Abstract: Systems, methods, and non-transitory computer-readable media can identify a set of media content items based on at least one search query. The set of media content items can be ranked based on information associated with one or more media content items in the set of media content items to produce a ranked set of media content items. The ranked set of media content items can be provided for sequential video presentation. A set of image frame previews can be selected for at least some media content items in the ranked set. Each image frame preview in the set of image frame previews can be selected based on a respective confidence score associated with viewer interest. One or more image frame previews, out of the set of image frame previews, can be provided during media navigation associated with the sequential video presentation.

Abstract: In one embodiment, a method includes receiving a plurality of input frames of a video sequence associated with a time t, predicting, using a convolutional network, one or more future frames of the video sequence from the plurality of input frames, wherein the convolutional network is trained with randomly selected temporal sequences of a n×m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow. In addition, the training may comprise randomly selecting temporal sequences of a n×m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow.

Abstract: In one embodiment, a computing system is configured to track objects in an environment or localize a user device. For example, the system accesses an image of an environment captured from a viewpoint. Based on the image, the system detects landmarks that are associated with objects in the environment and identifies expected landmarks that are expected to be observable from the viewpoint using a landmark database. The system determines that at least one of the expected landmarks is currently unobservable in the environment by comparing the expected landmarks with the detected landmarks. By accessing semantic information associated with the at least one expected landmark, the system updates the landmark database based on a determination that the semantic information satisfies predetermined criteria and removes the at least one expected landmark from the landmark database. The system performs object tracking, object mapping, or re-localization within the environment using the updated landmark database.

Abstract: A computer-implemented method for updating pixel arrays may include (i) displaying an image on an array of pixels via a set of pixel control modules, where each pixel within the array of pixels is communicatively coupled to a different pixel control module within the set of pixel control modules, (ii) receiving an instruction to update the image displayed on the array of pixels to a new image, (iii) identifying a pixel within the array of pixels that is in a different state in the new image than in the image, and (iv) updating the pixel to the different state by transmitting a signal from the pixel control module directly to the pixel that updates the pixel independently of additional pixels. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An online system predicts the user's activity on the online system during a future time interval (e.g., the next day). The system collects activity data, such as actions that the user has taken on the system. The system predicts whether the user is likely to be active during the future time interval based on features extracted from the activity data. This system determines selection of notifications and delivery of notifications based on the predicted time when the user is likely to be active on the online system. The system further records the user's past interactions with notifications, such as whether the user viewed the notification, whether the user interacted with a content item associated with the notification, and so on. If system determines a rate of delivery of notifications to the user based on the frequency of past user interactions with notifications.

Abstract: Embodiments relate to a stacked photo sensor assembly where two substrates that are stacked vertically. The two substrates are connected via interconnects at a pixel level to provide a signal from a photodiode at a first substrate to circuitry on a second substrate. The circuitry on the second substrate performs operations that were conventionally performed on first substrate. By stacking the first and second substrates, the photo sensor assembly can be made more compact while increasing or at least retaining the photodiode fill factor of the photo sensor assembly.

Abstract: Systems, methods, and non-transitory computer-readable media can determine at least one media content item being posted through a social networking system, wherein the media content item is able to be shared through one or more non-ephemeral content feeds, an ephemeral story feed, or with a favorites list of users; determine that the media content item is being shared with the favorites list of users; determine users included in the favorites list; and distribute the media content item to users included in the favorites list.

Abstract: Systems and methods for automatically locating web-based social network members are provided. According to one embodiment, contact content including an associated GPS identifier and status for web-based social network members located at or near the same location automatically appears on a GPS-enabled device. A further exemplary system includes a GPS-enabled device configured to receive a GPS identifier and a status representing a location and a current state for a web-based social network member, a processing module that associates the received GPS-identifier and the received status, and a communications module that sends the associated GPS-identifier and status to a server comprising a web-based social network database. Contact content in a web-based social network database record in the web-based social network database is updated to include the associated GPS identifier and status for the web-based social network member.

Abstract: The automatic transmission of communications between a mobile device and a social networking system is regulated based on the communication mode of the mobile device. A communication for transmission between the mobile device and the social networking system is detected. A communication switch setting, such as a switch position, is determined for the mobile device. A communication mode for the mobile device is determined based on the communication switch setting. For example, if the switch is in a first position, the mobile device is determined to be in a social mode. Likewise, if the switch is in a second position, the mobile device is determined to be a manual mode. If the mobile device is in the social mode, the communication is automatically transmitted. If the mobile device is in the manual mode, the communication is transmitted only in response to authorization from the user of the mobile device.

