Abstract: An example operation may include one or more of generating a three-dimensional (3D) model of an object via execution of a machine learning model on one or more images of the object, capturing a plurality of snapshots of the 3D model of the object at different angles to generate a plurality of snapshot images of the object, fusing a feature into each of the plurality of snapshots to generate a plurality of fused snapshots of the 3D model of the object, and storing the plurality of fused snapshots of the 3D model of the object in memory.

Abstract: Detecting fine-grained similarity in image includes determining a core area of a search image by generating an image salient map from a plurality of layers of the search image and determining a connected area based on the image salient map. Feature descriptors are generated from the core area of the search image. A plurality of capsule vectors are generated from different ones of a plurality of keypoints of the feature descriptors. Capsule vectors of the search image are compared with capsule vectors of each image of the dataset to generate a top-K matrix. Similarity scores for the top-K matrix are calculated. One or more image of the dataset having fine-grained similarity with the search image are selected based a bundled similarity score for each image of the dataset. The bundled similarity score is a summation of the similarity scores of the image.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to detecting a closed ring in a three-dimensional (3D) point cloud via cycle basis. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a filtering component that can filter a first undirected graph of a three-dimensional (3D) point cloud, by eliminating one or more edges of the first undirected graph that are longer than an adaptive threshold, wherein filtering the first undirected graph can produce a second undirected graph; and a detection component that can detect a minimum cycle basis of the second undirected graph to determine a cycle path that can traverse an irregular annular shape that is represented by the 3D point cloud.

Abstract: A user input in a source language is received. A set of contextual data is received. The user input is encoded into a user input feature vector. The set of contextual data is encoded into a context feature vector. The user input feature vector and the context feature vector are used to generate a fusion vector. An adaptive neural network is trained to identify a second context feature vector, based on the fusion vector. A second user input in the source language is received for translation into a target language. The adaptive neural network is used to determine, based on the second context feature vector, a second user input feature vector. The second user input feature vector is decoded, based on the source language and the target language, into a target language output. A user is notified of the target language output.

Abstract: A computer-implemented method, system and computer program product for improving accuracy of a vision model. Images of an object with a first set of perspectives are received from a dataset used to train the vision model. A three-dimensional model of the object is then generated using the images of the object from the dataset. Using the three-dimensional model of the object, images of the object with a second set of perspectives are obtained. For example, the second set of perspectives may include different perspectives than the perspectives of the object from the images contained in the dataset. The dataset used to train the vision model may then be augmented with such images of the object with a second set of perspectives. In this manner, the dataset used to train the vision model includes a greater number of perspectives of the object thereby improving the accuracy of the vision model.

Abstract: Embodiments of the present invention relate to methods, systems, and computer program products for managing a plurality of live comments. A plurality of live comments is obtained for a video, the plurality of live comments being associated with a plurality of fragments in the video, respectively. A plurality of features are extracted from the plurality of live comments, respectively. A knowledge base is generated for the plurality of live comments based on the plurality of features. With these embodiments, the live comments may be managed in an effective way. Further, the knowledge base may provide answers to a user query.

Abstract: A flexible battery includes a plurality of electrode assemblies, an electrical connector, elastic insulation members, and a package bag. The electrical connector is electrically connected to two adjacent electrode assemblies. The elastic insulation members are disposed at two end terminals of the electrical connector and have a gap with the electrode assemblies. The package bag is provided with a first dent accommodating the electrode assembly and the elastic insulation member, and a second dent accommodating the electrical connector. In the flexible battery, stress concentration caused by bending after packaging can be effectively reduced, so the package bag and electrical connector of the flexible battery are not prone to fracture, providing effective protection for the electrode assemblies, improving service life of the flexible battery, and ensuring stable performance and safety of the flexible battery.

Abstract: A battery pack, including a housing, a circuit board, and a plurality of electrode assemblies. The housing includes a first surface and a second surface opposite to each other. The first surface is provided with a plurality of first slots. The battery pack further includes a plurality of first caps, and the plurality of first caps respectively cover the plurality of first slots to form a plurality of mutually separated accommodation spaces. The electrode assemblies each includes an electrode plate assembly, a first electrode tab, and a second electrode tab. The electrode plate assembly is accommodated in the accommodating space. The first tab and the second tab extend out of the accommodating space. At least one first electrode tab and at least one second electrode tab are electrically connected to the circuit board. The structure and the manufacturing process of the battery pack can be simplified.

Abstract: An electrode assembly includes a first electrode plate, a separator, and a second electrode plate that are disposed in a stack. The first electrode plate and the second electrode plate respectively have coating areas and empty foil areas arranged at intervals. Centers of the coating areas overlap each other to form a coating portion of the electrode assembly, and centers of the empty foil areas overlap each other to form a flexible portion of the electrode assembly. The first packaging layer coats the coating portion and the flexible portion of the electrode assembly, and the second packaging layer at least coats the first packaging layer on the flexible portion.

Abstract: An example operation may include one or more of generating a three-dimensional (3D) model of an object via execution of a machine learning model on one or more images of the object, capturing a plurality of snapshots of the 3D model of the object at different angles to generate a plurality of snapshot images of the object, fusing a feature into each of the plurality of snapshots to generate a plurality of fused snapshots of the 3D model of the object, and storing the plurality of fused snapshots of the 3D model of the object in memory.

