Abstract: Methods and systems are described for imaging and content generation. During a road trip, a driver or passenger observes an object or scene from a vehicle. From a perspective of the driver or passenger, the object or scene flows out of view in a relatively short amount of time. Images and video of the object or scene are captured with cameras. A field of view is extended beyond what the driver or passenger can easily observe. The capture is configurable to focus on particular types of objects or scenes. Recordings of billboards and road signs are easily displayed after passing the object. Object identification, gaze determination, and interest determination are provided. Curated content is generated. Applications to extended reality environments are provided. Artificial intelligence systems, including neural networks, and models are utilized to improve the imaging and content generation. Related apparatuses, devices, techniques, and articles are also described.

Abstract: Methods and systems are described for imaging and content generation. During a road trip, a driver or passenger observes an object or scene from a vehicle. From a perspective of the driver or passenger, the object or scene flows out of view in a relatively short amount of time. Images and video of the object or scene are captured with cameras. A field of view is extended beyond what the driver or passenger can easily observe. The capture is configurable to focus on particular types of objects or scenes. Recordings of billboards and road signs are easily displayed after passing the object. Object identification, gaze determination, and interest determination are provided. Curated content is generated. Applications to extended reality environments are provided. Artificial intelligence systems, including neural networks, and models are utilized to improve the imaging and content generation. Related apparatuses, devices, techniques, and articles are also described.

Abstract: System and method are provided for sharing a counterpart version of a media asset. A media application generates for display a first media asset on a first device associated with a first user profile. The media application determines that a second device associated with a second user profile is generating for display a second media asset and the second user profile is designated to share a counterpart version of media consumed in association with the second user profile with the first device. The media application identifies a time to share a counterpart version of the second media asset. At the identified time, the media application generates for display an overlay over the display of the first media asset on the first device. The overlay comprises the counterpart version of the second media asset and a plurality of user interface options.

Abstract: Systems and methods are described for inputting text input to a trained machine learning model; generating, using the trained machine learning model and based on the text input, a single-layer image comprising a plurality of objects; segmenting the single-layer image to generate a plurality of images, each image of the plurality of images comprising a depiction of a respective object of the plurality of objects of the single-layer image; extracting, from the text input, a portion of the text input describing a background portion of the single-layer image; generating, using the trained machine learning model and based on the extracted portion of the text input, a background image; and generating the multi-layer image based on the plurality of images and the background image.

Abstract: Systems and methods are described for generating, using the first trained machine learning model and based on text input, a single-layer image comprising a plurality of objects; generating a plurality of masks associated with the plurality of objects; determining a plurality of attributes associated with the plurality of objects; generating, using a second trained machine learning model, a plurality of textual descriptions respectively corresponding to the plurality of objects; inputting the plurality of textual descriptions, and the plurality of attributes, to the first trained machine learning model; generating, using the first trained machine learning model, a plurality of images respectively corresponding to the plurality of textual descriptions; and generating the multi-layer image by combining the plurality of images and by using the plurality of masks, wherein the plurality of images respectively correspond to a plurality of layers of the multi-layer image.

Abstract: A vocabulary level of a user in a language to be learned is identified. During playback of a media asset on a first device, subtitles in the language are extracted for at least a portion of the media asset. The extracted subtitles may contain a single word, or a plurality of words in the language in question. Based on the vocabulary level, a subset of words from the extracted subtitles are predicted to be new to the user. The predicted new words are then generated for display on a second device associated with the user, along with an explanation of each word of the subset of words.

Abstract: A method and device for enhancing speech audio signals of an individual in a noisy environment based on a user's gaze and a captured image of the user's environment. A direction of a user's gaze is determined using image sensors configured to capture an orientation of a user's eyes and an image of the user environment is captures. Spatial audio is captured and analyzed along with the direction of gaze and image of the user environment to enhance audio of an active speaker.

Abstract: Embodiments herein provide control of an AR media asset generated on a display of an AR device. The AR media asset is displayed as part of a 3D environment and at a first depth in the 3D environment. A gaze of a user of the AR device is determined to be focused at a second depth in the 3D environment. The second depth is deeper than the first depth. In response to determining the gaze of the user is focused at the second depth, the AR media asset is repositioned to a third depth in the 3D environment. The third depth is deeper than the second depth. The AR media asset is automatically moved to allow the user to focus at the second depth, which allows the user to pay attention to the physical surroundings and consume the AR media asset while on-the-go.

Abstract: Systems and methods are provided herein for detecting and measuring characteristics of a ball during a sporting event, and further for presenting the detected characteristics. For example, the disclosed system uses a camera to detect the location of an object (e.g., a ball used in a sporting event) and, based on the determined location, emits a laser beam at the object. The emitted laser beam scatters off the object and creates a speckle pattern detectable in the same direction as the emitted laser beam. The speckle pattern is detected, for example, using a photodetector. The photodetector captures the speckle pattern caused by the emitted laser beam interacting with the object's surface. The system analyzes the detected speckle pattern over time to determine characteristics of the object. The system may optionally display the characteristics of the object using one or more visualizations.

