Abstract: Systems, methods, and apparatuses are described for capturing panoramic images and positioning virtual objects on a device screen, using a device having a static camera and an adjustable camera. To generate a panoramic image, the device moves the field of view of the adjustable camera by moving a corresponding MEMS mirror. The device then captures a first image using the static camera, and a second image using the adjustable camera, and generates a panoramic image by combining the first and second images. To position a virtual object, the device captures a first image using the static camera, and determines that there are insufficient visual features in the first image for positioning. The device moves the field of view of the adjustable camera by moving the corresponding MEMS mirror, and captures a second image. Visual features from the second image are then used to position the virtual object.

Abstract: Systems, methods, and apparatuses are described for causing a camera of a head-mounted computing device to capture a first video, the head-mounted computing device comprising a camera direction control element for controlling a capture direction of the camera, and a camera zoom control element for controlling zoom of the camera. One or more objects in the captured first video may be identified based on a detected gaze angle of a user wearing the head-mounted computing device. A target location in an environment may be determined, and based on such target location, the capture direction and zoom of the camera may be adjusted using the camera direction control element and the camera zoom control element, respectively. The camera may capture, based on the adjusted capture direction and the adjusted zoom of the camera, a second video using the camera of the head-mounted computing device.

Abstract: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.

Abstract: The present disclosure is directed to systems and methods for reducing or preventing motion sickness using an animated overlay displayed over a content item and reflecting a detected acceleration. In some embodiments the systems and methods generate for display, on a device, a content item. The systems and methods determine an acceleration of the device along a vector, where the vector comprises a vector component that is normal to a plane defined by the display of the content item. The systems and methods then generate for display a graphical overlay over the display of the content item, wherein the graphical overlay is animated to appear to move in a direction defined by the vector comprising the vector component that is normal to the plane defined by the display.

Abstract: Systems and methods are provided herein for playing post-credits content in media assets by overriding play-next logic in OTT applications and presenting options for post-credits content in broadcast applications. A media application may be pre-configured to automatically “play-next” a queued media asset after the beginning of credits of a media asset start playing. However, if the media application detects post-credits content (e.g., trailer), it may display a user interface prompt to present options that may include continuing to play the credits, or to skip the credits entirely and go straight to the post-credits content. Upon receiving the user interface selection for one of the options, the media application modifies the playing of the media asset to override the configuration to automatically play-next, and instead modifies the logic to play the selected one of two options as described above.

Abstract: Systems and methods for alleviating neck pain during media consumption. The methods and systems comprise determining, using control circuitry a current orientation of each of a user's head and a user device, determining an environmental parameter relating to the user's environment, determining a range of permitted orientations of the user's head based on the environmental parameter and the current orientations of the user's head and the user device, determining, using control circuitry, whether the orientation of the user's head is outside of the range of permitted orientations, and in response to determining that the orientation of the user's head is outside of a range of permitted orientations, causing, using control circuitry, a change in a mode of display of the user device.

Abstract: System and methods are disclosed for engaging and disengaging a regenerative braking system of a first vehicle coupled to a second vehicle. In an embodiment, a coupler (e.g., a tow bar) connects the front of a first vehicle (e.g., a towed vehicle) to the rear of a second vehicle (e.g., towing vehicle). The regenerative braking systems includes a motor-generator coupled to a wheel set of the first vehicle and a battery for storing electrical power generated by the motor-generator. The motor-generator is used to apply an accelerating force to the driven wheel set when forward acceleration is needed. The motor-generator is also used to generate electrical power by harnessing the vehicles' momentum to turn the rotor of the motor-generator, which causes a decelerating torque to be applied to the driven wheel set.

