A method and a system for obtaining a product prototype based on an eye movement data. The method comprises the following steps: Obtaining A front-side view of the target product for establishing a underlying sample library; The target product is divided into several detection areas according to its structure or function features, and the eye movement is detected to obtain the fixation time of the target product The invention adopts computer and image collecting technology to process the observation data of human eyes, and adopts K-means clustering to obtain the prototype of the target product, to assist the designer to grasp the categories of personal interest contour, so as to improve the design effect of product appearance.

Using detection of low variance regions for improving detection is described. In an example, sensor data can be received from a sensor associated with a vehicle. The sensor data can represent an environment. An indication of a low variance region associated with the sensor data can be determined and an indication of a high variance region associated with the sensor data can be determined based at least in part on the indication of the low variance region. The vehicle can be controlled based on at least one of the sensor data or the indication of the high variance region.

A method for generating positive and negative training samples is presented. The method includes identifying false positive images of an object based on multiple images of an environment. The method also includes generating positive training samples from a set of images of the object. The method further includes generating a negative training sample from the false positive image. The method still further includes training an object detection system based on the positive training samples and the negative training sample.

Example systems may include a head-mounted device configured to present an artificial reality view to a user, a control device including a plurality of electromyography (EMG) sensors, and at least one physical processor programmed to receive EMG data based on signals detected by the EMG sensors, detect EMG signals corresponding to user gestures within the EMG data, classify the EMG signals to identify gesture types, and provide control signals based on the gesture types, wherein the control signal triggers the head-mounted device to modify the artificial reality view. Various other methods, systems, and computer-readable media are also disclosed.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated detection of emergent behaviors in interactive agents of an interactive environment. The disclosed system represents an artificial intelligence based entity that utilizes a trained machine-learning-based clustering algorithm to group users together based on similarities in behavior. The clusters are processed based on a determination of the type of activity of the clustered users. In order to identify new categories of behavior and to label those new categories, a separate cluster analysis is performed using interaction data obtained at a subsequent time. The additional cluster analysis determines any change in behavior between the clustered sets and/or change in the number of users in a cluster. The identification of emergent user behavior enables the subject system to treat users differently based on their in-game behavior and to adapt in near real-time to changes in their behavior.

An example method performed by a processing system includes obtaining a light detecting and ranging point cloud of a building, where the point cloud includes a plurality of points, and where each point is associated with a set of (x,y,z) coordinates. A first point of the plurality of points is assigned to a subset of the plurality of points that is associated with the building, where the subset includes points whose (x,y) coordinates fall within a footprint of the building. The first point is grouped into a first cluster according to at least one of: a (z) coordinate of the first point and a gradient to which the first point belongs. A first prism formed by the first cluster is constructed. A model of the building is stored as a plurality of connected prisms, where the plurality of connected prisms includes the first prism.

A method is provided that includes receiving points of an image in which objects are depicted. The method includes performing a greedy nearest-neighbor (GNN) cluster analysis of the image to group the points of the image. The GNN cluster analysis includes grouping the points into a plurality of local GNN clusters, from a greedy analysis using a k-d tree in which the points are organized. The plurality of local GNN clusters are then extended into a plurality of global GNN clusters. This evaluating similarity of the local GNN clusters, merging the local GNN clusters into a global GNN cluster when each of the defined similarity criteria is evaluated to true, and passing the local GNN clusters as global GNN clusters when any of the defined similarity criteria is evaluated to false. The method then includes detecting the objects depicted in the image based on the global GNN clusters.

Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

A method and system for clustering-based panoptic segmentation of point clouds and a method of training the same are provided. Features of a point cloud that includes a plurality of points are extracted. Clusters of the plurality of points corresponding to objects from the features of the point cloud frame are identified. A subset of the plurality of points is selectively shifted using the features and the clusters of the plurality of points via a neural network that is trained to recognize a subset of points of objects that are closer to points of other objects than a distance between centroids of the corresponding objects and shift the subset of points away from the other objects.

This document generally relates to techniques for testing or training data augmentation. One example includes a method or technique that can include accessing a repository of private data items. The repository can provide a distribution of the private data items that is representative of a designated real-world scenario for a machine learning model. The method or technique can also include assigning classifications to the private data items in the repository. The method or technique can also include augmenting a testing or training set for the machine learning model based at least on the classifications of the private data items to obtain an augmented testing or training set that is relatively more representative of the distribution of classifications in the repository.