Abstract: A computer-implemented method for performing few-shot imitation is disclosed. The method comprises obtaining at least one set of training data, wherein each set of training data is associated with a task and comprises (i) one of samples of rewards and a reward function, (ii) one of samples of state transitions and a transition distribution, and (iii) a set of first demonstrations, training a policy network embodied in an agent using reinforcement learning by inputting at least one set of first demonstrations of the at least one set of training data into the policy network, and by maximizing a risk measure or an average return over the at least one set of first demonstrations of the at least one set of training data based on respective one or more reward functions or respective samples of rewards, obtaining a set of second demonstrations associated with a new task, and inputting the set of second demonstrations and an observation of a state into the trained policy network for performing the new task.

Abstract: A training system for training a trained model for use by a navigating robot to perform visual navigation includes memory including N base virtual training environments, each of the N base virtual training environments including a field of view at a location within an indoor space, where N is an integer greater than 1. A randomization module is configured to generate N varied virtual training environments based on the N base virtual training environments, respectively, by varying at least one characteristic of the respective N base virtual training environments. A training module is configured to train the trained model for use by the navigating robot to perform visual navigation based on a training set including: the N base virtual training environments; and the N varied virtual training environments.

Abstract: A method for optimizing autonomous driving includes applying different autonomous driving parameters to a plurality of robot agents in a simulation through an automatic setting by means of the system or a direct setting by means of a manager, so that the robot agents learn robot autonomous driving; and optimizing the autonomous driving parameters by using preference data for the autonomous driving parameters.

Abstract: A training system for training a trained model for use by a navigating robot to perform visual navigation includes memory including N base virtual training environments, each of the N base virtual training environments including a field of view at a location within an indoor space, where N is an integer greater than 1. A randomization module is configured to generate N varied virtual training environments based on the N base virtual training environments, respectively, by varying at least one characteristic of the respective N base virtual training environments. A training module is configured to train the trained model for use by the navigating robot to perform visual navigation based on a training set including: the N base virtual training environments; and the N varied virtual training environments.

Abstract: In a system for updating a contacts database (42, 46), a portable imager (12) acquires a digital business card image (10). An image segmenter (16) extracts text image segments from the digital business card image. An optical character recognizer (OCR) (26) generates one or more textual content candidates for each text image segment. A scoring processor (36) scores each textual content candidate based on results of database queries respective to the textual content candidates. A content selector (38) selects a textual content candidate for each text image segment based at least on the assigned scores. An interface (50) is configured to update the contacts list based on the selected textual content candidates.

Abstract: A method and system for contrast enhancement of an input image that utilizes luminance values of pixels of the input image to derive transforms. The method down-samples and partitions an image into sub-images whereby transforms are generated for selected sub-images. The selected sub-image transforms are used to generate an output transform which is applied to the input image for local contrast enhancement of the image. Furthermore, a decision method as to whether or not the input image is to receive local contrast enhancement wherein darkness features of the input image are compared to threshold values and combined into an expression which results in the determination.

Abstract: A method for recommending a collection of digital images from a set of images includes specifying at least one image selection criterion. For each of a plurality of images in the set of images, an image quality value for the image is determined. Images are recommended for the collection by taking into consideration the image quality value for the images and the degree to which the collection satisfies the at least one image selection criterion.

Abstract: A method suited to the detection and correction of red-eyes includes assigning a probability to pixels of a digital image of the pixel being in a red-eye, the probability being a function of a color of the pixel. Optionally, generally circular regions in the image of contiguous pixels which satisfy at least one test for a red-eye are identified. The test may include determining a size or shape of the region or an extent of overlap with a region comprising pixels having at least a threshold probability of being in a red-eye. For each of a plurality of the pixels, such as simply those in identified regions, or for all pixels or a larger group of the pixels, a color correction for the pixel is determined. The correction is a function of the assigned probability that the pixel is within a red-eye and a color of the pixel.

Abstract: A digital image is automatically combined with text data by automatically classifying the image according to a predetermined set of categories, and automatically selecting text data from a repository, wherein the selected text data match the category of the image according to a predetermined criterion.

Abstract: A foreground color for a digital image is automatically determined by dividing the colors of the pixels of at least a part of the digital image into a number of color clusters in a color space, and for at least one cluster selecting a color being related to the at least one color cluster according to predetermined criteria.

Abstract: Output documents similar to an input document are identified. A query is formulated using a list of best keywords from the input document to search for a first set of output documents. The list of best keywords is defined with a maximum number of keywords less than the total number of keywords in the list of best keywords that are identified as belonging to a domain specific dictionary of words and as having no measurable linguistic frequency. Lists of keywords are identified for each output document in the first set of documents. A second set of similar documents is determined using a measure of similarity that is computed between keywords identified in the input document and each output document in the first set of documents.

Abstract: A measure of similarity between two documents is computed. In computing the measure of similarity, a first list of rated keywords extracted from the first document and a second list of rated keywords extracted from the second document are received. The first and second lists of keywords are used to determine whether the first document forms part of the second document using a first computed percentage indicating what percentage of keyword ratings in the first list also exist in the second list. A second percentage is computed that indicates what percentage of keyword ratings along with a set of their neighboring keyword ratings in the first list that also exist in the second list when the first percentage indicates that the first document is included in the second document. The first percentage is used to specify the measure of similarity when the second percentage is greater than the first percentage.

Abstract: An observed signal that is corrupted with impulse noise is recorded in a signal processing system of an image processing system or a digital subscriber line (xDSL). The observed signal that is recorded by the signal processing system includes a noise component and data component. The signal processing system estimates the parameters of an alpha-stable distribution using a modified iteratively reweighted least squares (IRLS) technique. The estimated parameters define a probability density function that is used to model the noise component of the observed signal. Once the parameters of the alpha-stable distribution are estimated, the signal processing system uses them to estimate model coefficients of a non-linear prediction filter such as a Volterra filter. Using the model coefficients, the non-linear prediction filter estimates the data component of the observed signal.