Abstract: Methods and systems for non-destructive, stabilization-based encoder optimization. A video item to be provided to one or more users of a platform is identified. An indication of a motion is identified between an initial video frame of a video sequence associated with the video item and a subsequent video frame of the video sequence. One or more motion stabilization transformations are applied to the video item to modify the motion between at least the initial frame and the subsequent frame. Upon applying the one or more motion stabilization transformations to the video item, the video item is encoded. The encoded video item and one or more instructions to cause the client device to reverse the one or more motion stabilization transformations applied to the video item after decoding the encoded video item are transmitted to a client device connected to the platform.

Abstract: A method for providing autofill suggestions in a development environment includes obtaining, from a user interface executing on a user device, a user input representing source code generated within a development environment. The source code created using a particular programming language and a programming code base. The method further includes determining, using a machine learning model, at least one autofill suggestion based on the user input, the autofill suggestion continuing the source code represented by the user input. The method further includes determining, using a rule-based semantic checker configured for the particular programming language, whether the autofill suggestion is semantically correct based on the development environment and the programming code base. The method also includes, when the autofill suggestion is semantically correct, transmitting the autofill suggestion for display on the user interface of the user device.

Abstract: The disclosure provides technology for enhancing the ability of a computing device to detect when a user has discontinued reading a text source. An example method includes receiving audio data comprising a spoken word associated with a text source, wherein the audio data comprises a first duration and a second duration; comparing the audio data with data of the text source, wherein the first duration of the audio data corresponds with the data of the text source; calculating, by a processing device, a correspondence measure between the second duration of the audio data and the data of the text source; and responsive to determining the correspondence measure satisfies a threshold, transmitting a signal to cease comparing audio data with the data of the text source.

Abstract: A method of detecting a cough in an audio stream includes a step of performing one or more pre-processing steps on the audio stream to generate an input audio sequence comprising a plurality of time-separated audio segments. An embedding is generated by a self-supervised triplet loss embedding model for each of the segments of the input audio sequence using an audio feature set, the embedding model having been trained to learn the audio feature set in a self-supervised triplet loss manner from a plurality of speech audio clips from a speech dataset. The embedding for each of the segments is provided to a model performing cough detection inference. This model generates a probability that each of the segments of the input audio sequence includes a cough episode. The method includes generating cough metrics for each of the cough episodes detected in the input audio sequence.

Abstract: This disclosure relates to generating telecommunication network measurements. In one aspect, a method includes presenting, by a client device, a digital component that, when interacted with, initiates a call by the client device to a phone number specified by the digital component. A trusted program stores, in a presentation event data structure, a presentation event data element specifying the phone number and resource locator for a reporting system to which reports for the digital component are sent. The trusted program detects a phone call by the client device to a given phone number. The given phone number is compared to one or more presentation event data elements stored in the presentation event data structure. A determination is made that the given phone number matches the phone number specified by the digital component. In response, an event report is transmitted to the reporting system.

Abstract: Methods, systems, and media for presenting offset content are provided.

Abstract: A system is described that obtains first performance data collected during execution of a first application at a first group of computing devices, determines, based on the first performance data, at least one metric for quantifying performance of the first application, and compares the at least one metric to a corresponding benchmark derived from second performance data collected during execution of one or more second applications at a second group of computing devices. Each of the one or more second applications being different than the first application. The system determines whether the at least one metric is within a threshold amount of the corresponding benchmark, and further determines, determines, based at least in part on the at least one metric is not within the threshold amount of the corresponding benchmark, a fix to the first application and outputs, for presentation at a developer device, an indication of the fix.

Abstract: In one general aspect, a method can include displaying, on a display device included in a computing device, content in an application executing on the computing device. The method can further include displaying, in a user interface on the display device, at least one identifier, receiving a selection of the at least one identifier, and initiating casting in response to receiving the selection of the at least one identifier.

Abstract: A method for shuffle-less reclustering of clustered tables includes receiving a first and second group of clustered data blocks sorted by a clustering key value. A range of clustering key values of one or more the data blocks in the second group overlaps with the range of clustering key values of a data block in the first group. The method also includes generating split points for partitioning the first and second groups of clustered data blocks into a third group. The method also includes partitioning using the split points, the first and second groups into the third group. Each data block in the third group includes a range of clustering key values that do not overlap with any other data block in the third group. Each split point defines an upper limit or lower limit for the range of clustering key values a data block in the third group.

Abstract: Methods, systems, and media for adaptive presentation of a video content item based on an area of interest are provided.

