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

We propose a probabilistic method to track and interpret interactions of moving objects. The proposed method is based on the analysis of location data from different moving objects that modify their dynamics according to rules of interactions, namely attractive and repulsive forces governing moving objects in a scene. Our method uses a Bayesian structure to identify key elements of the interplay rules and facilitates the prediction of objects' dynamics as the interacting system.

CT image reconstruction from incomplete data, such as sparse views and limited angle reconstruction, is an important and challenging problem in medical imaging. This work proposes a new deep convolutional neural network (CNN), called JSR-Net, that jointly reconstructs CT images and their associated Radon domain projections. JSR-Net combines the traditional model-based approach with deep architecture design of deep learning. A hybrid loss function is adapted to improve the performance of the JSR-Net making it more effective in protecting important image structures.

It is well known that electromagnetic and power side-channel attacks allow extraction of unintended information from a computer processor. However, little work has been done to quantify how small a sample is needed in order to glean meaningful information about a program's execution. This paper quantifies this minimum context by training a deep-learning model to track and classify program block types given small windows of side-channel data. We show that a window containing approximately four clock cycles suffices to predict block type with our experimental setup.

One of the major limitations of current electroencephalogram (EEG)-based brain-computer interfaces (BCIs) is the long calibration time. Due to a high level of noise and non-stationarity inherent in EEG signals, a calibration model trained using the limited number of train data may not yield an accurate BCI model. To address this problem, this paper proposes a novel subject-to-subject transfer learning framework that improves the classification accuracy using limited training data.

Obtaining aligned spectral pairs in case of non-parallel data for stand-alone Voice Conversion (VC) technique is a challenging research problem. Unsupervised alignment algorithm, namely, an Iterative combination of a Nearest Neighbor search step and a Conversion step Alignment (INCA) iteratively tries to align the spectral features by minimizing the Euclidean distance metric between the intermediate converted and the target spectral feature vectors.

Real-world data exhibiting high order/dimensionality and various couplings are linked to each other since they share
some common characteristics. Coupled tensor decomposition has become a popular technique for group analysis in recent
years, especially for simultaneous analysis of multi-block tensor data with common information. To address the multi-
block tensor data, we propose a fast double-coupled nonnegative Canonical Polyadic Decomposition (FDC-NCPD)

Real-world data exhibiting high order/dimensionality and various couplings are linked to each other since they share
some common characteristics. Coupled tensor decomposition has become a popular technique for group analysis in recent
years, especially for simultaneous analysis of multi-block tensor data with common information. To address the multi-
block tensor data, we propose a fast double-coupled nonnegative Canonical Polyadic Decomposition (FDC-NCPD)

This paper proposes a novel framework to regularize the highly illposed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our proposed algorithm, Deep Ptych, outperforms the existing Fourier ptychography techniques, in terms of quality of reconstruction and robustness against noise, using far fewer samples. We further modify the proposed approach to allow the generative model to explore solutions outside the range, leading to improved performance.