Abstract: Systems, methods and apparatuses are described herein for receiving user input via a user interface; determining, based on the received user input, a particular portion of interest corresponding to a location at a live event; identifying one or more microphones in a vicinity of the location corresponding to the particular portion of interest at the live event; and causing audio detected by the one or more microphones to be generated for output.

Abstract: Systems and methods are provided for identifying devices via a directional signal. A first directional signal having a first solid angle is emitted from a first device during a first time period, and a second directional signal having a second solid angle is emitted from the first device during a second time period. A second device that has received the first signal emitted during the first time period and has received the second signal emitted during the second time period is identified. A third device that has not received the first signal emitted during the first time period and has received the second signal emitted during the second time period is identified. A user interface element based on the identifying the second device and the identifying the third device is generated, for output at the first device.

Abstract: Systems and methods for enabling route determination to maximize an operator's intent are described. In an example, a method includes receiving an input via a user interface, the input comprising a destination. The method also includes determining a primary goal and a secondary goal, wherein the primary goal comprises identifying a traversable route from a starting location to the destination, determining a plurality of waypoints based on the secondary goal, and determining a plurality of candidate routes based on the starting location and the destination. The method then includes identifying, from among the plurality of candidate routes, based on a number of waypoints of the plurality of waypoints positioned along each respective route of the plurality of candidate routes, a target route, and generating for navigation by a vehicle, the target route.

Abstract: Disclosed is a method comprising receiving a request to view a content item comprising a first character having a first character representation, accessing permissions regarding replacement of the first character representation, determining whether the permissions allow replacement of the first character representation, in response to the determining, generating for display an option to replace the first character representation in the content item, receiving a request to replace in the content item the first character representation via selection of the displayed option, obtaining a representation of a source individual, and generating for display a modified version of the content, wherein the first character representation is replaced with the representation of the source individual in at least a portion of the content item.

Abstract: Systems and methods are provided herein for generating personalized audio settings for different users listening to the same piece of media content. For example, the system may receive a first audio setting for a first user corresponding to a first volume level for a first frequency and a second audio setting for a second user corresponding to a second volume level for the first frequency. The system may then use the first audio setting, second audio setting, position of the first user, and position of the second user to calculate a weight for each speaker of a plurality of speakers. Each speaker of the plurality of speakers then outputs the first frequency at the respective calculated weight, resulting in the first user perceiving the first frequency at the first volume level and the second user perceiving the first frequency at the second volume level.

Abstract: Systems and methods are described for generating subtitles. Utterance data is received. First subtitles are generated for the utterance data. A first term is identified in the first subtitles. Contextual data relating to the utterance data is determined. A replacement term for the first term is determined based on the contextual data. Second subtitles are generated for the utterance data. The second subtitles comprise the replacement term.

Abstract: An assistant receives an impression of a user, the impression including at least an image of the user. The assistant may then receive impression guidelines based on a trained computer model. Using the impression guidelines, the assistant analyzes the impression of the user to determine if the impression of the user is appropriate. The assistant then informs the user at a user device of the outcome of the said analyzing the impression of the user.

Abstract: Systems, methods and apparatuses are described for determining an image that corresponds to a received input instruction. Input may be received which comprises an instruction for an image sensor to capture at least one image of a subject and the instruction comprising at least one criterion for the at least one image of the subject. An image sensor may capture, based on the instruction, captured images of the subject. An instruction vector may be determined based on the instruction, and a captured image vector for each of the captured images of the subject may be determined. At least one captured image vector of the captured images and the instruction vector may be compared to determine a corresponding image from the captured images, and the corresponding image may be provided.

Abstract: Systems and methods are provided for enabling enhanced group media session interactions. A group session for consuming a media content item is initiated between first and second computing devices, and a portion of the media content item is received at the computing devices. A reaction of a first user is captured based at least in part on receiving the portion of the media content item. A trigger condition is identified, and it is determined that the captured reaction satisfies the trigger condition. In response to determining that the captured reaction satisfies the trigger condition, a prompt that is based on the portion of the media content item and the captured reaction is generated. A computing device is identified, and at least one of the portion of the media content item, the captured reaction, or the prompt is transmitted to the identified computing device and is generated for output.

Abstract: A vocabulary level of a user in a language to be learned is identified. During playback of a media asset on a first device, subtitles in the language are extracted for at least a portion of the media asset. The extracted subtitles may contain a single word, or a plurality of words in the language in question. Based on the vocabulary level, a subset of words from the extracted subtitles are predicted to be new to the user. The predicted new words are then generated for display on a second device associated with the user, along with an explanation of each word of the subset of words.

Abstract: Systems and methods for providing wireless power are described herein. A plurality of lasers may provide laser power to an array of laser absorbing elements. A laser of the plurality of lasers is assigned to a laser absorbing element of the array of laser absorbing elements. Portions of the laser absorbing element that are within a line of sight of the assigned laser are identified. The assigned laser scans the identified portions of the laser absorbing element to provide the laser power to the laser absorbing element. The laser absorbing element converts the laser power to electrical power. Electrical power from the laser absorbing elements may provide electrical power to a device.