Abstract: An alert peripheral device that provides sensory notification to a user of the device includes: a power subsystem; a communication mechanism by which notification signals is received from a first user equipment (UE) that generates and transmits the notification signals in response to detection of specific events at the first UE; and a response notification mechanism that provides a sensory response of the peripheral device following receipt of a notification of a detected event (NDE) signal. The device further includes an embedded controller coupled to each of the other components and which includes firmware that when executed on the embedded controller configures the embedded controller to: establish a communication link between the communication mechanism and the first UE; and in response to detecting a receipt of the NDE signal from the first UE, trigger the response notification mechanism to exhibit the sensory response.

Abstract: A method of generating an output image having an output resolution of N pixels×N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-resolution version of the output image to generate the output image having the output resolution by repeatedly performing the following operations: obtaining a current version of the output image having a current K×K resolution; and processing the current version of the output image using a set of convolutional neural networks that are specific to the current resolution to generate an updated version of the output image having a 2K×2K resolution.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. A request to generate an encoded representation of an input image is received. The encoded representation of the input image is then generated. The encoded representation includes a respective set of binary codes at each iteration. Generating the set of binary codes for the iteration from an initial set of binary includes: for any tiles that have already been masked off during any previous iteration, masking off the tile. For any tiles that have not yet been masked off during any of the previous iterations, a determination is made as to whether a reconstruction error of the tile when reconstructed from binary codes at the previous iterations satisfies an error threshold. When the reconstruction quality satisfies the error threshold, the tile is masked off.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output images. One of the methods includes obtaining data specifying (i) a partitioning of the H by W pixel grid of the output image into K disjoint, interleaved sub-images and (ii) an ordering of the sub-images; and generating intensity values sub-image by sub-image, comprising: for each particular color channel for each particular pixel in each particular sub-image, generating, using a generative neural network, the intensity value for the particular color channel conditioned on intensity values for (i) any pixels that are in sub-images that are before the particular sub-image in the ordering, (ii) any pixels within the particular sub-image that are before the particular pixel in a raster-scan order over the output image, and (iii) the particular pixel for any color channels that are before the particular color channel in a color channel order.

Abstract: Provided is a signal processing apparatus that estimates image distortion in a case where images are captured through a transmissive body allowing light to pass through. The signal processing apparatus includes a lens distortion estimation section that estimates lens distortion based on a location of a feature point in a first image and a second image of an object. The first image is captured by an imaging section through a transmissive body and a lens that allow light to pass through. The second image is free of transmissive body distortion caused by the transmissive body and free of the lens distortion caused by the lens. The apparatus further includes a transmissive body distortion estimation section that estimates the transmissive body distortion based on the location of the feature point in the first image and a third image that is obtained by removing the estimated lens distortion from the first image.

Abstract: A two-dimensional conversion unit converts point cloud data D1 acquired by a three-dimensional sensor into two-dimensional data with the distance as the pixel value. A convolutional neural network receives the image data as its input, and judges the position of and the category of an object included in the point cloud data.

Abstract: An electronic circuit includes a block determinator, a candidate selector, and a motion vector generator to perform motion estimation between images. The block determinator determines a current block corresponding to a current location on an image and candidate blocks corresponding to relative locations with respect to the current location for each recursion for blocks constituting the image. The candidate selector selects some of the candidate blocks. The motion vector generator generates a motion vector for the current block based on one reference patch which is determined from reference patches indicated by candidate motion vectors of the selected candidate blocks. At least one of the relative locations corresponding to the candidate blocks selected in a first recursion is different from each of the relative locations corresponding to the candidate blocks selected in a second recursion following the first recursion.

Abstract: An object is to make it possible to precisely infer a geometric transformation matrix for transformation between an image and a reference image representing a plane region even if correspondence to the reference image cannot be obtained. A first line segment group extraction unit 120 extracts, out of a line segment group in an image, line segments that correspond to a direction that is parallel or perpendicular to a side of a rectangle included in the image, from the inside of the rectangle, takes the extracted line segments to be a first line segment group, and extracts a plurality of line segments different from the first line segment group out of the line segment group.

Abstract: An image decoding apparatus includes a decoding unit configured to decode coded data into a decoded image and segmentation metadata, a segmentation metadata decoding unit configured to generate segmentation information, and an image processing unit configured to perform prescribed image processing on the decoded image with reference to the segmentation information.

