Abstract: In one embodiment, a method includes receiving touch inputs from a user corresponding to an activation trigger for an assistant system executing on a head-mounted device at the head-mounted device, accessing signals from inertial measurement unit (IMU) sensors of the head-mounted device by the head-mounted device, determining that the user is either donning or doffing the head-mounted device by an on-device don/doff detection model and based only on the signals from the IMU sensors, and overriding the activation trigger to prevent an activation of the assistant system responsive to the received touch inputs.

Abstract: In one embodiment, a method includes receiving, from a client system of a user, a user input comprising a plurality of n-grams, parsing the user input to identify one or more overall intents, hidden intents, and slots associated with the one or more n-grams, wherein at least one of the hidden intents is non-resolvable for being associated with partial slot information corresponding to an n-gram that has not been resolved to a particular entity identifier, wherein the partial slot information is associated with two more entity identifiers of two or more entities, respectively, sending, to the client system, instructions for prompting the user to select one of the entities to be associated with the non-resolvable hidden intent, resolving the non-resolvable hidden intent based on the entity identifier of the entity selected by the user, and generating a response to the user input based on the resolved hidden intent.

Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.

Abstract: A communication server facilitates a video call between client devices of a plurality of participants. During the video call, the communication server identifies an in-call activity to recommend to the plurality of participants in the video call based on user information. The in-call activity is selected to be relevant to each of the plurality of participants and jointly recommended to the plurality of participants of the video call. To identify the recommended in-call activity, the communication server may determine common interests among the plurality of participants and select an in-call activity that is associated with the common interests. After the recommended in-call activity is selected, an indication of the recommended in-call activity is provided to the client devices to enable the client devices to display a user interface including the in-call activity to the participants during the video call.

Abstract: An image processing system enables a user wearing a head-mounted display to experience a virtual environment combined with a representation of a real-world object. The image processing system receives a captured scene of a real-world environment that includes a target object. The image processing system identifies the target object in the captured scene and generates a representation of the target object. In some cases, the image processing system may include a graphical overlay with the representation of the target object. The image processing system can generate a combined scene that includes the target object and the virtual environment. The combined scene is presented to the user, thereby allowing the user to interact with the real-world target object (or a representation thereof) in combination with the virtual environment.

Abstract: Methods, systems, and storage media for facilitating collaboration on video media items are disclosed. Exemplary implementations may: receive, from a first user device, a video media item having core video content and an enhancement; store the received video media item on a server in an editable format; share the video media item, in the editable format, with a second user device; receive, from the second user device, a modification to the shared video media item to create a collaborative video media item; store the collaborative video media item on the server; and cause the collaborative video media item to be published in a non-editable format on a social media platform that supports display of user-created video media items.

Abstract: The disclosed systems and methods may include (1) identifying social media posts that have been posted to a social media platform by a creator account with fewer than a designated number of followers, (2) creating a social-engagement score for the creator account based on a measure of an amount of digital social engagement generated in response to the social media posts, (3) determining that the social-engagement score surpasses a threshold, (4) in response to (i) the creator account having fewer than the designated number of followers and (ii) the social-engagement score surpassing the threshold, designating the creator account as a prioritized creator account, and (5) presenting, in association with the creator account, a digital visual indicator indicating that the creator account is a prioritized creator account. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems and methods for screenless computerized social-media access may include (1) producing, via an audio speaker that is communicatively coupled to a computing device, a computer-generated verbal description of a social-media post provided via a social-media application, (2) detecting, via a microphone that is communicatively coupled to the computing device, an audible response to the social-media post from a user of the computing device, and (3) digitally responding to the social-media post in accordance with the detected audible response. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Techniques for enabling users logged-out of a social networking system to access content associated with the social networking system are described. For example, based at least in part on determining a user is unassociated with a social networking system, the social networking system may present content to the user. In some examples, the amount of content available to the user may be limited, in which the user may be prompted to create an account. In some examples, logged-out users may be prompted to pick topics associated with their interests, allowing the social networking system to curate content for logged-out users.

Abstract: The disclosed system may include (1) a drive subsystem that translates along a powerline conductor, (2) a rotation subsystem that rotates a segment of fiber optic cable about the powerline conductor while the drive subsystem translates along the powerline conductor such that the segment of fiber optic cable is wrapped helically about the powerline conductor, and (3) an extension subsystem that (a) mechanically couples the rotation subsystem to the drive subsystem, and (b) selectively extends the rotation subsystem away from the drive subsystem and the powerline conductor to avoid obstacles along the powerline conductor. Various other systems and methods are also disclosed.