Abstract: A cognitive well log analysis using a computer includes receiving, by one or more processors, well log data from a plurality of well logs. One or more processors identify geometric features, specific values, and well attributes from the received well log data and embed the identified features to generate a plurality of intermediate vectors arranged based on a relevance for identifying petrophysical properties. The intermediate vectors are combined to create a fusion vector based on which the one or more processors identify reservoir layers.

Abstract: An electrochemical apparatus, including two electrode assemblies and a packaging shell, where the two electrode assemblies are respectively disposed in independent cavities in the packaging shell; each electrode assembly includes two tabs with opposite polarities, where at least one tab of one electrode assembly is connected to one of two tabs of the other electrode assembly, and orthographic projections of the two connected tabs along a seal thickness direction Z overlap to form a tab overlapping region; and a ratio ? of an overlapping width of the two connected tabs along a seal length direction X at an outer edge of a seal of the packaging shell viewed along the seal thickness direction Z to a width of either of the two connected tabs satisfies 40%<??100%. The electrochemical apparatus not only implements high-voltage output, but also improves packaging reliability of a tab region during the high-voltage output.

Abstract: A liquid state battery includes a housing, a separator, a first slurry, a first current collector, a second slurry, a second current collector, a first tab, and a second tab having a different polarity than the first tab. The housing encloses a receiving space. The separator is disposed in the receiving space and divides the receiving space into a first chamber and a second chamber. The first slurry and the first current collector are disposed in the first chamber. The second slurry and the second current collector are disposed in the second chamber. The first tab is electrically connected to the first current collector and extending outside the housing. The second tab is electrically connected to the second current collector and extending outside the housing. This application further provides an electronic device containing such liquid state battery.

Abstract: A computer-implemented method includes receiving a viewer request for playing a video summary of a video, wherein the viewer request includes a length of the video summary, generating the video summary of the viewer-requested length comprising a set of frames selected from the video based on audience reviews of the video, and playing a video stream of the video summary.

Abstract: Disclosed herein are a battery cell housing, a battery cell, a battery, and an electric device. The battery cell housing defines a cavity configured to accommodate an electrode assembly, and the battery cell housing includes a first housing and a second housing. The first housing is electrically connected to a first tab of the electrode assembly. The second housing is fixed to the first housing in an insulated manner. The second housing is electrically connected to a second tab of the electrode assembly and the second tab is different from the first tab in polarity. The first housing includes a bulge electrically connected to the first tab, and the bulge extends in a direction approaching the second housing. Therefore, there is no need to provide a hole in the battery cell housing, thereby rendering the battery cell housing more integral.

Abstract: A system, method, and computer program product for implementing video action recognition is provided. The method includes receiving a video stream comprising user movement actions. Skeleton points associated with a video representation of a user executing the user movement actions are extracted and categorized with respect to multiple digital levels. Initial visual windows points are generated within video frames and an average movement distance for the group of skeleton points are determined with respect to the video frames. In response, sizes for the visual windows are adjusted and feature vectors are extracted from the group of skeleton points. Point coordinates of the skeleton points are extracted and linked with the feature vectors. A convolutional neural network associated with linking the feature vectors with the point coordinates is generated and the video stream is enabled with respect to video action recognition associated with accurate presentation of the video stream.

Abstract: A current collector, an electrochemical device containing the current collector, and an electronic device. The current collector includes a polymer substrate material and a conductive material. An electron resistivity of the current collector in an X-Y in-plane direction is 10 ?·cm to 1000 ?·cm, and an electron resistivity of the current collector in a Z direction is 0.01 ?·cm to 30 ?·cm. The current collector according to this application is excellent in oxidation resistance, reduction resistance, ionic insulation, mechanical strength, thermal stability, increases the energy density of bipolar electrochemical devices, and is more cost-effective and more suitable for mass production.

Abstract: A partition plate includes a partition substrate, a positive electrode membrane, a negative electrode membrane, and an insulation layer. The positive electrode membrane and the negative electrode membrane are respectively located on two surfaces of the partition substrate. The insulation layer is disposed on the partition substrate and the insulation layer is disposed at a periphery of the positive electrode membrane. A zone surrounded by orthographic projection of an outer edge of the insulation layer on the partition substrate covers orthographic projection of the negative electrode membrane on the partition substrate. This application can improve self-discharge and safety performances of electrochemical apparatuses.

Abstract: Data augmentation is described to train an artificial intelligence model that includes analyzing a first data set to measure an amount of data in the data set and the variation in the amount of data in the first data set to determine deficiencies for training an artificial intelligence model. Augmenting data is added for the first data set having an amount of data measured that fails to meet a threshold value. Deficiencies in the variation in the amount of data in the first data set are augmented using augmentation methods outside the variation scope of the first data set to provide a second data set of augmented data. An artificial intelligence model is trained with a combined data set of the first data set, and the second data set of augmented data when the first and second data set have an amount of data meeting the threshold value.

Abstract: A well log is scanned for one or more dimensions that describe one or more features of a well. Each dimension includes a plurality of values in a numerical format that represents each dimension. A missing value is detected in a first plurality of values of a first dimension of the well log. The first dimension of the well log is transformed, in response to the missing value, into a first image that visually depicts the first dimension including the first plurality of values and the missing value. Based on the first image and based on an image analysis algorithm a second image is created that visually depicts the first plurality of values and includes a found depiction visually depicting a found value in place of the missing value. The found depiction is converted, based on the second image, into a first value in the numerical format.