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

We consider the problem of differentiating a multivariable function specified by noisy data. Following previous work for the single-variable case, we regularize the differentiation process, by formulating it as an inverse problem with an integration operator as the forward model. Total-variation regularization avoids the noise amplification of finite-difference methods, while allowing for discontinuous solutions. Unlike the single-variable case, we use an alternating directions, method of multipliers algorithm to provide greater efficiency for large problems.

Scene text detection is a critical prerequisite for many fascinating applications for vision-based intelligent robots. Existing methods detect texts either using the local information only or casting it as a semantic segmentation problem. They tend to produce a large number of false alarms or cannot separate individual words accurately. In this work, we present an elegant segmentation-aided text detection solution that predicts the word-level bounding boxes using an end-to-end trainable deep convolutional neural network.

It is important to determine 3D shape properties of a population of 3D mesh models in biomedical imaging issues. In contrast to conventional 3D shape analysis techniques focusing on applications like shape matching and shape retrieval, we propose in this paper a strategy capable to collect statistical information of multiple triangular mesh models. Our method operates in a coarse-to-fine fashion based on wavelet synthesis. Hence, its analysis result can be invariant against the triangular tiling of the input mesh model.

In this paper, an image error concealment method based on joint local sparse representation and non-local similarity is proposed. The proposed method obtains an optimal sparse representation of an image patch, including missing pixels and known neighboring pixels for recovery purpose. At first, a pair of dictionary and a mapping function are simultaneously learned offline from a training data set.

This paper considers a two-user multiple-input single-output Gaussian broadcast channel model with two sorts of information transfer, i.e., multicasting and confidential broadcasting. Specifically, three service messages are combined at the transmitter. The transmitter sends a
multicast message to both users, and a confidential message to each user which is kept perfectly secret from the other user. Our goal