Abstract: An image decoding method is disclosed in the present specification. An image decoding method according to the present invention may comprise deriving a candidate list for inter-prediction of a current block, deriving motion information of the current block by using the candidate list, deriving a cumulative coding information candidate by using the motion information of the current block, inserting the derived cumulative coding information candidate into a cumulative coding information candidate list and updating the candidate list by using the cumulative coding information candidate list, wherein the updated candidate list is used for inter-prediction of a block to be decoded after the current block.

Abstract: A face information registration method performed by a terminal may comprise: acquiring customer information corresponding to a user; extracting biometric feature data from a face image of the user; acquiring card information of the user; requesting user registration while mapping the customer information, the biometric feature data, and the card information and transmitting same to an authentication server; and in response to successful registration of the customer information, the biometric feature data, and the card information in the authentication server, receiving a result of the registration from the authentication sever.

Abstract: A display device including: a display panel including a first area, a second area spaced apart from the first area, and a bent third area between the first and second areas; a first support film coupled to a bottom surface of the display panel and overlapping the first area; and a second support film coupled to the bottom surface of the display panel, overlapping the second area, and spaced apart from the first support film by a gap, the gap overlapping the third area, a top surface of the first support film facing the display panel and an inner side of the first support film form a first angle, a top surface of the second support film facing the display panel and an inner side of the second support film form a second angle, which is greater than the first angle, and the first support film includes a protruding pattern.

Abstract: An image processing system includes: an image signal processor including a first neural network, and processing an input image by using the first neural network so as to generate a post-processed image; and a discriminator including a second neural network, and receiving a target image and the post-processed image, and discriminating the target image and the post-processed image into a real image and a fake image by using the second neural network, wherein the second neural network is trained to discriminate the target image as a real image and to discriminate the post-processed image as a fake image, and the first neural network is trained in such a manner that the post-processed image is discriminated as a real image by the second neural network.

Abstract: A battery module includes a battery assembly including a plurality of sub-packing units, the plurality of sub-packing units respectively including a cell housing, at least one battery cell accommodated in an internal space of the cell housing, and at least one vent hole disposed in the cell housing and connecting the internal space to an outside of the cell housing, and a flame blocking structure coupled to the battery assembly, and including an inlet hole connected to the vent hole, an inner chamber communicating with the inlet hole, an outlet hole communicating with the inner chamber and the outside, and at least one partition wall protruding into the inner chamber.

Abstract: A spectroscopic analysis method having improved accuracy and correlation, a method for fabricating a semiconductor device using the same, and a substrate process system using the same are provided. The spectroscopic analysis method includes receiving plasma light emitted from plasma to generate an emission spectrum, detecting n (here, n is a natural number of 2 or more) peak wavelengths from the emission spectrum, generating a plurality of correlation factor time series from correlation factors between the peak wavelengths, filtering the plurality of correlation factor time series, and analyzing the plasma, using the filtered correlation factor time series.

Abstract: A display device includes a window including a planar portion and a bending portion that is bent from the planar portion. A display module is disposed below the window. The display module includes a central portion overlapping the planar portion and an edge portion overlapping the bending portion. An adhesive member including an adhesive layer is disposed between the window and the display module. A lubrication layer overlaps at least a portion of the adhesive layer.

Abstract: A method and an apparatus for detecting a defect based on a phased pass/fail determination are disclosed. According to at least one aspect of the present disclosure, a method comprising: a process of acquiring a product image which is an image of the product; a first determination process of inputting the product image into a first determination model to perform a pass/fail determination for the product; and a second determination process of inputting the product image into a second determination model to perform a pass/fail determination for the product when the product is determined to be undeterminable as a result of the pass/fail determination of the first determination process.

Abstract: The present disclosure relates to a method and apparatus for training artificial intelligence based on an episodic memory. According to an embodiment of the present disclosure, a method for training artificial intelligence based on an episodic memory may include: constructing an episodic memory by using a feature vector of a training dataset stored in a full memory; obtaining output data by inputting query data into an artificial intelligence model; deriving a similarity between the output data and a feature vector in the constructed episodic memory; and deriving an episode loss function based on the similarity.

Abstract: A method and apparatus use a geometric modified image for video encoding/decoding. The encoding method may include: generating a geometric modified reference picture by geometrically modifying a reference picture; generating a prediction block of a current block within an encoding target picture by performing inter prediction by referencing the reference picture or the geometrically modified reference picture; and encoding inter-prediction information of the current block.

