Disclosed are systems and methods to extract information about the size and shape of an object by observing variations of the radiation pattern caused by illuminating the object with coherent radiation sources and changing the wavelengths of the source. Sensing and image-reconstruction systems and methods are described for recovering the image of an object utilizing projected and transparent reference points and radiation sources such as tunable lasers. Sensing and image-reconstruction systems and methods are also described for rapid sensing of such radiation patterns. A computational system and method is also described for sensing and reconstructing the image from its autocorrelation. This computational approach uses the fact that the autocorrelation is the weighted sum of shifted copies of an image, where the shifts are obtained by sequentially placing each individual scattering cell of the object at the origin of the autocorrelation space.

This document describes techniques for fine-motion virtual-reality or augmented-reality control using radar. These techniques enable small motions and displacements to be tracked, even in the millimeter or sub-millimeter scale, for user control actions even when those actions are small, fast, or obscured due to darkness or varying light. Further, these techniques enable fine resolution and real-time control, unlike conventional RF-tracking or optical-tracking techniques.

A method comprising operating at least one hardware processor for: receiving, as input, a plurality of electronic documents, training a machine learning classifier based, at least on part, on a training set comprising: (i) labels associated with the electronic documents, (ii) raw text from each of said plurality of electronic documents, and (iii) a rasterized version of each of said plurality of electronic documents, and applying said machine learning classifier to classify one or more new electronic documents.

Provided is a user authentication method and apparatus that obtains first environmental information indicating an environmental condition in which an input image of a user is captured, extracts a first feature vector from the input image, selects a second feature vector including second environmental information that matches the first environmental information from enrolled feature vectors in an enrollment database (DB), and authenticates the user based on the first feature vector and the second feature vector.

Mechanisms are provided to implement an automated echocardiograph measurement extraction system. The automated echocardiograph measurement extraction system receives medical imaging data comprising one or more medical images and inputs the one or more medical images into a deep learning network. The deep learning network automatically processes the one or more medical images to generate an extracted echocardiograph measurement vector output comprising one or more values for echocardiograph measurements extracted from the one or more medical images. The deep learning network outputs the extracted echocardiograph measurement vector output to a medical image viewer.

A three-dimensional bounding box is determined from a two-dimensional image and a point cloud. A feature vector associated with the image and a feature vector associated with the point cloud may be passed through a neural network to determine parameters of the three-dimensional bounding box. Feature vectors associated with each of the points in the point cloud may also be determined and considered to produce estimates of the three-dimensional bounding box on a per-point basis.

Provided is an image classification method, an electronic device and a storage medium, relating to a field of artificial intelligence technology, and specifically, to the technical fields of deep learning, image processing and computer vision, which may be applied to scenes such as image classification. The image classification method includes: extracting a first image feature of a target image by using a first network model, where the first network model includes a convolutional neural network module; extracting a second image feature of the target image by using a second network model, where the second network model includes a deep self-attention transformer network (Transformer) module; fusing the first image feature and the second image feature to obtain a target feature to be recognized; and classifying the target image based on the target feature to be recognized.

A system, device and method are provided for generating image processing models for selected hardware. The method, illustratively, includes obtaining a reference model, a desired image resolution based on target hardware, and a training set of images comprising images with the desired image resolution and images with a higher resolution. The method includes generating an updated model by: iteratively training the reference model with a combined set of features, the combined set of features comprising features determined from the images with the higher resolution with at least one stem and features determined from the images with the desired resolution. The method includes outputting the trained updated model to the target hardware to process images with the desired image resolution.

Disclosed are a method for predicting reconstructability, a computer device, and a storage medium. In the method, a plurality of viewpoints to be evaluated for a target sampling point are obtained. The target sampling point is located on a rough geometric model. A spatial characteristic of the target sampling point is obtained based on spatial relationships between the plurality of viewpoints to be evaluated and the target sampling point. An image characteristic of the target sampling point is extracted from a target captured image based on a plurality of pre-acquisition viewpoints. The pre-acquisition viewpoints are obtained based on poses of a camera capturing the target captured image. The target captured image is an image containing the target sampling point. The predicting reconstructability for the target sample point is predicted based on the image characteristic and the spatial characteristic.

A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.