A method for constructing a dictionary to represent data from a training data set comprising: modeling the data as a linear combination of columns; modeling outliers in the data set via deterministic outlier vectors; formatting the training data set in matrix form for processing; defining an underlying structure in the data set; quantifying a similarity across the data; building a Laplacian matrix; using group-Lasso regularizers to succinctly represent the data; choosing scalar parameters for controlling the number of dictionary columns used to represent the data and the number of elements of the training data set identified as outliers; using BCD and PG methods on the vector-matrix-formatted data set to estimate a dictionary, corresponding expansion coefficients, and the outlier vectors; and using a length of the outlier vectors to identify outliers in the data.

A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.

The present disclosure relates to autonomous driving technology, and provides a method and an apparatus for positioning a movable device, as well as a movable device. The method includes: obtaining point cloud data for a predetermined area above the movable device; extracting, from the point cloud data, a first type of point cloud and a second type of point cloud on a left side and a right side of the movable device, respectively; matching the first type of point cloud and the second type of point cloud to obtain a transform matrix; and determining pose information of the movable device based on the transform matrix. With the above process, the present disclosure can solve the problem in the related art associated with accurate positioning of a movable device when GNSS signals are affected and it is difficult to accurately obtain point cloud data in front of the movable device.

A method and system for cross-modal manifold alignment of different data domains includes determining for a shared embedding space a first embedding function for data of a first domain and a second embedding function for data of a second domain using a triplet loss, wherein triplets of the triplet loss include an anchor data point from the first, a positive and a negative data point from the second domain; creating a first mapping for the data of the first domain using the first embedding function in the shared embedding space; creating a second mapping for the data of the second domain using the second embedding function in the shared embedding space; and generating a cross-modal alignment for the data of the first domain and the data of the second domain.

A method for acoustic source separation comprises inputting acoustic data from a plurality of acoustic sensors, combined from a plurality of acoustic sources, converting the acoustic data to time-frequency domain data comprising time-frequency data frames, and constructing a multichannel filter for the time-frequency data frames to separate signals from the acoustic sources. The constructing comprises determining a set of de-mixing matrices (W.sub.f) to apply to each time-frequency data frame to determine a vector of separated outputs (y.sub.ft) by modifying each of the de-mixing matrices by a respective gradient value (G;G′) for a frequency dependent upon a gradient of a cost function measuring a separation of the sources by the respective de-mixing matrix. The respective gradient values for each frequency are each calculated from a stochastic selection of the time-frequency data frames.

A method for determining a sensor configuration in a vehicle which includes a plurality of sensors. The method comprises: (i) establishing a preliminary sensor configuration for the vehicle, which sensor configuration includes a first number of real sensors, each of which outputting a real sensor signal, (ii) determining whether at least one of the real sensors can be replaced by a virtual sensor, and (iii) changing the preliminary sensor configuration into a final sensor configuration which includes a second number of real sensors and at least one virtual sensor which has been determined to replace at least one of the real sensors, wherein the second number is smaller than the first number.

A method and an apparatus for length-aware local tiling in a sparse attention module in a transformer in heterogeneous devices are provided. The method includes that a heterogeneous device including one or more GPUs: divides a transformed sparsity mask into a plurality of first tiles and obtaining one or more effective first tiles from the plurality of first tiles, where each effective first tile includes at least one non-zero element; loads the one or more effective first tiles into a shared memory in the one or more GPUs and loads a plurality of elements in a first matrix corresponding to the one or more effective first tiles into the shared memory; and performs multiplication by a first sampled dense-dense matrix multiplication (SDDMM) kernel in the sparse attention module in the transformer by fetching the one or more effective first tiles and the plurality of elements from the shared memory.

The present invention provides a target tracking method, system, device and storage medium, which includes: Determining a target area based on the current frame of a training sample, extracting and fusing histogram of oriented gradient (HOG), color naming (CN), and color space HSV features of the target area to obtain a target template; Determining a target function according to the target template and a spatial regularization weight factor; Introducing the Sherman-Morrison formula into the alternating direction method of multipliers (ADMM) to accelerate the solution of the target function and obtain the response value; Iterating the target tracking model when the response value meets the preset confidence threshold until training is completed to obtain a trained target tracking model, and tracking the target in the video to be observed by using the trained target tracking model.

In one embodiment, a method includes accessing a stream of F video frames, where each of the F video frames includes N patches that are non-overlapping, generating an initial embedding vector for each of the N×F patches in the F video frames, generating a classification embedding by processing the generated N×F initial embedding vectors using a self-attention-based machine-learning model that computes a temporal attention and a spatial attention for each of the N×F patches, and determining a class of the stream of video frames based on the generated classification embedding.

A server computer may receive and process a plurality of time series data to generate sparse datasets based on sparsity levels. The server computer applies a time series forecasting model to each respective subset of previous data points of the sparse datasets increasingly at the first time granularity to generate a set of prediction values and a set of residuals; applies a regression model to the set of the prediction residuals to generate a set of adjusted residuals for the sparse datasets; and generates a visualized explanation based on the set of the prediction values and the set of adjusted residuals for one or more of the sparse datasets.