Abstract: Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training one or more layers of the 3D perception network as part of a training network using real source rig data and simulated source and target rig data. Feature statistics extracted from the real source data may be used to transform the features extracted from the simulated data during training. The paths for real and simulated data through the resulting network may be alternately trained on real and simulated data to update shared weights for the different paths. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks.

Abstract: Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simulated source and target rig data. A consistency loss that compares (e.g., top-down) transformed feature maps extracted from simulated source and target rig data may be used to minimize differences across training channels. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks.

Abstract: Disclosed are a terminal and operating method thereof. The present invention includes obtaining an input for selecting at least one video, displaying a polyhedron displaying a preview image of the selected at least one video on each of a plurality of faces, obtaining an input for selecting at least one of a plurality of the faces included in the displayed polyhedron, and outputting a video corresponding to the selected face.

Abstract: Disclosed are a terminal and operating method thereof. The present invention includes obtaining an input for selecting at least one video, displaying a polyhedron displaying a preview image of the selected at least one video on each of a plurality of faces, obtaining an input for selecting at least one of a plurality of the faces included in the displayed polyhedron, and outputting a video corresponding to the selected face.

Abstract: A mobile terminal and a method for converting a display mode thereof are disclosed. The mobile terminal performs a first display action for three-dimensionally displaying a part of a image in a first zone of an entire display zone and two-dimensionally displaying the other part of the image in a second zone as a gesture externally input for conversion between two-dimensional display and three-dimensional display is recognized, and performs a second display action subsequently to the first display action for three-dimensionally displaying a part of the image in a third zone of the entire display zone and two-dimensionally displaying the other part of the image in a fourth zone.

Abstract: A mobile terminal including a wireless communication unit configured to wirelessly communicate with at least one other terminal; a display unit including a touchscreen; and a controller configured to display on the display unit a log information region representing page edges of an e-book executed on the mobile terminal, determine a variable characteristic of the executed e-book including at least one of 1) a number of times prescribed pages of the e-book have been displayed, and 2) an amount of time spent displaying the prescribed pages of the e-book, and distinctively mark the page edges of the e-book in accordance with the determined variable characteristic of the executed e-book.

Abstract: A mobile terminal including a wireless communication unit configured to wirelessly communicate with at least one other terminal; a display unit including a touchscreen; and a controller configured to display on the display unit a log information region representing page edges of an e-book executed on the mobile terminal, determine a variable characteristic of the executed e-book including at least one of 1) a number of times prescribed pages of the e-book have been displayed, and 2) an amount of time spent displaying the prescribed pages of the e-book, and distinctively mark the page edges of the e-book in accordance with the determined variable characteristic of the executed e-book.

Abstract: A mobile terminal and a method for converting a display mode thereof are disclosed. The mobile terminal performs a first display action for three-dimensionally displaying a part of a image in a first zone of an entire display zone and two-dimensionally displaying the other part of the image in a second zone as a gesture externally input for conversion between two-dimensional display and three-dimensional display is recognized, and performs a second display action subsequently to the first display action for three-dimensionally displaying a part of the image in a third zone of the entire display zone and two-dimensionally displaying the other part of the image in a fourth zone.