Abstract: Examples relating to calibrating an estimated gaze location are disclosed. One example method comprises monitoring the estimated gaze location of a viewer using gaze tracking data from a gaze tracking system. Image data for display via a display device is received, the image data comprising at least one target visual and target visual metadata that identifies the at least one target visual. The target visual metadata is used to identify a target location of the at least one target visual. The estimated gaze location of the viewer is monitored and a probability that the viewer is gazing at the target location is estimated. The gaze tracking system is calibrated using the probability, the estimated gaze location and the target location to generate an updated estimated gaze location of the viewer.

Abstract: A hand held appliance including a handle having an outer wall, an inner structure disposed within the outer wall and an end wall extending across the outer wall wherein the end wall is attached to the handle via the inner structure and the end wall extends away from the outer wall. The handle may have a longitudinal axis along which the outer wall extends; the end wall may extend away from the outer wall towards the longitudinal axis. The end wall may extend from the outer wall towards the longitudinal axis as the end wall extends away from the outer wall and may taper as it extends away from the outer wall. The end wall may be frustoconical in shape. The end wall may include at least one first attachment member that extends from the end wall to engage with one or more cooperating attachment members of the inner structure.

Abstract: Methods of low power detection of an activation phrase are described. A microphone system comprises dedicated hardware logic for detecting a pre-defined activation phrase in an audio stream received via a microphone. If the pre-defined activation phrase is detected, the hardware logic sends a trigger signal to activate a module, such as a main speech detection module, which is external to the microphone system and which may be in a low power standby state.

Abstract: Methods of low power detection of an activation phrase are described. A microphone system comprises dedicated hardware logic for detecting a pre-defined activation phrase in an audio stream received via a microphone. If the pre-defined activation phrase is detected, the hardware logic sends a trigger signal to activate a module, such as a main speech detection module, which is external to the microphone system and which may be in a low power standby state.

Abstract: Embodiments are disclosed herein that relate to selecting user interface elements via a periodically updated position signal. For example, one disclosed embodiment provides a method comprising displaying on a graphical user interface a representation of a user interface element and a representation of an interactive target. The method further comprises receiving an input of coordinates of the periodically updated position signal, and determining a selection of the user interface element if a motion interaction of the periodically updated position signal with the interactive target meets a predetermined motion condition.

Abstract: Methods of low power detection of an activation phrase are described. A microphone system comprises dedicated hardware logic for detecting a pre-defined activation phrase in an audio stream received via a microphone. If the pre-defined activation phrase is detected, the hardware logic sends a trigger signal to activate a module, such as a main speech detection module, which is external to the microphone system and which may be in a low power standby state.

Abstract: Examples relating to calibrating an estimated gaze location are disclosed. One example method comprises monitoring the estimated gaze location of a viewer using gaze tracking data from a gaze tracking system. Image data for display via a display device is received, the image data comprising at least one target visual and target visual metadata that identifies the at least one target visual. The target visual metadata is used to identify a target location of the at least one target visual. The estimated gaze location of the viewer is monitored and a probability that the viewer is gazing at the target location is estimated. The gaze tracking system is calibrated using the probability, the estimated gaze location and the target location to generate an updated estimated gaze location of the viewer.

Abstract: The present invention relates to sanitization devices and methods. More particularly, the invention relates to devices and methods that significantly reduce or eliminate germs, bacteria and/or other microorganisms from objects such as bags, purses, footwear or other objects, as well as bare feet, hands, paws, hooves or other anatomical surfaces, which come into contact with them. The device and method uses germicidal radiation which exposes only the areas of the object that come into applied contact with the device. The device contains an array of individual cells which are configured to turn on and off sanitizing radiation. The devices may be interconnected to fill a large area such as a lobby, the floor of a hospital and the like.

Abstract: Methods of low power detection of an activation phrase are described. A microphone system comprises dedicated hardware logic for detecting a pre-defined activation phrase in an audio stream received via a microphone. If the pre-defined activation phrase is detected, the hardware logic sends a trigger signal to activate a module, such as a main speech detection module, which is external to the microphone system and which may be in a low power standby state.

Abstract: Examples relating calibrating an estimated gaze location are disclosed. One example method comprises monitoring the estimated gaze location of a viewer using gaze tracking data from a gaze tracking system. Image data for display via a display device is received and, without using input from the viewer, at least one target visual that may attract a gaze of the viewer and a target location of the target visual are identified within the image data. The estimated gaze location of the viewer is compared with the target location of the target visual. An offset vector is calculated based on the estimated gaze location and the target location. The gaze tracking system is calibrated using the offset vector.

Abstract: In various implementations, specific attributes found in images can be used in a visual-based search. Utilizing machine learning, deep neural networks, and other computer vision techniques, attributes of images, such as color, composition, font, style, and texture can be extracted from a given image. A user can then select a specific attribute from a sample image the user is searching for and the search can be refined to focus on that specific attribute from the sample image. In some embodiments, the search includes specific attributes from more than one image.

Abstract: In various implementations, one or more specific attributes found in an image can be modified utilizing one or more specific attributes found in another image. Machine learning, deep neural networks, and other computer vision techniques can be utilized to extract attributes of images, such as color, composition, font, style, and texture from one or more images. A user may modify at least one of these attributes in a first image based on the attribute(s) of another image and initiate a visual-based search using the modified image.

Abstract: Methods of low power detection of an activation phrase are described. A microphone system comprises dedicated hardware logic for detecting a pre-defined activation phrase in an audio stream received via a microphone. If the pre-defined activation phrase is detected, the hardware logic sends a trigger signal to activate a module, such as a main speech detection module, which is external to the microphone system and which may be in a low power standby state.

Abstract: A hand held appliance comprising a body, a handle having a first end connected to the body and a second end distal to the first end, an end wall extending across the handle at the second end of the handle wherein said end wall is detachable from the handle and a filter is provided within the handle. The end wall may include a plurality of apertures which may comprise a fluid inlet into the appliance. The end wall may be flexible and may be made from a plastic material such as polypropylene and ABS. The end wall may comprise a rim and a lip extending radially inwards of the rim.

Abstract: Embodiments that relate to scaling a visual element displayed via a display device are disclosed. In one embodiment a method includes receiving and using gaze tracking data to determine gaze locations at which a user is gazing on the display device. Depth tracking data is received and used to determine that a user's pointer is at a predetermined location. In response, a locked gaze location on the screen is locked, where the locked gaze location includes at least a portion of the visual element. In response to locking the locked gaze location, the visual element is programmatically scaled by a predetermined amount to an enlarged size. A user input selecting the visual element is then received.

Abstract: A hand held appliance including a handle having an outer wall, an inner structure disposed within the outer wall and an end wall extending across the outer wall wherein the end wall is attached to the handle via the inner structure and the end wall extends away from the outer wall. The handle may have a longitudinal axis along which the outer wall extends; the end wall may extend away from the outer wall towards the longitudinal axis. The end wall may extend from the outer wall towards the longitudinal axis as the end wall extends away from the outer wall and may taper as it extends away from the outer wall. The end wall may be frustoconical in shape. The end wall may include at least one first attachment member that extends from the end wall to engage with one or more cooperating attachment members of the inner structure.