Abstract: The disclosed computer-implemented method may include (i) receiving a video stream for encoding, (ii) determining that the video stream is associated with an application, (iii) analyzing the video stream to label one or more regions of a frame within the video stream with a semantic category, (iv) determining, based at least in part on the application with which the video stream is associated, a prioritization of the semantic category, and (v) allocating encoding resources to one or more portions of the frame that comprise at least a part of the one or more regions of the frame based at least in part on the prioritization of the semantic category. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Exemplary embodiments relate to improvements in the design of a messaging inbox. The inbox may display different units or “modules” for providing a user with quick access to different inbox functionalities. Content may be ranked and ordered within a module, and modules may be ranked and ordered with respect to each other. Inter-module ranking may be based on elements such as individual activity and the activity of the messaging service's user base, the value of the module to the messaging service, and offline models. Intra-module ranking may be defined by individual modules (e.g., based on recency, importance to user, affinity, etc.). Intra-module ranking may affect inter-module ranking, such as when individual content in a low-rated module is particularly exciting or pertinent (causing the entire module to receive a higher inter-module ranking).

Abstract: Systems and associated methods for reducing Doppler shifts in the broadband signals between Unmanned Aerial Vehicles (UAVs) and ground stations are disclosed herein. In one embodiment, a method for reducing the Doppler shift of wireless signals includes estimating a velocity of the UAV based on a Global Positioning System (GPS) or an Inertial Measurement Unit (IMU) of the UAV and calculating the Doppler shift of an upload (UL) wireless signal based on the velocity of the UAV. The method further includes predistorting a frequency of the UL wireless signal at the ground station to reduce the Doppler shift at a UAV receiver (RX) and transmitting the UL wireless signal from a ground station transmitter (TX) to the UAV RX. In some embodiments, calculating the Doppler shift of the UL wireless signal is performed at the ground station.

Abstract: The present disclosure is directed toward systems and methods for providing message element in electronic communication threads. For example, systems and methods described herein identify message elements in electronic communication threads and add interactions between the message elements to the electronic communication thread.

Abstract: The disclosed computer-implemented method may include (1) receiving, via a social networking system, a request from a user to participate in a discovery service designed to facilitate connections between users of the social networking system who share common attributes, (2) obtaining, from the user, data representative of at least one desired user attribute, possessed by the user, for new user connections, (3) identifying, within the social networking system, at least one additional user who is both a participant in the discovery service and who also possesses the desired user attribute, and (4) providing a visual indication to the user, when representing the additional user within a user interface of the social networking system, that the additional user is a participant in the discovery service and that the additional user possesses the desired user attribute. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a method includes accessing posts in a social-networking system. Each of the posts is unlabeled with respect to whether the post is known to be spam. The method also includes determining a posting user who submitted the post to the social-networking system and a recipient user to whom the post is addressed. The method further includes determining a first vector representation of the posting user and a second vector representation of the recipient user based on one or more features associated with the post, the posting user, and the recipient user. The method still further includes comparing the vector representations and building a machine learning model for automatically detecting spam posts in the social-networking system using a subset of the plurality of posts as non-spam training data.

Abstract: Exemplary embodiments relate to methods, mediums, and systems for moving language models from a server to the client device. Such embodiments may be deployed in an environment where the server is not able to provide modeling services to the clients, such as an end-to-end encrypted (E2EE) environment. Several different techniques are described to address issues of size and complexity reduction, model architecture optimization, model training, battery power reduction, and latency reduction.

Abstract: Techniques are described for generating content to be shared between users. For example, user interfaces are described that include features and/or mode controls for generating content to be shared between users. Additionally, the described techniques include determining content shared between users (e.g., previously distributed content) based on a selection of a second user account, and generating customized content which may be specific to an event that includes the shared content.

Abstract: The disclosed computer-implemented method may include receiving, at a server, a request from a client for live data. The method may include establishing, at the server, a data transfer promise that is embedded in a live data stream. The live data stream may include the requested live data. The method may further include transferring the live data stream with the embedded data transfer promise to the client, receiving an indication that the status of the embedded data transfer promise was changed during transmission of the live data stream and providing, to the client, an indication of the current status of the live stream based on the received status indication. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: One variation of a method for selectively advertising items in an image includes: loading an image to a social feed; receiving a first tag and a second tag including identification of a first item and a second item visible in the image, respectively; based on the first tag and the second tag, correlating the first item with a first product and the second item with the second product; based on the first product and the second product, sourcing a first link to a first electronic storefront and a second link to a second electronic storefront that facilitate purchase of the first product and the second product, respectively; and selectively displaying a first visual cue of the first link and a second visual cue of the second link to a first user and to a second user, respectively, according to demographics of the first user and the second user.

