deep learning method which jointly aims at aligning
image regions for gaining spatial invariance and learning strongly localized features. Our …

The objective of this work is to recognize object categories (such as animals and vehicles) in
paintings, whilst learning these categories from natural images. This is a challenging …

The recent development in learning deep representations has demonstrated its wide
applications in traditional vision tasks like classification and detection. However, there has …

The automatic discovery of distinctive parts for an object or scene class is challenging since
it requires simultaneously to learn the part appearance and also to identify the part …

Recently introduced RGB-D cameras are capable of providing high quality synchronized
videos of both color and depth. With its advanced sensing capabilities, this technology …

Designing effective features is a fundamental problem in computer vision. However, it is
usually difficult to achieve a great tradeoff between discriminative power and robustness …

We explore multi-scale convolutional neural nets (CNNs) for image classification.
Contemporary approaches extract features from a single output layer. By extracting features …

In this paper, we introduce a novel framework for WEakly supervised Learning of Deep
cOnvolutional neural Networks (WELDON). Our method is dedicated to automatically …