Abstract: The present invention provides a multiclass classification apparatus and method robust to imbalanced data, which generate artificial data of a minority class on the basis of an over-sampling technique based on adversarial learning to balance imbalanced data and performs multiclass classification robust to imbalanced data by using corresponding data in class classification learning without additionally collecting data.

Abstract: Provided is an apparatus for classifying an attribute of an image object, including: a first memory configured to store target object images that are indexed; a second memory configured to store target object images that are un-indexed; and an object attribute classification module configured to perform learning on the un-indexed target object images to construct a classifier for classifying a detailed attribute of target object, and finely adjust the classifier on the basis of the indexed target object images.

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: A domain adaptation-based object recognition apparatus includes a memory configured to store a domain adaptation-based object recognition program and a processor configured to execute the program. The processor learns a generative model for generating a feature or an image similar to a gallery image on the basis of domain adaptation in association with an input probe image and learns an object recognition classification model by using a learning database corresponding to the gallery image and the input probe image, thereby performing object recognition using the input probe image.

Abstract: Provided is an apparatus for classifying an attribute of an image object, including: a first memory configured to store target object images that are indexed; a second memory configured to store target object images that are un-indexed; and an object attribute classification module configured to perform learning on the un-indexed target object images to construct a classifier for classifying a detailed attribute of target object, and finely adjust the classifier on the basis of the indexed target object images.

Abstract: A domain adaptation-based object recognition apparatus includes a memory configured to store a domain adaptation-based object recognition program and a processor configured to execute the program. The processor learns a generative model for generating a feature or an image similar to a gallery image on the basis of domain adaptation in association with an input probe image and learns an object recognition classification model by using a learning database corresponding to the gallery image and the input probe image, thereby performing object recognition using the input probe image.

Abstract: Provided is a dynamic object detecting technique, and more specifically, a system and method for determining a state of a motion of a camera on the basis of a local motion estimated on the basis of a video captured by a dynamic camera and a result of analyzing a global motion, flexibly updating a background model according to the state of the motion of the camera, and flexibly detecting a dynamic object according to the state of the motion of the camera.

Abstract: Smart glasses for selectively tracking a target of visual cognition according to the present invention include a first camera configured to capture a first input image that is a first-person view image of a user, a second camera configured to capture a second input image containing sight line information of the user, a display configured to output additional information corresponding to the first input image, a memory configured to store a program for selectively tracking a target of visual cognition on the basis of the first and second input images, and a processor configured to execute the program stored in the memory, wherein upon executing the program, the processor is configured to detect the target of visual cognition from the first input image and determine, from the second input image, whether the user is in an inattentive state with respect to the target of visual cognition.

Abstract: Disclosed herein are a video interpretation apparatus and method. The video interpretation apparatus includes an object information generation unit for generating object information based on objects in an input video, a relation generation unit for generating a dynamic spatial relation between the objects based on the object information, a general event information generation unit for generating general event information based on the dynamic spatial relation, a video information generation unit for generating video information including any one of a sentence and an event description based on the object information and the general event information, and a video descriptor storage unit for storing the object information, the general event information, and the video information.

Abstract: Disclosed herein are a query input apparatus and method. The query input apparatus includes: an input unit providing a graphic user interface (GUI) to receive a schematized composite activity that a user wants to search from the user; and a processing unit generating a query using an activity descriptor corresponding to the schematized composite activity depending on a query request from an activity searching system and transferring the generated query to the activity searching system.

Abstract: Provided is a dynamic object detecting technique, and more specifically, a system and method for determining a state of a motion of a camera on the basis of a local motion estimated on the basis of a video captured by a dynamic camera and a result of analyzing a global motion, flexibly updating a background model according to the state of the motion of the camera, and flexibly detecting a dynamic object according to the state of the motion of the camera.