Abstract: Systems and methods for self-supervised depth estimation using image frames captured from a plurality of cameras mounted on a vehicle, may include: receiving a first image from a camera mounted at a first location on the vehicle, the source image comprising pixels representing a scene of the environment of the vehicle; receiving a reference image from a camera mounted at a second location on the vehicle, the reference image comprising pixels representing a scene of the environment; predicting a depth map for the first image, the depth map comprising predicted depth values for pixels of the first image; warping the first image to a perspective of the camera mounted at the second location on the vehicle to arrive at a warped first image; projecting the warped first image onto the source image; determining a loss based on the projection; and updating the predicted depth values for the first image.

Abstract: Aspects of the subject disclosure may include, for example, collecting and storing data about a communication environment including one or more communication networks wherein respective communication networks of the one or more communication networks employ respective communication technologies for communication with remote user devices in the communication environment, providing traffic forecasts of communication traffic, creating importance layers for potential build locations for equipment of the one or more communication networks, identifying desirable build locations among the potential build locations of the one or more communication networks based on the traffic forecasts of communication traffic and the importance layers, receiving user input defining planning parameters for the communication environment and determining respective target goal values for respective build options for the one or more communication networks based on the planning parameters, the identified desirable build locations and the

Abstract: A user interface and method for viewing communications events on a mobile device includes a user interface, a communications event handler, and a communications event database is disclosed herein. The communications event handler interfaces with the database and the user interface to provide a user of the mobile device with a communications event history associated with the correspondent of an incoming communications event. Additionally the communications event handler interfaces with the database and the user interface to provide a user of the mobile device with a communications event history for a specified correspondent.

Abstract: Methods, systems, and computer readable medium for optimizing physical products. The method includes detecting a set of physical attributes for each physical item among multiple different physical items, obtaining a velocity factor for each of the physical items, generating a mapping of a velocity contribution to various combinations of physical attributes among the set of physical attributes based on the velocity factor for each physical item and the set of physical attributes of that physical item, determining, based on the mapping, that the velocity factor of a particular physical item will increase in response to a change to one or more physical attributes of the particular physical item, and transmitting, to a source of the particular item, an electronic message that conveys the increase to the velocity factor of the particular physical item that will result from a selection of the one or more physical attributes of the particular item.

Abstract: A system and method of detecting objects are provided. The method includes generating first edge information from first image data representing an object based on a first mode of image capture, generating second edge information from second image data representing the object based on a second mode of image capture, the second mode being different from the first mode, fusing the first edge information with the second edge information to generate fused edge information, generating an object detection hypothesis based on the fused edge information, and validating the object detection hypothesis based on the fused edge information, the first edge information, and/or the second edge information.

Abstract: Systems and methods for texture hallucination with a large upscaling factor are described. Embodiments of the systems and methods may receive an input image and a reference image, extract an upscaled feature map from the input image, match the input image to a portion of the reference image, wherein a resolution of the reference image is higher than a resolution of the input image, concatenate the upscaled feature map with a reference feature map corresponding to the portion of the reference image to produce a concatenated feature map, and generate a reconstructed image based on the concatenated feature map using a machine learning model trained with a texture loss and a degradation loss, wherein the texture loss is based on a high frequency band filter, and the degradation loss is based on a downscaled version of the reconstructed image.

Abstract: A lifting transform method performed on an elemental image array may perform a lifting transform on an elemental image array to obtain a difference image (or an error image representing a prediction error) and movement information used for prediction and may appropriately reorder the difference image to obtain a wavelet-type elemental image array.

Abstract: Embodiments of the present invention provide notification management across a plurality of electronic communication devices based on the present situational context of the intended communication recipient. Some types of relevant situational context information include the geographic location of the intended recipient, what electronic communication devices they may have in their possession, calendar or schedule information, the presence of other people, the identity of other people present in their vicinity, their relationship to the communication sender, and context information concerning the sender, such as how frequently the sender has attempted to communicate with the intended recipient and news information relevant to the known or assumed location of the sender. Notifications are managed by adjusting which electronic communication devices emit notifications and what type of notifications are emitted.

Abstract: A computerized domain matching image conversion method for transportable imaging applications first performs a target domain A to source domain B matching converter training by computing means using domain B training images and at least one domain A image to generate an A to B domain matching converter. The method then applies the A to B domain matching converter to a domain A application image to generate its domain B matched application image. The method further applies a domain B imaging application analytics to the domain B matched application image to generate an imaging application output for the domain A application image.

Abstract: A method of intelligent persistent mobile device management connectivity, including establishing a session between a mobile device and a mobile device management provider, directing the mobile device by the mobile device management provider to perform a successive operation, maintaining the established session between the mobile device and the mobile device management provider while the mobile device is online and periodically checking the mobile device management communication at a communication frequency, wherein the communication frequency is based on a performance feedback parameter.