Abstract: In one embodiment, a method includes receiving a source image and its associated parameters from each of multiple image sources, associating each of the source images with a layer in a range of layers based on the parameters associated with the source images, the range of layers specifying a composition layering order of the source images, generating a corresponding customized distortion mesh for each particular source image in the source images based on the parameters associated with the particular source image and at least a portion of the parameters associated with each of the source images that is associated with any layer preceding a layer associated with the particular source image, modifying each of the source images using the corresponding customized distortion mesh, generate a composite image using the modified source images, and display the composite image as a frame in a video.

Abstract: Machine-learning-aided automatic taxonomy for web data. In an embodiment, a training dataset of annotated features is used to train a model to predict a class in a taxonomy of web-based activities. The features may be derived from a uniform resource locator (URL) of an online resource and associated metadata. During operation, the features may be extracted from the URL and metadata of each activity record in web data. The trained model may be applied to the extracted features for each activity record to predict a class within the taxonomy. The predicted taxonomic class may be stored in association with the URL that was extracted from the activity record to produce a taxonomized URL.

Abstract: In one aspect, an example methodology implementing the disclosed techniques includes, responsive to a determination, by a computing device, of a scheduling of an online conference between a plurality of conference participants, the online conference including food service, determining a food service application that is appropriate for at least one conference participant in the online conference. The method also includes sending to the at least one conference participant a notification regarding the scheduling of the online conference that includes food service, wherein the notification includes a link to the food service application. The method may also include, responsive to a receipt of a bill for a food order placed with the food service application by the at least one conference participant, collecting an amount from a conference organizer to pay for the food order and making an appropriate payment to the food service application to pay for the food order.

Abstract: A system and a method for assigning a student to a cohort in real time on a platform. The system receives a set of information from a student for enrolling the student on the platform. Further, the system receives a question from the student. Furthermore, the system extracts a plurality of parameters from the question based on a machine learning model. Subsequently, the system creates a student profile based on the plurality of parameters and the set of information. Further, the system determines a difficulty level of the question using deep learning algorithms. Furthermore, the system computes a similarity score of the student on the platform in real time. Finally, the system automatically assigns the student to a cohort on the platform. The cohort is a subset of the students on the platform.

Abstract: Examples described herein include systems and methods for providing user-specific previews for terms within text. An example method can include receiving tracked user behavior reflecting terms selected by a user and entered into a search. A representation of known words can be created based on the tracked user behavior. By training machine-learning models for each individual user, personalized previews can be presented when each user encounters a new body of text, such as in a webpage or email. The preview can apply to a term not previously known to the user but likely to be searched by the user, relying on content gathered from a search on a search medium that the user was likely to use. The content can be presented to the user in a graphical user interface allowing for interaction and feedback.

Abstract: This disclosure relates to methods and devices for a user equipment device (UE) to perform band measurements and provide a pruned measurement report to a base station. A first connection is established between the UE and a base station, and a configuration message is received from the base station. The configuration message identifies a plurality of bands for which the UE is to provide measurement reporting. The UE determines whether a band combination of the plurality of bands has an aggregate bandwidth that is greater than the aggregate bandwidth of the first connection and whether a signal quality metric of the determined band combination is greater than a predetermined threshold. Responsive to these determinations, the UE performs band measurements on the bands of the band combination and transmits a pruned measurement report to the base station.

Abstract: A system and a method for adjusting brightness of a content are provided.

Abstract: Responsive to a user instruction or a security breach occurring in an enterprise computing environment, an emergency shutdown and restore module is adapted to obtain and evaluate an identity population definition to determine a population of identities (e.g., a forensic team) associated with accounts distributed across applications in the enterprise computing environment. The emergency shutdown and restore module is further adapted to determine source systems of such accounts and communicate with those source systems via source-specific connectors. The emergency shutdown and restore module can respectively request the source systems to shut down access to the applications by the accounts associated with the population of identities, or to exclude the accounts associated with the population of identities in shutting down access to the applications.

Abstract: Machine-learning-aided automatic taxonomy for marketing automation and customer relationship management. In an embodiment, a plurality of machine-learning models are trained to classify activity records into action, channel, and type classes, using a training dataset of annotated features. During operation, relevant features may be extracted from each activity record, and each model may be applied to a respective set of those features to classify the activity record into an action class, channel class, and type class. These classes may then be stored in association with the activity record as a taxonomized activity record.

Abstract: A glitch detector includes a metastability detector circuit, a reference storage circuit, and a pattern comparison circuit. The metastability detector circuit is configured to generate state signals at each cycle of the clock signal. The reference storage circuit is configured to store a logic state of each state signal based on a delayed version of the clock signal, and generate reference signals. A logic state of each reference signal is equal to a logic state of a corresponding state signal generated during a previous cycle of the clock signal. The pattern comparison circuit is configured to receive the state signals generated during a current cycle of the clock signal, the reference signals, and first and second values, and generate clock and voltage glitch signals based on first and second patterns that are associated with the state signals generated during the current cycle and the reference signals, respectively.

