Abstract: The electronic device includes a folding apparatus and a flexible display. The folding apparatus is configured to bear the flexible display. An elastic component of the folding apparatus may transfer an elastic force to the flexible display by using a housing of the folding apparatus. A force that is away from a main shaft and that is applied to the flexible display when the electronic device is in a flattened state is greater than a force that is away from the main shaft and that is applied to the flexible display when the electronic device is in a closed state.

Abstract: Carbon nanoparticle-porous skeleton composite material, its composite with lithium metal, and their preparation methods and use A carbon nanoparticle-porous skeleton composite material, its composite with lithium metal, and their preparation methods and use. In the carbon nanoparticle-porous skeleton composite material, the porous skeleton is a carbon-based porous microsphere material with a diameter of 1 to 100 ?m or a porous metal material having internal pores with a micrometer-scale pore size distribution, and the carbon nanoparticles are distributed in pores and on the surface of the carbon-based porous microsphere material or the porous metal material. The carbon nanoparticle-porous skeleton composite material is mixed with a molten lithium metal to form a lithium-carbon nanoparticle-porous skeleton composite material.

Abstract: Systems and methods for providing a neural network system for time series forecasting are described. A time series dataset that includes datapoints at a plurality of timestamps in an observed space is received. The neural network system is trained using the time series dataset. The training the neural network includes: generating, using an encoder of the neural network system, one or more estimated latent variables of a latent space for the time series dataset; generating, using an auxiliary predictor of the neural network system, a first latent-space prediction result based on the one or more estimated latent variables; transforming, using a decoder of the neural network system, the first latent-space prediction result to a first observed-space prediction result; and updating parameters of the neural network system based on a loss based on the first observed-space prediction result.

Abstract: Embodiments described herein provide a time-index model for forecasting time-series data. The architecture of the model takes a normalized time index as an input, uses a model, g_?, to produce a vector representation of the time-index, and uses a “ridge regressor” which takes the vector representation and provides an estimated value. The model may be trained on a time-series dataset. The ridge regressor is trained for a given g_? to reproduce a given lookback window. g_? is trained over time-indexes in a horizon window, such that g_? and the corresponding ridge regressor will accurately predict the data in the horizon window. Once g_? is sufficiently trained, the ridge regressor can be updated based on that final g_? over a lookback window comprising the time-indexes with the last known values. The final g_? together with the updated ridge regressor can be given time-indexes past the known values, thereby providing forecasted values.

Abstract: Systems and methods for providing a neural network system for time series forecasting are described. A time series dataset that includes datapoints at a plurality of timestamps in an observed space is received. A first state-space model of a dynamical system underlying the time series dataset is provided. The first state-space model includes a non-parametric latent transition model. One or more latent variables of a latent space for the time series dataset are determined using the neural network system based on the first state-space model. A first prediction result for the time series dataset is provided by the neural network system based on the estimated latent variables.

Abstract: Embodiments described herein provide using a measure of distance between time-series data sequences referred to as optimal transport warping (OTW). Measuring the OTW distance between unbalanced sequences (sequences with different sums of their values) may be accomplished by including an unbalanced mass cost. The OTW computation may be performed using cumulative sums over local windows. Further, embodiments herein describe methods for dealing with time-series data with negative values. Sequences may be split into positive and negative components before determining the OTW distance. A smoothing function may also be applied to the OTW measurement allowing for a gradient to be calculated. The OTW distance may be used in machine learning tasks such as clustering and classification. An OTW measurement may also be used as an input layer to a neural network.

Abstract: Embodiments described herein provide a method of forecasting time series data at future timestamps in a dynamic system. The method of forecasting time series data also includes receiving, via a data interface, a time series dataset. The method also includes determining, via a frequency attention layer, a seasonal representation based on a frequency domain analysis of the time series data. The method also includes determining, via an exponential attention layer, a growth representation based on the seasonal representation. The method also includes generating, via a decoder, a time series forecast based on the seasonal representation and the trend representation.

Abstract: Embodiments provide a framework combining fast and slow learning Networks (referred to as “FSNet”) to train deep neural forecasters on the fly for online time-series fore-casting. FSNet is built on a deep neural network backbone (slow learner) with two complementary components to facilitate fast adaptation to both new and recurrent concepts. To this end, FSNet employs a per-layer adapter to monitor each layer's contribution to the forecasting loss via its partial derivative. The adapter transforms each layer's weight and feature at each step based on its recent gradient, allowing a finegrain per-layer fast adaptation to optimize the current loss. In addition, FSNet employs a second and complementary associative memory component to store important, recurring patterns observed during training. The adapter interacts with the memory to store, update, and retrieve the previous transformations, facilitating fast learning of such patterns.

Abstract: A moving device for a three-dimensional scanner, including a main body, a moving mechanism, a round tube, a driving mechanism and a fixing mechanism. A connecting rod is vertically fixed on an upper side of the main body. The moving mechanism is configured to drive the main body to move. The round tube is sleevedly provided on an outer side of the connecting rod. A fixing sleeve is vertically fixed on an inner side wall of the round tube. A sliding rod is insertedly provided in the fixing sleeve. A lower end of the sliding rod is fixedly connected to the main body, and an upper end extends to be below the 3D scanner and is provided with a top plate. When the round tube moves upward to an outer side of the 3D scanner, the round tube is fixed by the fixing mechanism.

Abstract: A method includes receiving, via a data interface, a training dataset of time-series data samples; and generating, by an encoder of a representation training model, intermediate representations of a training data sample from the training dataset. One or more trend feature representations are generated based on the intermediate representations. One or more seasonal feature representations are generated based on the intermediate representations. The representation training model is trained, using the one or more trend feature representations and one or more seasonal feature representations, to generate a trained representation training model.