Abstract: Systems and methods are described for enabling delivery of an order to a customer's vehicle travelling along a first navigational route. The customer inputs an order, and a plurality of candidate vendors and candidate delivery locations are determined. A target delivery location and target vendor are selected from among the plurality of candidate delivery locations and candidate vendors based on optimizing one or more predetermined criteria. The order is transmitted to the target vendor, and a confirmation is received. The target delivery location is then transmitted to the customer. The customer travels to the target delivery location to pick up the order.

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: Methods and systems are disclosed herein for modifying one or more color changing exterior surfaces of a vehicle in response to identified safety events. Specifically, a safety event is identified in a surrounding environment of a vehicle that comprises one or more color-changing exterior surfaces. In response to the identifying of the safety event, a color scheme is selected for the one or more color-changing exterior surfaces of the vehicle based on the type or safety event and the appearance of the surrounding environment. One or more color changing exterior surfaces of the vehicle are modified to match the selected color scheme.

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that perform language guided digital image editing utilizing a cycle-augmentation generative-adversarial neural network (CAGAN) that is augmented using a cross-modal cyclic mechanism. For example, the disclosed systems generate an editing description network that generates language embeddings which represent image transformations applied between a digital image and a modified digital image. The disclosed systems can further train a GAN to generate modified images by providing an input image and natural language embeddings generated by the editing description network (representing various modifications to the digital image from a ground truth modified image). In some instances, the disclosed systems also utilize an image request attention approach with the GAN to generate images that include adaptive edits in different spatial locations of the image.

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: System and methods are provided to analyze media content to determine one or more parameters associated with the media content. Metadata is generated storing the one or more parameters. A request to display the media content with second captions is received. Second captions are generated for display based on the metadata.

Abstract: System and method are provided for capturing images based on dominant eye characteristics of a user. The system detects, by a wearable device, a hand gesture of the user indicating an image boundary for capturing an image from one or more cameras of the wearable device. The system generates, by the wearable device, the image based on (a) a dominant eye characteristic of the user, (b) the image boundary indicated by the hand gesture of the user, and (c) one or more images captured from the one or more cameras of the wearable device. The system stores, by the wearable device, the generated image to memory.

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: The present disclosure is directed to systems and methods to enhance the process of creating an artificial intelligence (AI) generated content or content items, such as images, text, video, sounds, etc., using a text or other suitable prompt, such as via voice input. The systems and methods disclosed provide streamlined content generation with, e.g., reduced processing power and computing time. In an embodiment the systems and methods receive a prompt for generating a first content item using a generative artificial intelligence (AI) model and retrieve, based on the prompt, a collection of matching content items. The systems and methods may then receive input selecting one of the content items from the collection and identify a prompt used to generate the selected content item. The systems and methods may then merge using a trained natural language processing model, the received prompt with the prompt of the selected content item to create a third prompt.

Abstract: Systems and methods are provided herein for improving efficiency of electric vehicle charging stations by allowing multiple charging connectors from each charging port at a station, so that the connectors can be plugged into multiple vehicles at the same time, establishing a queue based on order of arrival and other factors, and automatically switching active charging among the connectors. Specifically, the vehicle charging station identifies a plurality of vehicles simultaneously electrically connected to a plurality of charging cables, then identifies an order of connection of the plurality of vehicles to the plurality of charging cables, and based on the order of connection, selects a subset of the plurality of vehicles to be charged, then configures the switch system to enable the at least one power generator to charge the subset of the plurality of vehicles.

Abstract: The present disclosure relates to the technical field of display screen, and provides a display module set and a display screen. The display module set comprises a cabinet frame and a plurality of display modules. The cabinet frame comprises a power box and a plurality of sub-frames located on the left and right sides of the power box. The sub-frames on each side are arranged sequentially in a vertical direction. The plurality of the display modules corresponds to a plurality of the sub-frames on a one-to-one basis. A drive circuit and mounting members of the display module are both provided on a left side and/or right side region. A middle region of the display module is uniformly distributed with a hole structure for sound transmission. The display module is mounted on a corresponding sub-frame via the mounting members of the left side and/or right side region.