Techniques are described for an autonomous asset management system that integrates autonomous devices, such as drone devices and other robotic devices, with a home security system of a property to enable management, monitoring, and/or tracking of various assets located within the property. In some implementations, an indication of an asset associated with a property is obtained by an autonomous device. Sensor data collected by one or more sensors of the property is obtained by the autonomous device based on the indication of the asset. A present status of the asset is determined by the autonomous device based on the sensor data. A determination that the present status of the asset does not correspond to an expected status of the asset is made by the autonomous device. In response, the autonomous device navigates to the particular location of the property.

A terminal device including: a communication interface which is communicably connected to a server device via a network; a memory that is configured to store computer readable instructions; a processor configured to execute the computer-readable instructions so as to cause the communication interface to receive image selection information of a display image from the server, the display image being included in the advertisement and select one of a plurality of images as the display image to be included in the advertisement based on the selection information, the plurality of images being stored in at least one of the memory and a storage device connected to the terminal device via the network; and a display configured to display the advertisement including the selected display image.

Embodiments of the present disclosure disclose a method, apparatus and storage medium for implementing a discrete frame-based scene section, wherein the method comprises: obtaining at least one first tag for mapping a discrete frame to a scene section; for any second tag in the at least one first tag, performing polling query on to-be-processed first discrete frames respectively to determine whether there is a second discrete frame matched with the second tag in the first discrete frames; if there is the second discrete frame, marking the second discrete frame with the second tag corresponding to a scene section; if the polling query corresponding to the second tag ends, storing start frame timestamp information and end frame timestamp information of the scene section. The solutions of embodiments of the present disclosure may be applied to save the storage resources.

A method including receiving at a first time a textual query, receiving at a second time after the first time a visual input associated with the textual query, generating text based the visual input, generating a composite query based on a combination of the textual query and the text based on the visual input, and generating search results based on the composite query, the search results including a plurality of links to content.

A content retrieval system uses a graph neural network architecture to determine images relevant to an image designated in a query. The graph neural network learns a new descriptor space that can be used to map images in the repository to image descriptors and the query image to a query descriptor. The image descriptors characterize the images in the repository as vectors in the descriptor space, and the query descriptor characterizes the query image as a vector in the descriptor space. The content retrieval system obtains the query result by identifying a set of relevant images associated with image descriptors having above a similarity threshold with the query descriptor.

A content retrieval system uses a graph neural network architecture to determine images relevant to an image designated in a query. The graph neural network learns a new descriptor space that can be used to map images in the repository to image descriptors and the query image to a query descriptor. The image descriptors characterize the images in the repository as vectors in the descriptor space, and the query descriptor characterizes the query image as a vector in the descriptor space. The content retrieval system obtains the query result by identifying a set of relevant images associated with image descriptors having above a similarity threshold with the query descriptor.

An approach is provided in which the approach the approach deconstructs a user interface into user interface elements that each are assigned an importance score. The approach compares a user eye gaze pattern of a user viewing the user interface against an expected eye gaze pattern corresponding to the user interface, and determines that the user requires assistance navigating the user interface. The approach selects one of the user interface elements based on its importance score, generates an augmented reality overlay of the selected user interface element, and displays the augmented reality overlay on the user interface using an augmented reality device.

Disclosed is an electronic apparatus providing a reply to a query of a user. The electronic apparatus includes a microphone, a camera, a memory configured to store at least one instruction, and at least one processor, and the processor is configured to execute the at least one instruction to control the electronic apparatus to: identify a region of interest corresponding to a co-reference in an image acquired through the camera based on a co-reference being included in the query, identify an object referred to by the co-reference among at least one object included in the identified region of interest based on a dialogue content that includes the query, and provide information on the identified object as the reply.

Embodiments provide for an augmented reality (AR) system able to track the movement of real-world objects and apply that movement to virtual objects. The AR system includes a radio configured to receive first sensor data from a sensor attached to a first physical object in physical space. The AR system further includes a processor configured to determine when a physical object changes from a first state to a second state object based on the first sensor data, and update an environmental map based on the change from the first state to the second state of the first physical object.

Systems, apparatus, methods, and articles of manufacture provide for managing and presenting historical environment information as virtual content in augmented reality (AR) environments and applications.