Abstract: A mobile robot, capable of communicating with neighboring devices in a 5G communication environment and capable of efficient cleaning via machine learning based on such communication, comprises a main body configured to move in the movement space, a driving unit mounted on the main body to move the main body, a receiving unit configured to receive moving history information of a user robot that has been moved by a user in the movement space, a memory in which a computer-readable program and map information of the movement space are stored, and a control unit configured to communicate with the receiving unit, the memory, and the driving unit to control the main body, wherein the control unit establishes a moving area of the mobile robot based on the moving history information of the user robot received by the receiving unit.

Abstract: A battery rack includes: a housing; a module unit provided in the housing, including a plurality of battery cells, and having at least one vent hole; and a cooling unit provided to face the vent hole in the housing, and including a cooling line in which a coolant is provided, wherein the cooling line is provided so that at least a portion of an outer periphery thereof is melted by heat generated from the module unit to supply the coolant toward the vent hole.

Abstract: An apparatus for maintaining spacing of a cutout portion of lamina used for patient-customized laminoplasty is proposed. The apparatus for maintaining spacing of a cutout portion of lamina used for patient-customized laminoplasty includes a spacer configured to be fitted in a cutout space secured by opening in order to open a cutout portion and expand a spinal canal after a portion of a lamina of a vertebra is cut, and configured to keep the spinal canal expanded, and a plate coupled to the spacer and fixed to an outer side of the lamina, thereby preventing movement of the spacer.

Abstract: A bit line sense amplifier includes: a first inverter having an input terminal connected to a first sensing node and an output terminal connected to a second inner bit line; a second inverter having an input terminal connected to a second sensing node and an output terminal connected to a first inner bit line; a first capacitor connected between the first sensing node and the first inner bit line; a second capacitor connected between the second sensing node and the second inner bit line; an isolation unit configured to cut off a connection between the first inner bit line and a second bit line; and an offset cancellation unit configured to connect the first sensing node to the second inner bit line, the first inner bit line to the first bit line, the second sensing node to the first inner bit line, and the second inner bit line to the second bit line.

Abstract: There is provided a method of decoding an image, the method comprising: decoding information for motion information prediction of a current block from a bitstream, predicting motion information of the current block based on the information, refining motion information of the current block by using the decoded information and the predicted motion information of the current block and reconstructing the current block based on the refined motion information of the current block.

Abstract: A method of acquiring probability information of a gacha system includes: acquiring, by a first user terminal, second gacha event information that is information about a gacha event occurring in a second user terminal; acquiring, by the first user terminal, third gacha event information that is information about a gacha event occurring in a third user terminal; acquiring probability information of the gacha system based on the acquired second gacha event information and third gacha event information; and displaying the acquired probability information of the gacha system.

Abstract: The present disclosure in some embodiments provides artificial intelligence or AI-based document classification apparatus and method for providing, based on a hierarchical attention network (HAN) and a semantic analysis technique, an evaluation of a document, and an explainable basis or supporting data for the evaluation, thereby generating an evaluation index for the document.

Abstract: The present invention relates to a secondary battery and an apparatus and method for measuring a dimension of the secondary battery. The secondary battery according to the present invention comprises: an electrode assembly in which an electrode and a separator are alternately laminated to be combined with each other; a pouch accommodating the electrode assembly therein; and a fluorescent reference marker applied to a portion of an outer surface of the pouch and comprising a fluorescent material, wherein the fluorescent reference marker emits fluorescence when an electromagnetic wave is irradiated so that the fluorescent reference marker serves as a reference point for measuring a dimension of the secondary battery.

Abstract: An electronic apparatus includes: an image sensor for acquiring an image including normal pixel values that are sensed during a first exposure time and short exposure pixel values that are sensed during a second exposure time that is shorter than the first exposure time; and a processor configured to acquire flag information that indicates that a selected region, among a plurality of regions of the image, is one of a motion region and a normal region by using an exposure ratio of the first exposure time and the second exposure time and by using a short exposure pixel value and normal pixel values, which are included in the selected region, and configured to output a restoration image including a restoration pixel value that is corrected from the short exposure pixel value that is included in the selected region, based on the flag information.

Abstract: An image sensing device includes an image sensor including at least one pixel including a plurality of color channels and an image processor for processing an input image, based on brightness intensity values of the plurality of color channels. The image processor includes: a transmission map generator for generating color channel transmission maps including transmission values that are obtained by respectively converting brightness intensity values of the plurality of color channels, and generating a target transmission map including target transmission values that are obtained by multiplying transmission values among the transmission values that correspond to color channels; a white pixel detector for determining target pixels that are included in a white area, based on the target transmission map; and a white balance adjuster for adjusting white balance, based on average brightness intensity values of respective color channels.