Abstract: An image correcting method of the present invention includes: a step of performing a preprocessing process on an original image to generate a mask image including only an erased area of the original image; a step of predicting, by using generative adversarial networks, an image which is to be synthesized with the erased area in the mask image; and a step of synthesizing the predicted image with the erased area of the original image to generate a new image.

Abstract: The disclosure relates to a method of extracting image features based on a vision transformer, a method of performing embedding on an input image in units of patches and extracting visual features through global attention. An apparatus for extracting an image feature based on a vision transformer according to an embodiment of the disclosure includes a memory configured to store data and a processor configured to control the memory, wherein the processor is configured to perform embedding on multi-patches for an input image, extract feature maps for the embedding multi-patches, perform transformer encoding based on a neural network using the extracted feature maps, extract a feature of the input image through a final feature map extracted through the transformer encoding, and wherein the patches have different sizes.

Abstract: The present disclosure relates to a method and apparatus for constructing a network adaptable to consecutive/complex domains. An apparatus for constructing a domain adaptive network according to an embodiment of the present disclosure includes a memory configured to store data; and a processor configured to control the memory, wherein the processor is configured to determine a weight to be applied to one or more neural networks based on input data, construct a final neural network by applying the weight to the one or more neural networks, and output result data of the input data using the final neural network, wherein the one or more neural networks are trained using data for each prototype domain.

Abstract: Disclosed herein are a method and apparatus for processing feature information based on an artificial neural network. According to an embodiment of the present disclosure, the apparatus for processing feature information based on an artificial neural network may include a memory for storing data and a processor for controlling the memory, and the processor may further be configured to extract a graph, which includes vertices, based on a feature map of an image, to extract a feature vector corresponding to the vertices and to process the graph and the feature vector based on an artificial neural network, and the graph may include positions of the vertices and information on a connection relationship between the vertices.

Abstract: Provided are an object detection system and an object detection method. An object detection system may include a feature map extraction module configured to receive an image for object detection and extract a feature map having multiple resolutions for the image; a bounding box detection module configured to classify a bounding box by applying a first group of convolutional layers to the feature map, and predict the bounding box by applying a second group of convolutional layers to the feature map; and a mask generation module configured to generate a mask for the shape of the object in the bounding box using the feature map.

Abstract: An image correcting method of the present invention includes: a step of performing a preprocessing process on an original image to generate a mask image including only an erased area of the original image; a step of predicting, by using generative adversarial networks, an image which is to be synthesized with the erased area in the mask image; and a step of synthesizing the predicted image with the erased area of the original image to generate a new image.

Abstract: Provided are an object detection system and an object detection method. An object detection system may include a feature map extraction module configured to receive an image for object detection and extract a feature map having multiple resolutions for the image; a bounding box detection module configured to classify a bounding box by applying a first group of convolutional layers to the feature map, and predict the bounding box by applying a second group of convolutional layers to the feature map; and a mask generation module configured to generate a mask for the shape of the object in the bounding box using the feature map.

Abstract: A system for generating a multimedia knowledge base uses a multimedia information detection unit to detect texted meta information from multimedia data including at least one combination of a text, a voice, an image and a video and allows a knowledge base shaping unit to use the texted meta information and context information of the multimedia data to divide the multimedia data into syntactic information representing extrinsic configuration information and semantic information representing intrinsic meaning information and may shape the syntactic information and the semantic information into the multimedia knowledge.

Abstract: Disclosed are a terminal and a method for controlling thereof that load a user authorization function in a terminal such as a remote controller that remotely controls an external display apparatus such as a TV, etc. and allow only users who accept user authorization to use the display apparatus.

Abstract: An apparatus for controlling digital appliances based on parking management is disclosed. The apparatus includes an interface unit, connected to a control terminal through a wired/wireless communication network, for providing an interface for establishing a home network service environment that is dependent upon information about incoming or outgoing vehicle; a storage unit for storing the home network service environment established by the interface; and an appliance controller for controlling the digital appliances based on the home network service environment stored in the storage unit, upon receipt of the information about incoming or outgoing vehicle.

Abstract: Provided is a home-network UMB system and a method thereof for providing interoperability between devices connected one another through different types of middlewares in a home network. The home-network UMB system includes: a bridge core for establishing/releasing a connection between bridge adaptors of different types of middlewares and analyzing/transferring a universal middleware message in order to interoperate devices connected through different types of middlewares existed on a home network; and a plurality of bridge adaptor for connecting the bridge core to a corresponding middleware, and finding/releasing different types of devices, controlling/monitoring different types of devices and registering/creating an event for different types of devices through transforming a universal middleware bridge message to a local message of each middleware and vice versa.

Abstract: Disclosed are a terminal and a method for controlling thereof that load a user authorization function in a terminal such as a remote controller that remotely controls an external display apparatus such as a TV, etc. and allow only users who accept user authorization to use the display apparatus.

Abstract: An apparatus for controlling digital appliances based on parking management is disclosed. The apparatus includes an interface unit, connected to a control terminal through a wired/wireless communication network, for providing an interface for establishing a home network service environment that is dependent upon information about incoming or outgoing vehicle; a storage unit for storing the home network service environment established by the interface; and an appliance controller for controlling the digital appliances based on the home network service environment stored in the storage unit, upon receipt of the information about incoming or outgoing vehicle.

Abstract: A home network system includes: a plurality of wireless devices cooperated with a home network, each device having a tag attached thereto to identify it; a tag reader for reading tag information from the tag of each wireless device; and a network manager for storing a shared key and identifying each wireless device connected to the home network using the tag information and supporting information exchange between the wireless devices by using the shared key.

Abstract: Provided is a home-network UMB system and a method thereof for providing interoperability between devices connected one another through different types of middlewares in a home network. The home-network UMB system includes: a bridge core for establishing/releasing a connection between bridge adaptors of different types of middlewares and analyzing/transferring a universal middleware message in order to interoperate devices connected through different types of middlewares existed on a home network; and a plurality of bridge adaptor for connecting the bridge core to a corresponding middleware, and finding/releasing different types of devices, controlling/monitoring different types of devices and registering/creating an event for different types of devices through transforming a universal middleware bridge message to a local message of each middleware and vice versa.

Abstract: Disclosed are system and method of remotely controlling the home appliance by employing the voice/character recognition technique. The appliance detects a connection relationship between the appliance and the mobile terminal and dynamically transmits the control code and a module for transmission. If the appliance control command is inputted through the voice control command input screen or the handwriting control command input screen, after the inputted command is interpreted through the voice/character recognition technique and is transformed to the control code of the appliance to be sent to the home appliance, the control code is sent to the home appliance to remotely control it. The function thereof may be extended to the environment capable of implementing the bi-directional communication with the appliance by receiving the control code from the appliance, while overcoming the limitation of the conventional terminal having a fixed function.

Abstract: Disclosed are system and method of remotely controlling the home appliance by employing the voice/character recognition technique. The appliance detects a connection relationship between the appliance and the mobile terminal and dynamically transmits the control code and a module for transmission. If the appliance control command is inputted through the voice control command input screen or the handwriting control command input screen, after the inputted command is interpreted through the voice/character recognition technique and is transformed to the control code of the appliance to be sent to the home appliance, the control code is sent to the home appliance to remotely control it. The function thereof may be extended to the environment capable of implementing the bi-directional communication with the appliance by receiving the control code from the appliance, while overcoming the limitation of the conventional terminal having a fixed function.