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

We address the problem of camera motion estimation from a single blurred image with the aid of deep convolutional neural networks.
Unlike learning-based prior works that estimate a space-invariant blur kernel, we solve for the global camera motion which in turn


In this work, we study the optimal trajectory of an unmanned aerial vehicle (UAV) acting as a base station (BS) to serve multiple users. Considering multiple flying epochs, we leverage the tools of reinforcement learning (RL) with the UAV acting as an autonomous agent in the environment to learn the trajectory that maximizes the sum rate of the transmission during flying time. By applying Q-learning, a model-free RL technique, an agent is trained to make movement decisions for the UAV. We compare table-based and neural network (NN) approximations of the Q-function and analyze the results.


We examine the usability of deep neural networks for multiple-input multiple-output (MIMO) user positioning solely based on the orthogonal frequency division multiplex (OFDM) complex channel coefficients. In contrast to other indoor positioning systems (IPSs), the proposed method does not require any additional piloting overhead or any other changes in the communications system itself as it is deployed on top of an existing OFDM MIMO system. Supported by actual measurements, we are mainly interested in the more challenging non-line of sight (NLoS) scenario.


Full-duplex systems require very strong self-interference cancellation in order to operate correctly and a significant part of the self-interference signal is due to non-linear effects created by various transceiver impairments. As such, linear cancellation alone is usually not sufficient and sophisticated non-linear cancellation algorithms have been proposed in the literature. In this work, we investigate the use of a neural network as an alternative to the traditional non-linear cancellation method that is based on polynomial basis functions.


Gaussian mixture model (GMM) is a powerful probabilistic model for representing the probability distribution of observations in the population. However, the fitness of Gaussian mixture model can be significantly degraded when the data contain a certain amount of outliers. Although there are certain variants of GMM (e.g., mixture of Laplace, mixture of t distribution) attempting to handle outliers, none of them can sufficiently mitigate the effect of outliers if the outliers are far from the centroids.


Head movement is an integral part of face-to-face communications. It is important to investigate methodologies to generate naturalistic movements for conversational agents (CAs). The predominant method for head movement generation is using rules based on the meaning of the message. However, the variations of head movements by these methods are bounded by the predefined dictionary of gestures. Speech-driven methods offer an alternative approach, learning the relationship between speech and head movements from real recordings.


Memorability of media content such as images and videos has recently become an important research subject in computer vision. This paper presents our computation model for predicting image memorability, which is based on a deep learning architecture designed for a classification task. We exploit the use of both convolutional neural network (CNN) - based visual features and semantic features related to image captioning for the task. We train and test our model on the large-scale benchmarking memorability dataset: LaMem.


Researchers have recently examined a modified approach to sparse coding that encourages dictionaries to learn anomalous features. This is done by incorporating the matrix 1-norm, or \ell_{1,\infty} mixed matrix norm, into the dictionary update portion of a sparse coding algorithm. However, solving a matrix norm minimization problem in each iteration of the algorithm