Abstract: Techniques for ephemeral message are described. In one embodiment, an apparatus may comprise a delayed-action worker module operative to wake according to a wake timer; determine a current update object for a delayed-action cursor for a recipient update queue for a messaging system, the delayed-action cursor associated with an action delay for the recipient update queue; determine a delayed-action activity for the current update object; perform the delay-action activity for the current update object; determine a next update object for the delayed-action cursor for the recipient update queue; and determine a next wake timer for the delayed-action worker module based on the action delay and a creation time for the next update object. Other embodiments are described and claimed.

Abstract: The disclosed computer-implemented method may include tracking (1) a position of a primary real-world object within a real-world environment via a primary tracking method, and (2) a position of a secondary real-world object within the real-world environment via a secondary tracking method. The method may further include presenting (1) a primary virtual object at a position within an artificial environment corresponding to the tracked position of the primary real-world object, and (2) a secondary virtual object at a position within the artificial environment corresponding to the tracked position of the secondary real-world object. The method may further include (1) detecting an interaction of the primary real-world object with the secondary real-world object, and (2) transitioning to tracking the position of the primary real-world object via the secondary tracking method. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a computer server running a social networking application aggregates raw local area network (LAN) traffic data received from one or more listening nodes in one or more LANs. The aggregated LAN traffic data is comprised of multiple entries, each of which includes a MAC address for a networked device, as well as an association between each MAC address and a user of a social networking system. The computer server may then detect, identify, and qualify recurring patterns when a particular user is on the same LAN as other users of the social networking system. Based upon the qualified patterns, the social networking system may suggest friend connections or other interactions on the social networking system to the particular user.

Abstract: In one embodiment, a method includes determining an ornamental pattern to be transferred to a substrate. The ornamental pattern is specific to a particular user, and one or more parameters of the ornamental pattern are based at least in part on social-graph information of the user. The method also includes generating one or more instructions for controlling a laser-treatment system to transfer the ornamental pattern to the substrate; sending the instructions to the laser-treatment system to transfer the ornamental pattern to the substrate; and transferring the ornamental pattern to the substrate.

Abstract: Systems, methods, and non-transitory computer-readable media can determine at least one request to access a content item, wherein the content item was composed using a set of camera feeds that capture at least one scene from a set of different positions. A viewport interface can be provided on a display screen of the computing device through which playback of the content item is presented, the viewport interface being configured to allow a user operating the computing device to virtually navigate the at least one scene by changing i) a direction of the viewport interface relative to the scene or ii) a zoom level of the viewport interface. A navigation indicator can be provided in the viewport interface, the navigation indicator being configured to visually indicate any changes to a respective direction and zoom level of the viewport interface during playback of the content item.

Abstract: An online system receives an image associated with a set of pixel values and provides the set of pixel values to a deep learning or machine-learned model that is trained to assign a set of regions of interest within the image to one or more classes. The model is structured to identify the set of regions of interest based on the pixel values, in which each region of interest is associated with an embedding corresponding to a vector representation of the region of interest. The online system compares each embedding to a database of embeddings associated with multiple labeled images, in which the labels indicate an identity of a brand and/or an obfuscated identity of the brand. The online system then determines whether the identity of the brand and/or the obfuscated identity of the brand is/are detected within each region of interest based on the comparison.

Abstract: A method for generating an individualized audio output response for a headset using a machine learning model. One or more images of a portion of a user's head including at least the user's ear are received. One or more features describing the user's ear are identified based on the one or more images. The features are input to a model, and the model is configured to determine an audio output response for the user based on the identified one or more features. The audio output response describes one or more acoustic parameters perceived by the user. An individualized audio output response is generated for the user based on the audio output response, the individualized audio output response configured to adjust one or more acoustic parameters of audio content provided to the user by the headset.

Abstract: An audio system presented herein includes a transducer array, a sensor array, and a controller. The transducer array presents audio content to a user. The controller controls the transducer array to adjust a level of tactile content imparted to the user via actuation of at least one transducer in the transducer array while presenting the audio content to the user. The audio system can be part of a headset.

Abstract: An electronic device with a display selects a subset of templates from a library of templates. Each of the templates comprises logged movements of one or more predefined input device types in a 3D space and each template includes one or more movement parameters. The electronic device tracks, for a user, movement parameters of at least one input device of the user. The at least one input device corresponds to one of the predefined input device types. The electronic device compares the tracked movement parameters of the at least one input device of the user to the movement parameters for the subset of the templates selected from the library of templates. The electronic device predicts, based on the comparison, a goal target ray, within the 3D space. In some embodiments, the goal target ray is highlighted or visually emphasized according to the prediction.

Abstract: An online system customizes content items using navigation information of users and geographical catchment areas. In an embodiments, the online system receives first sensor data indicating that a client device of a user is at a first geographical area and second sensor data indicating that the client device is at a second geographical area. The online system identifies an electronic display located at point of interest within the second geographical area and transmits navigation information to the electronic display for presentation, where the navigation information is generated based on the sensor data. The online system receives a request, from the electronic display, to provide a content item to a client device and transmits the content item to the client device.