Abstract: This disclosure relates to an image processing method, an image processing apparatus, a device, and a storage medium, wherein after acquiring an expression image, an expression in the expression image can be adjusted based on a preset image processing model to generate a video with a change process of the expression, and the video is displayed to the user.

Abstract: A method for restoring electrochemical activity and cycling stability to spent graphite anode material for a lithium-ion battery includes exposing powdered graphite anode material to boric acid to form borated material, then sintering the borated material. The processing removes dead lithium from the bulk structure and applies boron doping to surfaces of the graphite material.

Abstract: A method for regeneration of spent cathode material of lithium-ion batteries involves lithiating the cathode material in a relithiation solution including a reducing agent at a temperature in the range of 60° C. to 180° C. for a sufficient time to heal composition defects in the cathode material. The lithiated material is then sintered to completely recover the properties. The relithiation solution may be a Li-ion source combined with nature-based organic reducing agent such as citric acid, ascorbic acid, tartaric acid, or similar.

Abstract: The present disclosure provides a wireless flexible magnetic sensor based on magnetothermal effect, and a preparation method and a detection method thereof. The magnetic sensor includes an aerogel substrate, and magnetic nanoparticles having magnetothermal effect that are attached to a surface of the aerogel substrate. The magnetic sensor is placed in the alternating magnetic field to be measured, and then a trigger signal is generated by a data collecting device and sent to an infrared camera. The infrared camera can collect temperature distribution information at different instants of time from the surface of the magnetic sensor. A curve of temperature rise changes at different positions on the surface of the magnetic sensor can be obtained by analyzing a temperature distribution image captured by the infrared camera. Thus, a spatial distribution of the strength of the alternating magnetic field at different positions on the surface of the sensor can be determined.

Abstract: The present disclosure provides a method and apparatus for processing three dimensional graphic data, a device, a storage medium and a product, relating to a field of artificial intelligence, in particular to a field of autonomous driving. The specific implementation is: receiving a data compression request for a target graphic element in a three dimensional electronic map, and obtaining at least one vertex data corresponding to the target graphic element; extracting a global coordinate matrix with a shared attribute in the at least one vertex data; extracting local coordinate data with a private attribute respectively corresponding to the at least one vertex data; and sending, in response to a graphic drawing request for the target graphic element, the global coordinate matrix and the local coordinate data respectively corresponding to the at least one vertex data to a graphic display device.

Abstract: The present disclosure provides a wireless flexible magnetic sensor based on magnetothermal effect, and a preparation method and a detection method thereof. The magnetic sensor includes an aerogel substrate, and magnetic nanoparticles having magnetothermal effect that are attached to a surface of the aerogel substrate. Themagnetic sensor is placed in the alternating magnetic field to be measured, and then a trigger signal is generated by a data collecting device and sent to an infrared camera. The infrared camera can collect temperature distribution information at different instants of time from the surface of the magnetic sensor. A curve of temperature rise changes at different positions on the surface of the magnetic sensor can be obtained by analyzing a temperature distribution image captured by the infrared camera. Thus, a spatial distribution of the strength of the alternating magnetic field at different positions on the surface of the sensor can be determined.

Abstract: Systems and methods are disclosed for identifying target graphs that have nodes or neighborhoods of nodes (sub-graphs) that correspond with an input query graph. A visual analytics system supports human-in-the-loop, example-based subgraph pattern search utilizing a database of target graphs. Users can interactively select a pattern of nodes of interest. Graph neural networks encode topological and node attributes in a graph as fixed length latent vector representations such that subgraph matching can be performed in the latent space. Once matching target graphs are identified as corresponding to the query graph, one-to-one node correspondence between the query graph and the matching target graphs.

Abstract: A computer-implemented method includes receiving one or more images from one or more sensors, creating one or more image patches utilizing the one or more images, creating one or more latent representations from the one or more image patches via a neural network, outputting, to a concept extractor network, the one or more latent representations utilizing the one or more image patches, defining one or more scores associated with the one or more latent representations, and outputting one or more scores associated with the one or more image patches utilizing at least the concept extractor network.

Abstract: Methods and systems for providing an interactive image scene graph pattern search are provided. A user is provide with an image having a plurality of selectable segmented regions therein. The user selects one or more of the segmented regions to build a query graph. Via a graph neural network, matching target graphs are retrieved that contain the query graph from a target graph database. Each matching target graph has matching target nodes that match with the query nodes of the query graph. Matching target images from an image database are associated with the matching target graphs. Embeddings of each of the query nodes and the matching target nodes are extracted. A comparison of the embeddings of each query node with the embeddings of each matching target node is performed. The user interface displays the matching target images that are associated with the matching target graphs.

Abstract: A novel interpretable and steerable deep sequence modeling technique is disclosed. The technique combines prototype learning and RNNs to achieve both interpretability and high accuracy. Experiments and case studies on different real-world sequence prediction/classification tasks demonstrate that the model is not only as accurate as other state-of-the-art machine learning techniques but also much more interpretable. In addition, a large-scale user study on Amazon Mechanical Turk demonstrates that for familiar domains like sentiment analysis on texts, the model is able to select high quality prototypes that are well aligned with human knowledge for prediction and interpretation. Furthermore, the model obtains better interpretability without a loss of performance by incorporating the feedback from a user study to update the prototypes, demonstrating the benefits of involving human-in-the-loop for interpretable machine learning.