Abstract: Techniques for context sensitive overlays, comprising a social networking application. The social networking application may include, among other components, a social networking overlay management component to receive a request from a mobile device to determine a list of aggregate overlay information and user context information, and providing the list of aggregate overlay information and user context information to the mobile device, a context determination component to determine the user context information representative of at least one user context based at least partially on user profile information, location information, calendar event information, and/or external event information, and an overlay selection component to generate the list of aggregate overlay information based at least partially on the user profile information, overlay promotion information, and user context information.

Abstract: In one embodiment, a method includes receiving a user's utterance comprising a word in a custom vocabulary list of the user, generating a previous token to represent a previous audio portion of the utterance, and generating a current token to represent a current audio portion of the utterance by generating a bias embedding by using the previous token to query a trie of wordpieces representing the custom vocabulary list, generating first probabilities of respective first candidate tokens likely uttered in the current audio portion based on the bias embedding and the current audio portion, generating second probabilities of respective second candidate tokens likely uttered after the previous token based on the previous token and the bias embedding, and generating the current token to represent the current audio portion of the utterance based on the first probabilities of the first candidate tokens and the second probabilities of the second candidate tokens.

Abstract: Techniques to optimize memory reads when computing a video quality metric are disclosed. In some embodiments, an application-specific integrated circuit for computing video quality metrics includes a set of caches configured to store neighbor pixel data for edge width searches of pixels comprising a frame of a video being analyzed for a video quality metric and a kernel configured to receive corresponding neighbor pixel data for pixels comprising a current processing block of the frame from a subset of the set of caches and simultaneously perform edge width searches for pixels comprising the current processing block to determine corresponding pixel edge width values used for computing the video quality metric.

Abstract: In one embodiment, a method includes accessing a stream of F video frames, where each of the F video frames includes N patches that are non-overlapping, generating an initial embedding vector for each of the N×F patches in the F video frames, generating a classification embedding by processing the generated N×F initial embedding vectors using a self-attention-based machine-learning model that computes a temporal attention and a spatial attention for each of the N×F patches, and determining a class of the stream of video frames based on the generated classification embedding.

Abstract: Various embodiments set forth optical patterning systems. Each pixel of the optical patterning systems includes an amplitude-modulating cell that is in line with a phase-modulating cell. The amplitude-modulating cell includes a liquid crystal and a drive method for modulating at least the amplitude of a wavefront of light that passes through the amplitude-modulating cell. The phase-modulating cell includes a liquid crystal and a drive method for modulating at least the phase of a wavefront of light that passes through the phase-modulating cell. In some embodiments, the amplitude-modulating cell shares a common ground with the phase-modulating cell. The amplitude-modulating cell and the phase-modulating cell can be used to independently control the amplitude change and phase delay imparted by the pixel, enabling complex wavefront modulation.

Abstract: A disclosed system may include a disaggregated artificial intelligence (AI) operation accelerator including a dense AI operation accelerator configured to accelerate dense AI operations and a sparse AI operation accelerator, physically separate from the dense AI operation accelerator, configured to accelerate sparse AI operations. The system may also include a scheduler that includes (1) a receiving module that receives an AI operation, (2) an identifying module that identifies the AI operation as a dense AI operation or sparse AI operation, and (3) a directing module that directs (a) the dense AI operation accelerator to accelerate identified dense AI operations, and (b) the sparse AI operation accelerator to accelerate identified sparse AI operations. The system may also include a physical processor that executes the receiving module, the identifying module, and the directing module. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems, apparatuses and methods provide technology that identifies a plurality of data samples of a data set. In response to a trigger, the technology identifies a first subset of samples of the plurality of data samples that are outside a range associated with a decision boundary of a machine learning model, and removes the first subset of samples from the data set to generate a modified training set. The technology train the machine learning model based on the modified training set.

Abstract: Systems and methods are provided for operating an artificial reality device using gestures. In various exemplary embodiments, an artificial reality device may receive information initiating a gesture recognition mode via the artificial reality device, and cause a camera associated with the artificial reality device to operate in the gesture recognition mode. The artificial reality device may further receive at least one image of a gesture captured by the camera and identify and evaluate the gesture. The gesture may be indicative of a user command. The artificial reality device may also execute the user command, and may generate feedback confirming execution of the user command.