Abstract: Methods and systems are disclosed for pose comparison, interactive physical gaming, and remote fitness training on a user computing device. The methods and systems are configured to first receive a reference feature generated from a frame of a reference video, the reference feature computed from a reference posture of a reference person in the frame of the reference video. Next, receive a frame of a user video, the frame of the user video comprising a user. Next, extract a user posture from the frame of the user video, by performing a machine learning-based computer vision algorithm that detects one or more body key points of the user in an image plane of the user video. Finally, generate a user feature from the user posture; and determine an output score based on a distance between the reference feature and the user feature.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations). In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations). In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments provide a method for an application executing on a mobile device. The method renders an animated navigation presentation for output to an external display screen not part of the mobile device. The navigation presentation includes an animated map showing at least a portion of a route to a destination. The method simultaneously displays information regarding a maneuver along the route on a display screen of the mobile device without displaying a same animated map on the mobile device. In some embodiments, the displayed information regarding the maneuver comprises a graphical instruction and a text instruction for a next maneuver along the route.

Abstract: A computer-implemented method for video processing is disclosed. The method includes receiving an input video of one or more persons from a camera; detecting a sequence of human poses in the input video using an artificial intelligence (AI) based technique; selecting a proper pose from among multiple poses in a given frame of the input video, to generate a sequence of proper poses; detecting one or more key points in the sequence of proper poses; computing changes in coordinates of the one or more key points; computing a function of the changes in the coordinates of the one or more key points in the sequence of proper poses; counting a given user movement as a repetitive motion of an activity based on the function; and computing a plurality of statistics about the activity based on the counting.

Abstract: Some embodiments provide a method for an application executing on a mobile device. The method renders an animated navigation presentation for output to an external display screen not part of the mobile device. The navigation presentation includes an animated map showing at least a portion of a route to a destination. The method simultaneously displays information regarding a maneuver along the route on a display screen of the mobile device without displaying a same animated map on the mobile device. In some embodiments, the displayed information regarding the maneuver comprises a graphical instruction and a text instruction for a next maneuver along the route.

Abstract: A system and method for implementing a virtual fitness application are disclosed. Embodiments may be built for various platforms, including web browsers and mobile phones. One embodiment uses pose estimation to count the repetitive motions of a fitness activity (e.g., running). In one embodiment, to count the repetitive motions, a repetitive motion counting process is used that is based on computing differences of Y-coordinates of key points of the user. The repetitive motion counting process includes selecting a proper pose of the user; computing one or more delta values (corresponding to Y-coordinate changes of the key points); and counting a given user movement as a repetitive motion based on a function (e.g., average) of the delta values. One embodiment uses the pose estimation and repetitive motion count results to provide a gamified experience, for example, a leaderboard, a stats report, instant visual feedback, badges, coins, and a social experience.

Abstract: A system and method for implementing a virtual fitness application are disclosed. Embodiments may be built for various platforms, including web browsers and mobile phones. One embodiment uses pose estimation to count the repetitive motions of a fitness activity (e.g., running). In one embodiment, to count the repetitive motions, a repetitive motion counting process is used that is based on computing differences of Y-coordinates of key points of the user. The repetitive motion counting process includes selecting a proper pose of the user; computing one or more delta values (corresponding to Y-coordinate changes of the key points); and counting a given user movement as a repetitive motion based on a function (e.g., average) of the delta values. One embodiment uses the pose estimation and repetitive motion count results to provide a gamified experience, for example, a leaderboard, a stats report, instant visual feedback, badges, coins, and a social experience.

Abstract: Methods and systems are disclosed for pose comparison, interactive physical gaming, and remote fitness training on a user computing device. The methods and systems are configured to first receive a reference feature generated from a frame of a reference video, the reference feature computed from a reference posture of a reference person in the frame of the reference video. Next, receive a frame of a user video, the frame of the user video comprising a user. Next, extract a user posture from the frame of the user video, by performing a machine learning-based computer vision algorithm that detects one or more body key points of the user in an image plane of the user video. Finally, generate a user feature from the user posture; and determine an output score based on a distance between the reference feature and the user feature.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations). In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations) In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations). In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments of the invention provide an address harvester that harvests addresses from one or more applications executing on a device. Some embodiments use the harvested addresses to facilitate the operation of one or more applications executing on the device. Alternatively, or conjunctively, some embodiments use the harvested addresses to facilitate the operation of one or more applications executing on another device than the one used for harvesting the addresses. In some embodiments, a prediction system uses the harvested addresses to formulate predictions, which it then provides to the same set of applications from which it harvested the addresses in some embodiments.

Abstract: Some embodiments provide a mapping application that provides a variety of UI elements for allowing a user to specify a location (e.g., for viewing or serving as route destinations). In some embodiments, these location-input UI elements appear in succession on a sequence of pages, according to a hierarchy that has the UI elements that require less user interaction appear on earlier pages in the sequence than the UI elements that require more user interaction. In some embodiments, the location-input UI elements that successively appear in the mapping application include (1) selectable predicted-destination notifications, (2) a list of selectable predicted destinations, (3) a selectable voice-based search affordance, and (4) a keyboard.

Abstract: Some embodiments provide a method for an application executing on a mobile device. The method renders an animated navigation presentation for output to an external display screen not part of the mobile device. The navigation presentation includes an animated map showing at least a portion of a route to a destination. The method simultaneously displays information regarding a maneuver along the route on a display screen of the mobile device without displaying a same animated map on the mobile device. In some embodiments, the displayed information regarding the maneuver comprises a graphical instruction and a text instruction for a next maneuver along the route.

Abstract: Some embodiments provide a method for a mobile device connected to a vehicle's interactive communication system that includes a display screen. The method identifies at least one search term from audio data received through the vehicle's interactive communication system. At the mobile device, the method performs a search to identify at least one location related to the identified search term. The method generates a map, that displays the identified location, for output on the display screen of the interactive communication system of the vehicle.

Abstract: Some embodiments provide a method for an application executing on a mobile device. The method renders an animated navigation presentation for output to an external display screen not part of the mobile device. The navigation presentation includes an animated map showing at least a portion of a route to a destination. The method simultaneously displays information regarding a maneuver along the route on a display screen of the mobile device without displaying a same animated map on the mobile device. In some embodiments, the displayed information regarding the maneuver comprises a graphical instruction and a text instruction for a next maneuver along the route.

Abstract: Some embodiments provide a method for an application that operates on a mobile device. The method predicts several likely destinations for a vehicle to which the mobile device is connected based on data from a several different sources. The method generates, for a display screen of the vehicle, a display that includes the several likely destinations. In some embodiments, the method receives a first type of input through a control of the vehicle to select one of the likely destinations, and enters a turn-by-turn navigation mode to the selected destination in response to the received input. In some embodiments, the display is for a first destination of the several likely destinations. The method receives a second type of input through a control of the vehicle to step through the set of likely destinations, and generates a display for a second destination in response to the input.