Sorry, you need to enable JavaScript to visit this website.

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mechanisms to the problem of sequence summarization in our end-to-end text-dependent speaker recognition system. We explore different topologies and their variants of the attention layer, and compare different pooling methods on the attention weights.

Deep neural networks inherently have large representational power for approximating complex target functions. However,

The signal processing (SP) landscape has been enriched by recent advances in artificial intelligence (AI) and machine learning (ML), especially since 2010 or so, yielding new tools for signal estimation, classification, prediction, and manipulation. Layered signal representations, nonlinear function approximation, and nonlinear signal prediction are now feasible at very large scale in both dimensionality and data size.

Artery/vein classification in fundus images is a prerequisite for the assessment of diseases such as diabetes, hypertension or other cardiovascular pathologies. One clinical measure used to assess the severity of cardiovascular risk is the retinal arterio-venous ratio (AVR), which significantly depends on the accuracy of vessel classification into arteries or veins. This paper proposes a novel method for artery/vein classification combining deep learning and graph propagation strategies.

We present an efficient multi-image super resolution (MISR) method. Our solution consists of a L1-norm optimized reconstruction scheme for super resolution (SR), and a three-layer convolutional network for artifacts removal, in a concatenated fashion. Such a two-stage method achieves excellent performance, which outperforms the existing state-of-the-art SR methods in both subjective and objective measurements (e.g., 5 to 7 dB improvements on popular image database using PSNR metric).

Deep neural networks have led to dramatic improvements in performance for many machine learning tasks, yet the mathematical reasons for this success remain largely unclear. In this talk we present recent developments in the mathematical framework of convolutive neural networks (CNN). In particular we discuss the scattering network of Mallat and how it relates to another problem in harmonic analysis, namely the phase retrieval problem. Then we discuss the general convolutive neural network from a theoretician point of view.

Classical approaches for estimating optical flow have achieved rapid progress in the last decade. However, most of them are too slow to be applied in real-time video analysis. Due to the great success of deep learning, recent work has focused on using CNNs to solve such dense prediction problems. In this paper, we investigate a new deep architecture, Densely Connected Convolutional Networks (DenseNet), to learn optical flow. This specific architecture is ideal for the problem at hand as it provides shortcut connections throughout the network, which leads to implicit deep supervision.