Abstract: A streaming system includes a streaming server and a client device. The streaming server is configured to train an interactive frame prediction model based on streaming data, a user input and metadata associated with the user input, encode the streaming data by selectively using a predicted frame generated based on the trained interactive frame prediction model and transmit the trained interactive frame prediction model and the encoded streaming data. The client device is configured to receive the trained interactive frame prediction model and the encoded streaming data, and decode the encoded streaming data based on the trained interactive frame prediction model to provide recovered streaming data to a user.

Abstract: Embodiments of the invention utilize a feature-extraction approach and/or a matching approach in combination with a nonparametric approach to estimate the proportion of documents in each of multiple labeled categories with high accuracy. The feature-extraction approach automatically generates continuously valued text features optimized for estimating the category proportions, and the matching approach constructs a matched set that closely resembles a data set that is unobserved based on an observed set, thereby improving the degree to which the distributions of the observed and unobserved sets resemble each other.

Abstract: A system and method for stitching separately encoded MPEG video fragments, each representing a different rectangular area of the screen together into one single full-screen MPEG encoded video fragment.

Abstract: A method for video decoding includes decoding prediction information of a current block from a coded video bitstream, the prediction information being indicative of a prediction mode that is based on a candidate list. The method includes constructing, in response to the prediction mode, the candidate list that includes a plurality of side candidates that includes (i) a first side candidate having a first corner that is at a middle point of a side of the block and a second corner that is one of above and below the middle point of the side of the block, and (ii) a second side candidate located between the first side candidate and a corner block neighboring the current block. The method further includes reconstructing at least one sample of the current block according to motion information from the plurality of side candidates.

Abstract: In an embodiment, a method includes receiving a trigger of machine learning model generation. In addition, the method includes algorithmically eliminating at least some of rows and at least some of columns of a training dataset, the algorithmically eliminating yielding a size-reduced training dataset. The method additionally includes generating, for a prediction target, a plurality of machine learning models via a plurality of machine learning algorithms. The method also includes measuring prediction accuracies of the plurality of machine learning models relative to the prediction target. Furthermore, the method includes selecting a particular machine learning model. Moreover, the method includes applying the particular machine learning model to a data source.

Abstract: The present disclosure relates to systems and methods for facing a tissue block. In some embodiments, a method is provided for facing a tissue block that includes imaging a tissue block to generate imaging data of the tissue block, the tissue block comprising a tissue sample embedded in an embedding material, estimating, based on the imaging data, a depth profile of the tissue block, wherein the depth profile comprises a thickness of the embedding material to be removed to expose the tissue sample to a pre-determined criteria, and removing the thickness of the embedding material to expose the tissue to the pre-determined criteria.

Abstract: Provided is a method and system for detection of anomalous work pieces that includes computing at least one deviation data signal for a target data signal of a target work piece with respect to reference data signals recorded for a corresponding production process step of a set of reference work pieces, performing a stepwise anomaly detection by data processing of the at least one computed deviation data signal and a process type indicator indicating a type of the production process step using a trained anomaly detection data model to calculate for each time step or path length step of the production process step an anomaly probability that the respective time step or path length step is anomalous, and classifying the target work piece and/or the production process step as being anomalous or not anomalous on the basis of the calculated anomaly probabilities.

Abstract: A user may be aided in modifying a product that is an assemblage of parts. This aid may involve a processor obtaining images of a target part captured by the user on a mobile device camera. The processor may compare, based on the captured images and a plurality of images of identified parts, the target part to the identified parts. Based on the comparison, the processor may determine an identity of the target part. This aid may also involve a processor obtaining images of a first configuration of a partial assembly of the product captured by a mobile device camera. The processor may compare, based on the captured images, the first configuration to a correct configuration of the partial assembly. Based on the comparison, the processor may determine that the first configuration does not match the correct configuration and may notify the user accordingly.

Abstract: Disclosed are methods and apparatuses for decoding an image. A method includes receiving a bitstream obtained by encoding the image; dividing a first coding block into a plurality of second coding blocks; generating a prediction block of a second coding block based on syntax information obtained from the bitstream; and reconstructing the second coding block based on the prediction block and a residual block of the second coding block, the residual block being obtained by performing a dequantization and an inverse-transform on quantized transform coefficients from the bitstream. The first coding block has a recursive division structure. The first coding block is divided based on at least one of a quad tree division, a binary tree division or a triple tree division.

Abstract: The present technology relates to an image processing device, an image processing method, an endoscope system, and a program that enable motion detection with higher accuracy. The endoscope system includes: a light source capable of performing a pulsed-light emission; a light-source control unit that controls the light source such that the light source performs the pulsed-light emission a plurality of times in an exposure time period of each captured image; an imaging unit that takes the captured images; and a motion detection unit that detects a motion of a photographic subject in the captured images. The present technology is applicable to the endoscope system.

Abstract: Techniques regarding explanations for artificial intelligence recommendations are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory.