Abstract: A method of providing user access history for a collaborative document includes receiving, by a server, a first request for the collaborative document from a client device of a user of a plurality of users that have permission to access the collaborative document; providing the collaborative document to the client device for presentation to the user in a user interface on the client device; determining whether a collaborator type of the user matches a predefined collaborator type; responsive to determining that the collaborator type of the user matches the predefined collaborator type: creating a first user access history for the collaborative document based on accesses of the collaborative document by one or more of the plurality of users, and providing the first user access history for the collaborative document to the client device for display within a consolidated view of the user interface presenting the collaborative document.

Abstract: A method includes generating a utility portal interface in response to a request from a utility computer system that receives parameters that specify a demand response event; providing a display of groups of energy-consuming locations that are available to be selected to participate in the demand response event; providing a display of an energy demand profile for the utility during the demand response event; receiving a selection of a subset of the groups of energy-consuming locations to participate in the demand response event; causing the display of the energy demand profile for the utility during the demand response event to be dynamically updated as the subset of the groups of energy-consuming locations are selected or deselected by the utility computer system to participate; and sending transmissions to thermostats associated with the subset of the groups of energy-consuming locations to execute the demand response event.

Abstract: The present disclosure provides systems and methods for an interactive user interface that allows for one or more submissions of update information related to a point of interest to be reviewed. The system may receive the submission from a computing device. The system may analyze the submission to determine the type of content, such as the name, address, website, photo, etc. related to the point of interest. The type of content may be classified using a machine learning model. The model may compare the content of the submission to a model of the type of content to determine whether the submission is approved for publishing or whether additional information is needed. The system may transmit one or more notifications to the computing device. The notifications may include updates on the workflow status of the submission.

Abstract: This document describes methods, devices, systems, and means for a peer-to-peer Citizens Broadband Radio Service, CBRS, grant. A base station sends a CBRS spectrum request to a Spectrum Access System, SAS, receives a CBRS spectrum grant from the SAS, and transmits a configuration for peer-to-peer, P2P, CBRS communication to at least a first UE that is effective to enable the first UE and a second UE to conduct P2P communication based on the configuration for P2P CBRS communication.

Abstract: An electronic device monitors audible output for media content being presented in its vicinity. It detects a volume change event within the monitored audible output. It obtains identification of the media content. Based on the identification, the device obtains a list of expected volume change events within the media content. It determines whether the detected volume change event correlates with one of the expected volume change events. In accordance with a determination that there is no correlation, the device determines that the detected volume change event comprises a volume change event from a user of the device. It analyzes the detected volume change event to determine user interest in the presented media content. The determined level of interest is sent to a server system. The device receives from the server system one or more recommendations based on the determined level of interest, and presents to the user the recommendations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

Abstract: A system and method for performing large-scale data processing using a statistical programming language are disclosed. One or more high-level statistical operations may be received. The received high-level statistical operations may be dynamically translated into a graph of low-level data operations. The unnecessary operations may be removed and operations may be fused or chained together. Operations may then be grouped into distributed data processing operation. The low-level operations may then be run.

Abstract: A method includes detecting, with a passive infrared sensor (PIR), a level of infrared radiation in a field of view (FOV) of the PIR, generating a signal based on detected levels over a period of time, the signal having values that exhibit a change in the detected levels, extracting a local feature from a sample of the signal, wherein the local feature indicates a probability that a human in the FOV caused the change in the detected levels, extracting a global feature from the sample of the signal, wherein the global feature indicates a probability that an environmental radiation source caused the change in the detected levels, determining a score based on the local feature and the global feature, and determining that a human motion has been detected in the FOV based on the score.

Abstract: The present disclosure describes various aspects of adaptive sounding reference signal mapping that a user equipment (UE) implements to improve channel estimation. In aspects, a set of sounding reference signal (SRS) symbols are generated that include at least first and second SRS symbols. An offset for the second SRS symbol is determined based on a difference between a first radio chain and a second radio chain of the UE. The first and second SRS symbols are then mapped to an antenna port of the first radio chain. The UE transmits the first SRS symbol to a base station via the antenna port of the first radio chain and transmits the second SRS symbol to the base station via the antenna port of the first radio chain while the offset is applied to the first radio chain. By so doing, the UE may improve channel estimation for uplink and/or downlink communications.

Abstract: A method for recognizing persons in video streams includes obtaining a live video stream, detecting a first person in the live video stream, determining from analysis of the live video stream first information that identifies an attribute of the first person, determining based on at least some of the first information that the first person is not identifiable to the computing system, storing at least some of the first information, receiving a user classification of the first person as being a stranger, and deleting the stored first information.