An information processing apparatus acquires video image data that includes target objects including a person and an object, and specifies, by using graph data that indicates a relationship between each of target objects stored in a storage unit, a relationship between each of the target objects included in the acquired video image data. The information processing apparatus specifies, by using a feature value of the person included in the acquired video image data, a behavior of the person included in the video image data. The information processing apparatus predicts, by inputting the specified behavior of the person and the specified relationship to a probability model, a future behavior or a future state of the person.

A method for detecting boundaries of lanes on a road is presented. The method comprises receiving, by one or more processors from an imaging system, a set of pixels associated with lane markings. The method further includes partitioning, by the one or more processors, the set of pixels into a plurality of groups. Each of the plurality of groups is associated with one or more control points. The method further includes generating, by the one or more processors, a spline that traverses the control points of the plurality of groups. The spline traversing the control points describes a boundary of a lane.

A method for detecting boundaries of lanes on a road is presented. The method comprises receiving, by one or more processors from an imaging system, a set of pixels associated with lane markings. The method further includes partitioning, by the one or more processors, the set of pixels into a plurality of groups. Each of the plurality of groups is associated with one or more control points. The method further includes generating, by the one or more processors, a spline that traverses the control points of the plurality of groups. The spline traversing the control points describes a boundary of a lane.

Provided is a method for feature extraction of a remote sensing image based on tensor collaborative graph discriminant analysis, including: taking each of pixels as a center for intercepting a three-dimensional tensor data block; dividing experimental data into a training set and a test set in proportion; computing a Euclidean distance between a current training pixel and each class of training data; configuring a L2 norm collaborative representation model with a weight constraint; acquiring a projection matrix of each dimension of each of the three-dimensional tensor data block; and utilizing a low-dimensional projection matrix to obtain a training set and a test set, expanding the training set and the test set into a form of column vectors according to a feature dimension, inputting extracted low-dimensional features into a support vector machine classifier for classification, to determine a class of the test set, and evaluating, by a classification effect, performance of feature extraction.

Provided is a method for feature extraction of a remote sensing image based on tensor collaborative graph discriminant analysis, including: taking each of pixels as a center for intercepting a three-dimensional tensor data block; dividing experimental data into a training set and a test set in proportion; computing a Euclidean distance between a current training pixel and each class of training data; configuring a L2 norm collaborative representation model with a weight constraint; acquiring a projection matrix of each dimension of each of the three-dimensional tensor data block; and utilizing a low-dimensional projection matrix to obtain a training set and a test set, expanding the training set and the test set into a form of column vectors according to a feature dimension, inputting extracted low-dimensional features into a support vector machine classifier for classification, to determine a class of the test set, and evaluating, by a classification effect, performance of feature extraction.

Computer automated interactive activity recognition based on keypoint detection includes retrieving, by one or more processors, a temporal sequence of image frames from a video recording. The one or more processors identify first and second keypoints in each of the image frames in the temporal sequence using machine learning techniques. The first keypoints are associated with an object in the temporal sequence of image frames while the second keypoints are associated with an individual interacting with the object. The one or more processors combine the first keypoints with the second keypoints and extract spatial-temporal features from the combination that are used to train a classification model based on which interactive activities can be recognized.

A computer-implemented method for generating feedback based on a handwritten text, comprises the steps of initializing a writing instrument to be used in a writing operation comprising a handwritten text and capturing and processing the handwritten text to generate digital text data. The method further comprises the steps of identifying at least one handwritten text attribute associated with the digital text data, comparing the at least one handwritten text attribute with predefined textual feature attributes, and generating a textual feature based on the compared at least one handwritten text attribute and predefined textual feature attributes. In addition, the method comprises the steps of modifying the digital text data using the textual feature and generating feedback to a user based on the modified digital text data.

In one embodiment, a method includes extracting a document object model (DOM) for a content page, wherein the DOM comprises a hierarchical tree-based data structure. The method also includes identifying candidate nodes in the DOM based on a context of the nodes, wherein the candidate nodes may correspond to listing items. The method additionally includes for each of the candidate nodes, locating its parent and child nodes by traversing the DOM from the candidate node, extracting information from the candidate node and its parent and child nodes, and assessing whether the candidate node qualifies as a listing item based on whether the extracted information fulfills a required set of characteristics for a listing item.

An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.

Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.