Abstract: In an embodiment, a method for tracking a target using a millimeter-wave radar includes: receiving radar signals using the millimeter-wave radar; generating a range-Doppler map based on the received radar signals; detecting a target based on the range-Doppler map; tracking the target using a track; generating a predicted activity label based on the track, where the predicted activity label is indicative of an actual activity of the target; generating a Doppler spectrogram based on the track; generating a temporary activity label based on the Doppler spectrogram; assigning an uncertainty value to the temporary activity label, where the uncertainty value is indicative of a confidence level that the temporary activity label is an actual activity of the target; and generating a final activity label based on the uncertainty value.

Abstract: An image display apparatus of the present invention includes: a beam emitting section (10) that radially emits a plurality of beams (Ls1 to Ls5) in a horizontal direction; a mirror rotary member (20) having a rotation axis (Pc) and an inner surface, the inner surface having a plurality of mirror surfaces (21) that reflects each of the plurality of beams (Ls1 to Ls5), the mirror rotary member as a whole rotating about the rotation axis (Pc) as a center to thereby perform, by the plurality of mirror surfaces (21), scanning with each of the plurality of beams (Ls1 to Ls5) emitted from the beam emitting section (10) in the horizontal direction; and a screen (2) to be irradiated with the plurality of beams (Ls1 to Ls5) with which the scanning is performed by the plurality of mirror surfaces (21).

Abstract: A method and system for increasing data quality of a dataset for semi-supervised machine learning analysis. The method includes: receiving known class label information for a portion of the data in the dataset; receiving clustering parameters from a user; determining a data cleanliness factor, and where the data cleanliness factor is below a predetermined cleanliness threshold: assigning data without class label information as a data point to a cluster using the clustering parameters, each cluster having a cluster class label associated with such cluster; and determining a measure of assignment, and where the measure of assignment for each data point is below a predetermined assignment threshold, receiving a class label for such data points, otherwise, assigning the respective cluster class label to each data point with the respective measure of assignment below the predetermined assignment threshold; and otherwise, outputting the dataset with associated class labels for machine learning analysis.

Abstract: A processor obtains an input image containing both bright and dark regions. The processor obtains a threshold between a first pixel value and a second pixel value of the display. Upon detecting a region of the input image having an original pixel value above the threshold, the processor can create a data structure including a location of the region in the input image and an original pixel value of the region. The data structure occupies less memory than the input image. The display presents the input image including the region of the image having the original pixel value above the threshold. The processor sends the data structure to a camera, which records the presented image. The processor performing postprocessing obtains the data structure and the recorded image and increases dynamic range of the recorded image by modifying the recorded image based on the data structure.

Abstract: A method of encoding video including: writing a plurality of predetermined buffer descriptions into a sequence parameter set of a coded video bitstream; writing a plurality of updating parameters into a slice header of the coded video bitstream for selecting and modifying one buffer description out of the plurality of buffer descriptions; and encoding a slice into the coded video bitstream using the slice header and the modified buffer description.

Abstract: A method and system for determining if an individual is impaired. In one embodiment, physical and cognitive testing of the individual are conducted in the field or at the scene of an event. The test results are compared to previously stored baseline test results taken for the specific individual while the individual is known to be in an unimpaired state or condition. The current test results are electronically compared to the baseline test results and if the results differ or deviate beyond a predetermined level or amount the individual is considered to be impaired. If no baseline test results exist for the specific individual, the current test results can alternatively be compared to previously determined or known scientifically accepted or minimums for the specific tests given to the individual.

Abstract: Techniques are described for an autonomous asset management system that integrates autonomous devices, such as drone devices and other robotic devices, with a home security system of a property to enable management, monitoring, and/or tracking of various assets located within the property. In some implementations, an indication of an asset associated with a property is obtained by an autonomous device. Sensor data collected by one or more sensors of the property is obtained by the autonomous device based on the indication of the asset. A present status of the asset is determined by the autonomous device based on the sensor data. A determination that the present status of the asset does not correspond to an expected status of the asset is made by the autonomous device. In response, the autonomous device navigates to the particular location of the property.

Abstract: Disclosed is an image data encoding/decoding method and apparatus. A method for decoding a 360-degree image comprises the steps of: receiving a bitstream obtained by encoding a 360-degree image; generating a prediction image by making reference to syntax information obtained from the received bitstream; combining the generated prediction image with a residual image obtained by dequantizing and inverse-transforming the bitstream, so as to obtain a decoded image; and reconstructing the decoded image into a 360-degree image according to a projection format.

Abstract: The disclosed computer-implemented method may include (i) identifying, by a server computer system, a provider computing device for use in capturing street-level image data, where the provider computing device controls a camera positioned to capture street-level imagery outside the vehicle, (ii) determining, by the server computer system, a configuration that controls use of the provider computing device to provide street-level image data captured by the camera to the server computer system, (iii) sending, by the server computer system, the configuration to the computing device, and (iv) receiving, from the computing device, street-level image data captured by the computing device using the camera responsive to the configuration. Various other methods, systems, and computer-readable media are also disclosed.