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: An apparatus and method for providing primitive visual knowledge are disclosed. The method of providing primitive visual knowledge includes receiving an image in a form of a digital image sequence, dividing the received image into scenes, extracting a representative shot from each of the scenes, extracting objects from frames which compose the representative shot, extracting action verbs based on a mutual relationship between the extracted objects, selecting a frame best expressing the mutual relationship with the objects, which are the basis for the extracting of the action verbs, as a key frame, generating the primitive visual knowledge based on the selected key frame, storing the generated primitive visual knowledge in a database, and visualizing the primitive visual knowledge stored in the database to provide the primitive visual knowledge to a manager.

Abstract: Disclosed herein are a video interpretation apparatus and method. The video interpretation apparatus includes an object information generation unit for generating object information based on objects in an input video, a relation generation unit for generating a dynamic spatial relation between the objects based on the object information, a general event information generation unit for generating general event information based on the dynamic spatial relation, a video information generation unit for generating video information including any one of a sentence and an event description based on the object information and the general event information, and a video descriptor storage unit for storing the object information, the general event information, and the video information.

Abstract: Disclosed herein are a query input apparatus and method. The query input apparatus includes: an input unit providing a graphic user interface (GUI) to receive a schematized composite activity that a user wants to search from the user; and a processing unit generating a query using an activity descriptor corresponding to the schematized composite activity depending on a query request from an activity searching system and transferring the generated query to the activity searching system.

Abstract: An apparatus and method for providing primitive visual knowledge are disclosed. The method of providing primitive visual knowledge includes receiving an image in a form of a digital image sequence, dividing the received image into scenes, extracting a representative shot from each of the scenes, extracting objects from frames which compose the representative shot, extracting action verbs based on a mutual relationship between the extracted objects, selecting a frame best expressing the mutual relationship with the objects, which are the basis for the extracting of the action verbs, as a key frame, generating the primitive visual knowledge based on the selected key frame, storing the generated primitive visual knowledge in a database, and visualizing the primitive visual knowledge stored in the database to provide the primitive visual knowledge to a manager.

Abstract: Disclosed herein are a server and method for providing collaboration service, and a sociality management server. The server includes a service provision unit and a space construction unit. The service provision unit sets up collaboration service corresponding to the results of combining functions of at least two collaboration terminals based on sociality values corresponding to the at least two collaboration terminals. The space construction unit constructs a service provision device space via which the collaboration service is to be provided. The service provision unit provides the collaboration service to the at least two collaboration terminals via the service provision device space.

Abstract: Disclosed are a system and method for managing personalization information of a virtual machine based on cloud computing. An exemplary embodiment of the present invention provides a system for managing personalization information of a virtual machine, including: virtual desktops positioned in on-demand services zone, and created and driven on the basis of the virtual machine; zone servers transmitting the personalization information of the virtual machine on at least one virtual desktop positioned in the on-demand service zones, and local servers storing personalization information of virtual machine on at least one virtual desktop positioned in at least one on-demand service zone and synchronizing the personalization information of the virtual machine with another local server.

Abstract: Disclosed herein are a device and method for displaying 3D images. The device includes an image processing unit for calculating the location of a user relative to a reference point and outputting a 3D image which is obtained by performing image processing on 3D content sent by a server based on the calculated location of the user, the image processing corresponding to a viewpoint of the user, and a display unit for displaying the 3D image output by the image processing unit to the user. The method includes calculating the location of a user relative to a reference point, performing image processing on 3D content sent by a server from a viewpoint of the user based on the calculated location of the user, and outputting a 3D image which is obtained by the image processing, and displaying the 3D image output by the image processing unit to the user.

Abstract: Disclosed are a multi-hop MIMO system and method. The multi-hop MIMO system according to an exemplary embodiment of the present invention includes: a server including a plurality of virtual machines; one remote screen device first connected to the server through at least one virtual machine of the plurality of virtual machines, receiving screen data from the server in a unicast scheme, and driven as a multicast server; and a plurality of different remote screen devices connected to the server through the at least one virtual machine, existing on a sub network where the one remote screen device exist, operating as multicast clients, receiving the screen data from the server or the one remote screen device in a multicast scheme, wherein the one remote screen device and the plurality of different remote screen devices simultaneously output the same screen data.