Abstract: Embodiments are disclosed for transliterating text entries across different script systems. A method according to some embodiments includes steps of: receiving an input string in a first script system input using a keyboard; segmenting, using a probabilistic model, the input string into phonemes that correspond to characters or sets of characters in a second script system; converting the phonemes in the first script system into the characters or sets of characters in the second script system, the characters or sets of characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: A system provides content describing an object, for example, a physical object or a customizable service. The system presents an interactive user interface displaying a customized version of a physical object. The interactive user interface allows the user to further customize the physical object. The user interface displays a plurality of options for customizing various components of the physical object. The system customizes the physical object presented via the interactive user interface based on the user profile and user interactions of the user with other users via an online system. The system allows the user to further customize the physical object via the interactive user interface. The interactive user interface presents various options for customization of the physical object based on predicted user preferences.

Abstract: The disclosure is directed to optimizing data writes in a distributed computing system, e.g., a social networking application. The system employs a write-ahead log (WAL) and a hybrid logical clock (HLC) together to improve data writes across data centers in the distributed computing system, including improving: (1) consensus monitoring and enforcement in replicating data across the data centers; (2) scalability of data writes, e.g., so that different data centers can together handle a sudden increase in data writes during specified periods and consistently maintain the time ordering of the data writes; (3) replication configuration of data centers so that client devices can specify a replication hierarchy per transaction, e.g., at the time of writing the data, rather than specifying at data center configuration time; and (4) a draining process to write transactions committed to the WAL to data storage systems in the data centers.

Abstract: Apparatuses, methods, and systems for distributing resource block between interfering cells, are disclosed. One method includes allocating resource blocks to a plurality of macro-cells and a plurality of sectors of a supercell, wherein the supercell includes a wireless communication cell that provides wireless coverage to a larger region than the plurality of macro-cells and includes the plurality of sectors, wherein each of the macro-cells provide wireless coverage that at least partially overlaps with a region of wireless coverage of the supercell, wherein the supercell includes one or more supercell sector coverage areas that are interfered by at least one macro-cell. The allocating the resource blocks includes determining which of the plurality of macro-cells wirelessly interfere with which of the plurality of sectors, and determining, for each interfered sector, a total unmet demand of the interfered sector and interfering macro-cells for a coverage area of the interfered sector.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating accurate digital media clusters corresponding to predicted distribution classes from a repository of digital media based on network distribution history. For example, a digital media clustering system can apply machine learning models at a remote server (based on network distribution history of a network account of a user) to generate predicted distribution classes for future electronic communications. The remote server can provide the predicted distribution classes to a user client device for secure local analysis of digital media stored at the client device. Based on the predicted distribution classes and the stored digital media, the client device can suggest digital media items to distribute via a networking system. Thus, the disclosed system can surface digital media content without providing any information regarding the digital media items stored at the client device to a remote server.

Abstract: Apparatuses, methods, and systems for assisted channel approximation wireless communication of a supercell base station are disclosed. One apparatus includes a wireless network, wherein the wireless network includes a supercell base station comprising a plurality of antennas, a plurality of user devices, wherein the plurality of user devices is located too far away to support omnidirectional electromagnetic communication with the supercell base station, and a separate communication device located proximate to the plurality of user devices. The separate communication device operates to receive omnidirectional wireless signals from the supercell base station, characterized a transmission channel between the supercell base station and the separate communication device, and directionally transmit the characterized channel back to the base station.

Abstract: In one embodiment, a method includes, by one or more computing devices of an online social network, receiving, from a client system of a first user of the online social network, an audio input from a second user, wherein the audio input comprises one or more voice commands, identifying the second user based on a comparison of the audio input to one or more voiceprints stored by the online social network, wherein each voiceprint comprises audio data for auditory identification of a unique user of the online social network, determining a relationship status between the first user and the identified second user within the online social network, and determining whether to perform an action associated with each voice command based on permission settings associated with the action and the determined relationship status between the first user and the identified second user.

Abstract: Techniques for a messaging agent platform are described. In one embodiment, an apparatus may comprise a intermediary server operative to send a page-scoped identifier to a front-end application, the front-end application associated with an entity, the page-scoped identifier identifying a user account with a messaging system in relation to a representation for the entity within the messaging system; receive a user information request from a contact application at the intermediary server, the contact application associated with the representation for the entity within the messaging system, the user information request for the page-scoped identifier; determine a user access consent setting for the page-scoped identifier for the user account; and send a user information data package to the contact application in response to the user information request when the user access consent setting for the page-scoped identifier indicates user consent. Other embodiments are described and claimed.