Abstract: Systems and methods are disclosed to analyze a social network by generating a data tensor from social networking data; applying a non-negative tensor factorization (NTF) with user prior knowledge and preferences to generate a core tensor and facet matrices; and rendering information to social networking users based on the core tensor and facet matrices.

Abstract: Systems and methods are disclosed for generating super resolution images by building a set of multi-resolution bases from one or more training images; estimating a sparse resolution-invariant representation of an image, and reconstructing one or more missing patches at any resolution level.

Abstract: Systems and methods are disclosed to classify an input image by determining a spatial-pyramid image representation based on sparse coding; determining a descriptor for each interest point in the input image; encoding the descriptor; and applying max pooling to form the spatial pyramid representation of images.

Abstract: Systems and methods are disclosed to find dynamic social networks by applying a dynamic stochastic block model to generate one or more dynamic social networks, wherein the model simultaneously captures communities and their evolutions, and inferring best-fit parameters for the dynamic stochastic model with online learning and offline learning.

Abstract: Systems and methods are disclosed for determining human pose by generating an Appearance and Position Context (APC) local descriptor that achieves selectivity and invariance while requiring no background subtraction; jointly learning visual words and pose regressors in a supervised manner; and estimating the human pose.

Abstract: In a technique for video segmentation, classification and summarization based on the singular value decomposition, frames of the input video sequence are represented by vectors composed of concatenated histograms descriptive of the spatial distributions of colors within the video frames. The singular value decomposition maps these vectors into a refined feature space. In the refined feature space produced by the singular value decomposition, the invention uses a metric to measure the amount of information contained in each video shot of the input video sequence. The most static video shot is defined as an information unit, and the content value computed from this shot is used as a threshold to cluster the remaining frames. The clustered frames are displayed using a set of static keyframes or a summary video sequence. The video segmentation technique relies on the distance between the frames in the refined feature space to calculate the similarity between frames in the input video sequence.

Abstract: System and methods are disclosed to perform multi-human 3D tracking with a plurality of cameras. At each view, a module receives each camera output and provides 2D human detection candidates. A plurality of 2D tracking modules are connected to the CNNs, each 2D tracking module managing 2D tracking independently. A 3D tracking module is connected to the 2D tracking modules to receive promising 2D tracking hypotheses. The 3D tracking module selects trajectories from the 2D tracking modules to generate 3D tracking hypotheses.

Abstract: Systems and methods are disclosed for generating a recommendation by performing collaborative filtering using an infinite dimensional matrix factorization; generating one or more recommendations using the collaborative filtering; and displaying the recommendations to a user.

Abstract: Systems and methods are disclosed for summarizing multiple documents by generating a model of the documents as a mixture of document clusters, each document in turn having a mixture of sentences, wherein the model simultaneously representing summarization information and document cluster structure; and determining a loss function for evaluating the model and optimizing the model.

Abstract: Systems and methods are disclosed for factorizing high-dimensional data by simultaneously capturing factors for all data dimensions and their correlations in a factor model, wherein the factor model provides a parsimonious description of the data; and generating a corresponding loss function to evaluate the factor model.

Abstract: A computer implemented technique for producing super resolution images from ordinary images or videos containing a number of images wherein a number of non-smooth low resolution patches comprising an image are found using edge detection methodologies. The low resolution patches are then transformed using selected basis of a Radial Basis Function (RBF) and Gaussian process regression is used to generate high resolution patches using a trained model. The high resolution patches are then combined into a high resolution image or video.

Abstract: Text summarizers using relevance measurement technologies and latent semantic analysis techniques provide accurate and useful summarization of the contents of text documents. Generic text summaries may be produced by ranking and extracting sentences from original documents; broad coverage of document content and decreased redundancy may simultaneously be achieved by constructing summaries from sentences that are highly ranked and different from each other. In one embodiment, conventional Information Retrieval (IR) technologies may be applied in a unique way to perform the summarization; relevance measurement, sentence selection, and term elimination may be repeated in successive iterations.

Abstract: A computer-implemented method and system for predicting operation risks of a vehicle. The method and system obtains a training data stream of vehicular dynamic parameters and logging crash time instances; partitions the data stream into units representing dimension vectors, labels the units that overlap the crash time instances as most dangerous; labels the units, which are furthest from the units that are labeled as most dangerous, as most safe; propagates the most dangerous and the most safe labeling information of the labeled units to units which are not labeled; estimates parameters of a danger-level function using the labeled and unlabeled units; and applies the danger-level function to an actual data stream of vehicular dynamic parameters to predict the operation risks of the vehicle.

Abstract: Systems and methods are disclosed to detect unsafe system states by capturing and analyzing data from a plurality of sensors detecting parameters of the system; and applying temporal difference (TD) learning to learn a function to approximate an expected future reward given current and historical sensor readings.

Abstract: A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference.

Abstract: Systems and methods for classifying documents each having zero or more links thereto include generating a link matrix; generating a document term matrix; and jointly factorizing the document term matrix and the link matrix.

Abstract: Systems and methods predict missing elements from a partially-observed matrix by receiving one or more user item ratings; generating a model parameterized by matrices U, S, V; and outputting the model.

Abstract: A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

Abstract: Systems and methods are disclosed to predict driving danger by capturing vehicle dynamic parameter, driver physiological data and driver behavior feature; applying a learning algorithm to the features; and predicting driving danger.

Abstract: Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.