Abstract: System, methods, and other embodiments described herein relate to reducing audible distractions for a driver of a vehicle. In one embodiment, a method includes obtaining audio data based on sound detected inside the vehicle, identifying an audio event based on the audio data, determining a distraction rating for the audio event, the distraction rating indicating an estimated level of distraction caused by the audio event, and generating an alert when the distraction rating exceeds a threshold.

Abstract: A primary container assembly includes a primary container defining a body having a proximal end defining an opening configured to receive a plunger, a distal end opposite the proximal end and defining an outlet, and a chamber extending from the proximal end to the distal end that is configured to receive a drug. The primary container assembly further comprises a tube extending from a first end that is integrally attached to the distal end of the primary container to a second end opposite the first end, where the tube defines a channel extending from the first end to the second end. The primary container assembly also includes a hollow needle configured to penetrate skin of a patient.

Abstract: In various examples, a two-dimensional (2D) and three-dimensional (3D) deep neural network (DNN) is implemented to fuse 2D and 3D object detection results for classifying objects. For example, regions of interest (ROIs) and/or bounding shapes corresponding thereto may be determined using one or more region proposal networks (RPNs)—such as an image-based RPN and/or a depth-based RPN. Each ROI may be extended into a frustum in 3D world-space, and a point cloud may be filtered to include only points from within the frustum. The remaining points may be voxelated to generate a volume in 3D world space, and the volume may be applied to a 3D DNN to generate one or more vectors. The one or more vectors, in addition to one or more additional vectors generated using a 2D DNN processing image data, may be applied to a classifier network to generate a classification for an object.

Abstract: This disclosure relates to techniques for determining a radio access technology to prioritize when obtaining cellular service in a wireless communication system. A wireless device may determine whether to deprioritize obtaining cellular service using a radio access technology. Whether to deprioritize obtaining cellular service using the RAT may be determined based at least in part on one or more cellular network characteristics. The wireless device may establish a wireless link with a cellular base station. The wireless link may be established with the cellular base station based at least in part on the determination of whether to deprioritize obtaining cellular service using the radio access technology.

Abstract: A system for remote editing of a file includes a database including a plurality of source media content files and a content host configured to generate a first proxy for at least a portion of a first one of the source media content files, the first proxy including data sufficient to enable a remote user device to identify a portion of content of the first source media content file to be included in a generated clip, the content host configured to receive from the remote user device a request to create the generated clip from the first source media content file, the request indicating parameters defining, based on the data in the first proxy, the portion of the first source media content file to be included in the generated clip, the content host configured to create the generated clip based on the parameters indicated in the request.

Abstract: This disclosure relates to methods and devices for a user equipment device (UE) to perform band measurements and provide a pruned measurement report to a base station. A first connection is established between the UE and a base station, and a configuration message is received from the base station. The configuration message identifies a plurality of bands for which the UE is to provide measurement reporting. The UE determines whether a band combination of the plurality of bands has an aggregate bandwidth that is greater than the aggregate bandwidth of the first connection and whether a signal quality metric of the determined band combination is greater than a predetermined threshold. Responsive to these determinations, the UE performs band measurements on the bands of the band combination and transmits a pruned measurement report to the base station.

Abstract: Systems and methods provide an intelligent vehicle to everything (iV2X) service that ensures robust communication of teleoperations and other data. An edge slice proxy system is used to incorporate edge platforms into network slicing considerations. A network device may receive a request for a connection from an end device, such as a vehicle requiring the iV2X service, via wireless signals. The network device may detect that the request is a request for an iV2X service and assign the end device to a network slice that supports stateful and robust iV2X services. The network slice may include one of the virtual network functions executed on the edge platform.

Abstract: In some implementations, a system may obtain a first model that is trained to identify feature data associated with a client system using one or more services of a service platform. The system may train, based on the feature data, a second model to identify anomalies associated with devices accessing the one or more services in association with a client identifier of the client system. The system may receive access data associated with an acting device accessing a service of the service platform. The system may determine, using the second model, that the acting device accessing the service corresponds to potential anomalous activity based on the access information. The system may obtain, from a verification device, a verification that the acting device accessing the service is anomalous activity. The system may perform, based on obtaining the verification, an action associated with the acting device.

Abstract: A method for ranking messages of conversation graphs in a messaging platform includes classifying messages of a conversation graph into a plurality of sections based on content quality of the messages, where the plurality of sections include a first section and a second section. The first section has messages from the conversation graph determined as higher quality than messages of the second section. The method includes determining a plurality of predictive outcomes for each of a plurality of messages of the conversation graph using predictive models, ranking the messages of the first section based on the predictive outcomes for the messages of the first section, and transmitting at least a subset of the messages of the first section to be rendered on a client application according to the rank.

Abstract: Systems and processes are disclosed for controlling television user interactions using a virtual assistant. In an example process, a virtual assistant can interact with a television set-top box to control content shown on a television display. Speech input for the virtual assistant can be received from a device with a microphone. The speech input can comprise a query associated with content shown on the television display. A user intent of the query can be determined based on one or more of the content shown on the television display and a viewing history of media content. A result of the query can be caused to be displayed based on the determined user intent.