Abstract: The present application relates to a use of a strain of the genus Cutibacterium, a culture of the strain, or a combination thereof for prevention, amelioration, and/or treatment of inflammatory skin diseases. A composition comprising a strain of the genus Cutibacterium, a culture of the strain, or a combination thereof does not show cytotoxicity, inhibits proliferation of immune cells that cause skin inflammation, suppresses immune responses, has an antibacterial effect against acne-causing bacteria, and promotes regeneration of skin cells, thereby exhibiting excellent preventive, ameliorating, and/or therapeutic effects of inflammatory skin diseases.

Abstract: The present disclosure relates to a novel Leuconostoc mesenteroides strain.

Abstract: The present invention relates to an image inpainting apparatus and an image inpainting method, the image inpainting apparatus including: a background inpainting part configured to generate a background-inpainted image by carrying out inpainting on a background with respect to an input image in which a region to be inpainted is set up; an object inpainting part configured to generate an object image by carrying out inpainting on an object; and an image overlapping part configured to generate an output image by causing the background-inpainted image and the object image, which are generated, to overlap each other.

Abstract: There are provided a method and a system for generating human motions, which generate motions of an empty frame by using motions in a given frame. A human motion generation method according to an embodiment includes: a first step of transforming, by a system, a domain of pose information of a frame; a second step of generating, by the system, motion features of an empty frame in the transformed domain; and a third step of inversely transforming, by the system, the generated motion features into a time domain. Accordingly, the method and system may effectively generate motions by obtaining a basis vector to be used for transforming a domain of motion trajectory information by training a deep learning-based transform model, transforming a motion trajectory through the basis vector, and inputting the transformed motion trajectory to a motion generation model.

Abstract: There is provided a video processing method performed by a computing device, the method including the steps of: collecting video from an external device; generating preprocessed data by extracting two-dimensional or three-dimensional skeleton information from the video; pre-training a first artificial intelligence model including N transformer blocks from the preprocessed data by applying an attention from a body of an object to a plurality of joints, an attention from each of the plurality of joints to the body, and an attention between persons; and learning, when parameters determined as a result of the pre-training of the first artificial intelligence model are transferred, a method of recognizing an action from the video received from the external device, using a second artificial intelligence model including the N transformer blocks on the basis of the parameters, wherein N is a natural number equal to or larger than 2.

Abstract: A method and a system for automatically generating multiple captions of an image are provided. A method for training an auto image caption generation model according to an embodiment of the present disclosure includes: generating a caption attention map by using an image; converting the generated caption attention map into a latent variable by projecting the caption attention map onto a latent space; deriving a guide map by using the latent variable; and training to generate captions of an image by using the guide map and the image. Accordingly, a plurality of captions describing various characteristics of an image and including various expressions can be automatically generated.

Abstract: A display apparatus is provided. The display apparatus includes: an image processor configured to process an image signal; a display; and a processor configured to control the image processor to produce, from a 360-degree image, a plurality of split images to be arranged along a circumference within a predetermined region that includes a great circle of a sphere shape being mapped, based on a viewpoint corresponding to a user input, the plurality of split images corresponding to a plurality of screens, and to produce a projection image to be displayed on the display based on the viewpoint from the split image of the screen that corresponds to the display apparatus from among the plurality of split images.

Abstract: A server according to the disclosure includes a communicator configured to communicate with a plurality of display apparatuses; and a controller configured to produce a plurality of split images corresponding to individual view angles of screens of the plurality of display apparatuses from each frame of a 360-degree image including a plurality of frames, transmit the plurality of split images according to the frames to the corresponding display apparatus, and control the communicator to transmit a split image updated corresponding to change in the individual view angle based on movement of a view point.

Abstract: A method and a system for automatically generating multiple captions of an image are provided. A method for training an auto image caption generation model according to an embodiment of the present disclosure includes: generating a caption attention map by using an image; converting the generated caption attention map into a latent variable by projecting the caption attention map onto a latent space; deriving a guide map by using the latent variable; and training to generate captions of an image by using the guide map and the image. Accordingly, a plurality of captions describing various characteristics of an image and including various expressions can be automatically generated.

Abstract: An electronic apparatus and a method of controlling the electronic apparatus are provided. The electronic apparatus includes a display configured to display an image, and a controller electrically connected to the display. The controller is configured to control the display to display a region of the image, using a first reproducing method, identify either one or both of a first event in which a control signal is externally received and a second event occurring based on a result of analyzing a feature of the region of the image, and change the first reproducing method to a second reproducing method, based on either one or both of the first event and the second event being identified.

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

Abstract: A server according to the disclosure includes a communicator configured to communicate with a plurality of display apparatuses; and a controller configured to produce a plurality of split images corresponding to individual view angles of screens of the plurality of display apparatuses from each frame of a 360-degree image including a plurality of frames, transmit the plurality of split images according to the frames to the corresponding display apparatus, and control the communicator to transmit a split image updated corresponding to change in the individual view angle based on movement of a view point.

Abstract: An electronic apparatus is provided. The apparatus includes a storage and a processor configured to convert an original image to a spherical image, to acquire a plurality of two-dimensional (2D) images corresponding to a respective plurality of points on the spherical image by projecting the spherical image onto a plane with reference to the respective plurality of points on the spherical image, and to store the acquired 2D images in the storage.

Abstract: An image display apparatus may include a display, and a processor configured to generate a viewpoint guide map based on at least one of viewing-history data of the 360-degree image and characteristics of the 360-degree image, generate a list of recommended viewpoints for the 360-degree image based on the viewpoint guide map, and control the display to display an image included in the 360-degree image corresponding to a viewpoint from among the list of recommended viewpoints.

Abstract: Provided are an electronic apparatus and a method of operating the same. The electronic apparatus includes a display and a controller electrically connected to the display, wherein the controller identifies at least one of aspect ratio information of the display, a type of the display, and curvature information of the display, determines an angle of view of a 360 degree image to be displayed on the display based on at least one of the identified aspect ratio information of the display, and type of the display, and curvature information of the display, and controls the display to display a region of the 360 degree image according to the determined angle of view.

Abstract: A copolymer includes (A) an aromatic vinyl-based monomer, (B) an unsaturated nitrile-based monomer, (C) a cross-linkable siloxane compound, and (D) an N-substituted maleimide-based monomer to realize a synergistic effect of matting characteristics and heat resistance properties. A thermoplastic resin composition including the copolymer, and a molded article including the thermoplastic resin composition are provided.

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

Abstract: A display apparatus is provided. The display apparatus includes: an image processor configured to process an image signal; a display; and a processor configured to control the image processor to produce, from a 360-degree image, a plurality of split images to be arranged along a circumference within a predetermined region that includes a great circle of a sphere shape being mapped, based on a viewpoint corresponding to a user input, the plurality of split images corresponding to a plurality of screens, and to produce a projection image to be displayed on the display based on the viewpoint from the split image of the screen that corresponds to the display apparatus from among the plurality of split images.

Abstract: An electronic apparatus is provided. The apparatus includes a storage and a processor configured to convert an original image to a spherical image, to acquire a plurality of two-dimensional (2D) images corresponding to a respective plurality of points on the spherical image by projecting the spherical image onto a plane with reference to the respective plurality of points on the spherical image, and to store the acquired 2D images in the storage.

Abstract: A display apparatus is provided. The display apparatus includes a storage that stores store a Virtual Reality (VR) image and a processor that converts the VR image into a spherical VR image, generates a planar VR image corresponding to an area of the spherical VR image, and controls a display to display the planar VR image.