Abstract: A deep sequence model with prototypes may be steered. A prototype overview is displayed, the prototype overview including a plurality of prototype sequences learned by a model through backpropagation, each of the prototype sequences including a series of events, where for each of the prototype sequences, statistical information is presented with respect to use of the prototype sequence by the model. Input is received adjusting one or more of the prototype sequences to fine-tune the model. The model is updated using the plurality of prototype sequences, as adjusted, to create an updated model. The model, as updated, is displayed in the prototype overview.

Abstract: Regeneration of degraded cathode particles in lithium-ion batteries is achieved using a combination of hydrothermal treatment of cycled electrode particles followed by short thermal annealing. The methods provide for direct regeneration of Li-ion cathode materials including LiCoO2, LiMn2O4, LiFePO4, and LixNiy Mnz Co1?y?zO2, in an economical and environmentally-friendly process.

Abstract: A method may include receiving a set of images, analyzing the images, selecting an internal layer, extracting neuron activations, factorizing the neuron activations via a matrix factorization algorithm to select prototypes and generate weights for each of the selected prototypes, replacing the neuron activations of the internal layer with the selected prototypes and the weights for the selected prototypes, receiving a second set of images, classifying the second set of images using the prototypes and weights, displaying the second set of images, selected prototypes, and weights, displaying predicted results and ground truth for the second set of images, providing error images based on the predicted results and ground truth; identifying error prototypes of the selected prototypes associated with the error images; ranking error weights of the error prototypes, and outputting a new image class based on the error prototypes being one of a top ranked error weights.

Abstract: A method to interpret a deep neural network that includes receiving a set of images, analyzing the set of images via a deep neural network, selecting an internal layer of the deep neural network, extracting neuron activations at the internal layer, factorizing the neuron activations via a matrix factorization algorithm to select prototypes and generate weights for each of the selected prototypes, replacing the neuron activations of the internal layer with selected prototypes and weights for each of the selected prototypes, receiving a second set of images, and classifying the second set of images via the deep neural network using the weighted prototypes without the internal layer.

Abstract: A method for generating a graphical depiction of summarized event sequences includes receiving a plurality of event sequences, each event sequence in the plurality of event sequences including a plurality of events, and generating a plurality of clusters using a minimum description length (MDL) optimization process. Each cluster in the plurality of clusters including a set of at least two event sequences in the plurality of event sequences that maps to a pattern in each cluster. The pattern in each cluster further includes a plurality of events included in at least one event sequence in the set of at least two event sequences in the cluster. The method includes generating a graphical depiction of a first cluster in the plurality of clusters, the graphical depiction including a graphical depiction of a first plurality of events in the pattern of the first cluster.

Abstract: A deep sequence model with prototypes may be steered. A prototype overview is displayed, the prototype overview including a plurality of prototype sequences learned by a model through backpropagation, each of the prototype sequences including a series of events, where for each of the prototype sequences, statistical information is presented with respect to use of the prototype sequence by the model. Input is received adjusting one or more of the prototype sequences to fine-tune the model. The model is updated using the plurality of prototype sequences, as adjusted, to create an updated model. The model, as updated, is displayed in the prototype overview.

Abstract: A method for extracting a pattern from spatio-temporal (ST) data includes receiving ST data, storing the ST data as s multi-dimensional array in a memory, and extracting at least one pattern from the ST data. The extracting includes generating a model approximating at least a portion of the array, and generating a visualization of a loading vector of the approximation. The ST data includes records with multiple categories of information, one of which is spatial, and one of which is temporal. Each dimension corresponds to a respective one of the categories of information. Generating the model includes applying tensor decomposition to the array, and extracting the at least one loading vector of the approximation. The extracted loading vector is indicative of a pattern in the ST data.

Abstract: A novel interpretable and steerable deep sequence modeling technique is disclosed. The technique combines prototype learning and RNNs to achieve both interpretability and high accuracy. Experiments and case studies on different real-world sequence prediction/classification tasks demonstrate that the model is not only as accurate as other state-of-the-art machine learning techniques but also much more interpretable. In addition, a large-scale user study on Amazon Mechanical Turk demonstrates that for familiar domains like sentiment analysis on texts, the model is able to select high quality prototypes that are well aligned with human knowledge for prediction and interpretation. Furthermore, the model obtains better interpretability without a loss of performance by incorporating the feedback from a user study to update the prototypes, demonstrating the benefits of involving human-in-the-loop for interpretable machine learning.

Abstract: A method for generating a graphical display of a bipartite graph includes receiving bipartite graph data, generating, a first meta-node including at least two nodes in the first set of nodes in the bipartite graph data and a second meta-node including at least two nodes in a second set of nodes in the bipartite graph data based on the bipartite graph data using a minimum description length (MDL) optimization process to generate the first meta-node and the second meta-node. The method further includes generating a first graphical depiction of the first meta-node and the second meta-node, the graphical depiction including a single edge connecting the first meta-node and the second meta-node to provide a summarized display of the bipartite graph data.

Abstract: A method for extracting a pattern from spatio-temporal (ST) data includes receiving ST data, storing the ST data as s multi-dimensional array in a memory, and extracting at least one pattern from the ST data. The extracting includes generating a model approximating at least a portion of the array, and generating a visualization of a loading vector of the approximation. The ST data includes records with multiple categories of information, one of which is spatial, and one of which is temporal. Each dimension corresponds to a respective one of the categories of information. Generating the model includes applying tensor decomposition to the array, and extracting the at least one loading vector of the approximation. The extracted loading vector is indicative of a pattern in the ST data.