Abstract: A device may receive a video and corresponding camera information associated with a camera that captured the video, and may select an object in the video and a wire model for the object. The device may adjust an orientation, location, or size of the wire model to align the wire model on the object in a frame of the video, based on the corresponding camera information and to generate an adjusted wire model. The device may identify the object in another frame of the video, and may align the adjusted wire model on the object in the other frame. The device may interpolate the adjusted wire model for the object for intermediate frames of the video between the first and other frames, and may generate three-dimensional annotations for the video based on the adjusted wire models. The device may train a machine learning model based on the three-dimensional annotations.

Abstract: A method according to one embodiment includes detecting a first touch event on a touch-sensitive input area of a device, determining that the first touch event corresponds to a command to anchor a first cursor at a current location of the first cursor on a display area coupled to the touch-sensitive input area, anchoring the first cursor at the current location thereof on the display area in response to determining that the first touch event corresponds to the command to anchor the first cursor, detecting a second touch event, outputting a second cursor on the display area, changing the output location of the second cursor in response to detecting that a detected touch of the second touch event departs from a starting location of the second touch event, and outputting a selection indicator on a portion of the display area between the first cursor and second cursor.

Abstract: A method according to one embodiment includes detecting a first touch event on a touch-sensitive input area of a device, determining that the first touch event corresponds to a command to anchor a first cursor at a current location of the first cursor on a display area coupled to the touch-sensitive input area, anchoring the first cursor at the current location thereof on the display area in response to determining that the first touch event corresponds to the command to anchor the first cursor, detecting a second touch event, outputting a second cursor on the display area, changing the output location of the second cursor in response to detecting that a detected touch of the second touch event departs from a starting location of the second touch event, and outputting a selection indicator on a portion of the display area between the first cursor and second cursor.