Abstract: In the field of artificial intelligence technologies, a gaze correction method and apparatus for a face image, a device, a computer-readable storage medium, and a computer program product are provided. The method includes: acquiring an eye image from a face image; determining an eye movement flow field based on the eye image and a target gaze direction, the target gaze direction being a gaze direction to which an eye gaze in the eye image is to be corrected; adjusting a pixel position in the eye image based on the eye movement flow field, to obtain a corrected eye image; and generating a face image with a corrected gaze based on the corrected eye image.

Abstract: An image gaze correction method, apparatus, electronic device, computer-readable storage medium, and computer program product. The image gaze correction method includes: acquiring a to-be-corrected eye image from a to-be-corrected image, generating, based on the to-be-corrected eye image, an eye motion flow field and an eye contour mask, the eye motion flow field being used for adjusting a pixel position in the to-be-corrected eye image, and the eye contour mask being used for indicating a probability that the pixel position in the to-be-corrected eye image belongs to an eye region, performing, based on the eye motion flow field and the eye contour mask, gaze correction processing on the to-be-corrected eye image to obtain a corrected eye image, and generating a gaze corrected image based on the corrected eye image.

Abstract: The disclosure relates to method and apparatus for operating image data. The method includes: reading matrix data from the image data based on a matrix size, M rows and N columns, of an image operator (220); calculating column data in the matrix data with a single calculation instruction corresponding to the image operator, to obtain an intermediate calculation result (240); multiplexing and rearranging the intermediate calculation result into N rows of cached data (260); calculating matrix elements of a target column in the N rows of cached data with the single calculation instruction, to obtain a calculation result of the matrix data under the single calculation instruction (280); and outputting the calculation result as an image processing result of the matrix data by the image operator (300).

Abstract: A moving device for a three-dimensional scanner, including a main body, a moving mechanism, a round tube, a driving mechanism and a fixing mechanism. A connecting rod is vertically fixed on an upper side of the main body. The moving mechanism is configured to drive the main body to move. The round tube is sleevedly provided on an outer side of the connecting rod. A fixing sleeve is vertically fixed on an inner side wall of the round tube. A sliding rod is insertedly provided in the fixing sleeve. A lower end of the sliding rod is fixedly connected to the main body, and an upper end extends to be below the 3D scanner and is provided with a top plate. When the round tube moves upward to an outer side of the 3D scanner, the round tube is fixed by the fixing mechanism.

Abstract: Disclosed are a metallic lithium-skeleton carbon composite material having a hydrophobic cladding layer, a preparation method thereof, an electrode, an electrochemical energy storage device containing the metallic lithium-skeleton carbon composite material, and a method for protecting a material containing a water- and oxygen-sensitive active metal. The metallic lithium-skeleton carbon composite material having a hydrophobic cladding layer comprises: a metallic lithium-skeleton carbon composite material comprising a porous carbonaceous support and metallic lithium at least distributed in pores of the porous carbonaceous support; and a hydrophobic cladding layer covering at least the metallic lithium in the metallic lithium-skeleton carbon composite material.

Abstract: Carbon nanoparticle-porous skeleton composite material, its composite with lithium metal, and their preparation methods and use A carbon nanoparticle-porous skeleton composite material, its composite with lithium metal, and their preparation methods and use. In the carbon nanoparticle-porous skeleton composite material, the porous skeleton is a carbon-based porous microsphere material with a diameter of 1 to 100 ?m or a porous metal material having internal pores with a micrometer-scale pore size distribution, and the carbon nanoparticles are distributed in pores and on the surface of the carbon-based porous microsphere material or the porous metal material. The carbon nanoparticle-porous skeleton composite material is mixed with a molten lithium metal to form a lithium-carbon nanoparticle-porous skeleton composite material.

Abstract: An image processing method includes: obtaining a target image; performing blurring processing on an original image of a specified channel of channels of the target image to obtain a first blurred image; performing high pass processing on the original image of the specified channel and the first blurred image to obtain a high pass image; obtaining, for a channel, a second blurred image corresponding to the channel based on an original image of the channel and the high pass image; and obtaining a processed image corresponding to the target image based on the second blurred image of the channel and the high pass image.

Abstract: A video denoising method includes: performing spatial filtering on pixels of a target image in a video to be processed to obtain a first image, the spatial filtering being used for eliminating dependencies between the pixels of the target image; performing, according to a frame difference between the first image and a first denoised image, temporal filtering on the pixels of the target image in parallel to obtain a second image, the first denoised image being an denoised image that corresponds to a preceding frame of the target image; predicting first gain coefficients corresponding to pixels of the second image in a second denoised image according to second gain coefficients corresponding to the pixels of the target image in the first denoised image; and fusing the first image and the second image according to the first gain coefficients to obtain the second denoised image that corresponds to the target image.

Abstract: An image processing method includes: determining a brightness value of an image; and enhancing a brightness of the image when the brightness value of the image is less than an image brightness threshold. Enhancing the brightness of the image includes: determining each pixel of the image as a target pixel; determining a brightness enhancement value of the target pixel based on the brightness value of the image, an initial brightness value of the target pixel, and initial brightness values of neighboring pixels of the target pixel; and using the brightness enhancement value as an enhanced brightness value of the target pixel.

Abstract: Systems and methods for identifying three dimensional (3D) content to stream. A method includes receiving information indicating a view field of a client device and identifying an amount of bandwidth available to stream the 3D content to the client device. The method includes assigning, for one or more of the objects, the bandwidth by, for each of the objects: determining whether the each object is within the view field of the client device based on a position of the each object; assigning a greater amount of the bandwidth to objects at least partially within the view field. The method includes streaming the 3D content to the client device according to the assigned bandwidth.