Adapting an automated assistant based on detecting: movement of a mouth of a user; and/or that a gaze of the user is directed at an assistant device that provides an automated assistant interface (graphical and/or audible) of the automated assistant. The detecting of the mouth movement and/or the directed gaze can be based on processing of vision data from one or more vision components associated with the assistant device, such as a camera incorporated in the assistant device. The mouth movement that is detected can be movement that is indicative of a user (to whom the mouth belongs) speaking.

Systems and methods for human-machine interaction. An adaptive behavioral control system of a human-machine interaction system controls an interaction sub-system to perform a plurality of actions for a first action type in accordance with a computer-behavioral policy, each action being a different alternative action for the action type. The adaptive behavioral control system detects a human reaction of an interaction participant to the performance of each action of the first action type from data received from a human reaction detection sub-system. The adaptive behavioral control system stores information indicating each detected human reaction in association with information identifying the associated action. In a case where stored information indicating detected human reactions for the first action type satisfy an update condition, the adaptive behavioral control system updates the computer-behavioral policy for the first action type.

An image processing apparatus sets a maximum size of an object that is to be included in a detection result of detection processing to detect the object from an image captured by an imaging unit, and sets a second region based on a position of a first region, designated by a user, in the image and the set maximum size. The second region, larger than the first region, includes the first region, and is subjected to the detection processing.

A method of image annotation includes selecting a plurality of annotation models related to an annotation task for an image, obtaining a candidate annotation map for the image from each of the plurality of annotation models, and selecting at least one of the candidate annotation maps to be displayed via a user interface, the candidate annotation maps comprising suggested annotations for the image. The method further includes receiving user selections or modifications of at least one of the suggested annotations from the candidate annotation map and generating a final annotation map based on the user selections or modifications.

A depth processor including a region of interest determination circuit and a depth decoder is provided. The region of interest determination circuit is configured to determine a size of a region of interest of an input image. The depth decoder is coupled to the region of interest determination circuit and configured to generate a depth map of the input image according to a filter size. The filter size is set according to the size of the region of interest of the input image.

An electronic apparatus includes a user interface unit and a user authentication unit. The user interface unit displays on a display device a user authentication screen that includes an input field for a password, and determines an inputted character string to the input field by a user operation performed to an input device. The user authentication unit performs user authentication on the basis of the inputted character string and a preregistered password. The user interface unit (a) determines a sight direction of the user on the basis of a face image taken by an imaging device, (b) determines whether the sight direction points to a predetermined range that includes the input field, and (c) if the sight direction points to the predetermined range, displays the inputted character string in the input field, or if not, displays a mask character string in the input field.

An electronic nameplate display method includes obtaining a position of a face of a participant in a video image and identity information of the participant, determining a display position and a size of an electronic nameplate in the video image based on the position of the face in the video image, and displaying the identity information of the participant using the electronic nameplate. In this method, self-adaptive adjustment of the electronic nameplate is implemented based on the position of the face.

There is disclosed an information handling system, including a camera, which may include an input lens, and an image signal processor, which may include circuitry that converts an analog image received at the input lens to a digital image data structure; a device interface may include circuitry that provides the image data structure to an information handling device, and a modifier circuit that modifies human features of the digital image data structure before the digital image data structure is provided to the device interface.

A video conferencing system for a vehicle includes a display device disposed in a passenger compartment of the vehicle, the display device comprising a screen, a first imager configured to capture a first image data corresponding to a field of view of a passenger compartment of the vehicle, at least one microphone configured to collect audio data from within the passenger compartment, and a controller. The controller is configured detect a display prompt within the image data corresponding to a portion of the image data received from the first imager, detect an audio prompt within a predetermined zone of the passenger compartment of the vehicle, and selectively crop the first image data according to the portion of the image data corresponding with the display prompt in response to determining a correlation between the portion of the image data and the zone of the passenger department associated with the audio prompt.

A method for generating interactive media content on a portable electronic user device is disclosed. The method includes in one or more electronic processing devices: retrieving an Edit Decision List (EDL), the EDL providing an event driven timeline for the interactive media content that defines events including: one or more segments of pre-existing media content to be used in the generation of the interactive media content; timestamps for when the one or more segments of pre-existing media content are to be introduced into the timeline and their associated duration; one or more user interactions to be used in the generation of the interactive media content; and, timestamps for when the one or more user interactions are to be introduced into the timeline and their associated duration; and, processing the EDL to generate the interactive media content in real time by: retrieving the one or more segments of pre-existing media content; recording the one or more user interactions using a sensing device of the user device; and, combining the one or more recorded user interactions with the one or more segments of pre-existing media in accordance with the event driven timeline of the EDL.