A method, apparatus, and storage medium for training a neural network model used for image processing are described. The method includes: obtaining a plurality of video frames; inputting the plurality of video frames through a neural network model so that the neural network model outputs intermediate images; obtaining optical flow information between an early video frame and a later video frame; modifying an intermediate image corresponding to the early video frame according to the optical flow information to obtain an expected-intermediate image; determining a time loss between an intermediate image corresponding to the later video frame and the expected-intermediate image; determining a feature loss between the intermediate images and a target feature image; and training the neural network model according to the time loss and the feature loss, and returning to obtaining a plurality of video frames continue training until the neural network model satisfies a training finishing condition.

A method for determining an electronic device, a system for determining an electronic device, a computer system, and a computer-readable storage medium, the method includes: acquiring a recognition result by recognizing a first action performed by an operating object through a first electronic device (S201); and determining a second electronic device which is controllable by the first electronic device according to the recognition result (S202).

Various embodiments of systems and methods for adaptive video subsampling for energy-efficient object detection are disclosed herein.

An apparatus configured for head-worn by a user, includes: a screen configured to present graphics for the user; a camera system configured to view an environment in which the user is located; and a processing unit coupled to the camera system, the processing unit configured to: obtain a first image with a first resolution, the first image having a first corner, determine a second image with a second resolution, the second image having a second corner that corresponds with the first corner in the first image, wherein the second image is based on the first image, the second resolution being less than the first resolution, detect the second corner in the second image, determine a position of the second corner in the second image, and determine a position of the first corner in the first image based at least in part on the determined position of the second corner in the second image.

A method, and corresponding system and computer program product, is provided for identifying meaningful information in connection with an investigation. The method comprises processing a dataset using a machine learning process to derive an initial model conveying first statistical significance information corresponding to features in the dataset. The method also comprises deriving an alternate model at least in part by processing the dataset using the machine learning process while nullifying a contribution of certain features in the dataset selected as candidates for nullification. The alternate model conveys second statistical significance information corresponding to features in the dataset. A user interface is rendered on the display and presents information for assisting the user in identifying the information in the dataset meaningful to the investigation, the information presented being derived at least in part by processing information conveyed by the initial model and the alternate model.

Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.

System, processes and devices for monitoring betting activities using bet recognition devices and a server. Each bet recognition device has an imaging component for capturing image data for a gaming table surface. The bet recognition device receives calibration data for calibrating the bet recognition device. A server processor coupled to a data store processes the image data received from the bet recognition devices over the network to detect, for each betting area, a number of chips and a final bet value for the chips.

Systems for identifying threat materials such as CBRNE threats and locations are provided. The systems can include a data acquisition component configured to determine the presence of a CBRNE threat; data storage media; and processing circuitry operatively coupled to the data acquisition device and the storage media. Methods for identifying a CBRNE threat are provided. The methods can include: determining the presence of a CBRNE threat using a data acquisition component; and acquiring an image while determining the presence of the CBRNE threat. Methods for augmenting a real-time display to include the location and/or type of CBRNE threat previously identified are also provided. Methods for identifying and responding to CBRNE threats are provided as well.

Systems and methods of improved network analytics are disclosed. A system may determine feature propagation in a network of nodes of a graph database. The system may compute, at scale, datasets having complex relationships using graph analysis to determine network effects of entities in a network of entities stored in a graph database. The system may identify entities of interest, which may be associated with a quantitative feature value. The system may compute paths from an entity to the entities of interest, centrality metrics for entities in each of the paths, and path lengths to determine network effects of the entity of interests on the entity. The system may use the computed network effects, taking into account types of relationships between entities in the paths, to determine scaled quantitative feature values for the entity that is subject to the network effects of the entities of interest.

Aspects of the present disclosure relate to machine learning techniques for identifying collections of items, such as furniture items, that are visually complementary. These techniques can rely on computer vision and item imagery. For example, a first portion of a machine learning system can be trained to extract aesthetic item qualities or attributes from pixel values of images of the items. A second portion of the machine learning system can learn correlations between these extracted aesthetic qualities and the level of visual coordination between items. Thus, the disclosed techniques use computer vision machine learning to programmatically determine whether items visually coordinate with one another based on pixel values of images of those items.