Abstract: According to the present invention, an adaptive scheme is applied to an image encoding apparatus that includes an inter-predictor, an intra-predictor, a transformer, a quantizer, an inverse quantizer, and an inverse transformer, wherein input images are classified into two or more different categories, and two or more modules from among the inter-predictor, the intra-predictor, the transformer, the quantizer, and the inverse quantizer are implemented to perform respective operations in different schemes according to the category to which an input image belongs. Thus, the invention has the advantage of efficiently encoding an image without the loss of important information as compared to a conventional image encoding apparatus which adopts a packaged scheme.

Abstract: An image sensing device is provided to include a pixel array having a plurality of pixels arranged in a matrix shape. Each of the pixels includes: a control node configured to generate a hole current in a substrate; a detection node configured to capture photocharge migrated by the hole current, formed in a shape whose at least part is partially open, and disposed to surround the control node, and a low resistance region including a dielectric layer formed in the substrate, and disposed in the opening on of the detection node. The low resistance region includes an inner low resistance region disposed between the control node and the center of the pixel.

Abstract: An apparatus for creating a virtual world includes a processor and a memory connected to the processor, in which the memory stores program instructions executed by the processor so as to receive an image of a real space through a device having a stereo camera, collect mesh data for the real space and an object existing in the real space through the image, determine coordinates for first edges of the real space from the mesh data for the real space, select one of a plurality of second edges based on an area of a virtual space defined by each of the plurality of second edges facing a predetermined direction, when there are more first edges of the real space than edges of a polygon preset for the real space, and output a virtual space defined by some of the first edges and the selected one second edge and a virtual object corresponding to the real object recognized in the real space.

Abstract: A method and an electronic device for translating a speech signal between a first language and a second language with minimized translation delay by translating fewer than all words of the speech signal according to a level of understanding of the second language by a user that receives the translation.

Abstract: A method and apparatus for training a fake image discriminative model according to an embodiment of the present disclosure includes generating one or more fake images for a real image by selecting one or more encoding layers and one or more decoding layers from a generator network of an autoencoder structure, generating a training image set based on the one or more fake images, and training a classifier for discriminating a fake image by using the training image set.

Abstract: A method for training a deep neural network according to an embodiment includes training a deep neural network model using a first data set including a plurality of labeled data and a second data set including a plurality of unlabeled data, assigning a ground-truth label value to some of the plurality of unlabeled data, updating the first data set and the second data set such that the data to which the ground-truth label value is assigned is included in the first data set, and further training the deep neural network model using the updated first data set and the updated second data set.

Abstract: Disclosed herein are an object recognition apparatus and method based on environment matching. The object recognition apparatus includes memory for storing at least one program, and a processor for executing the program, wherein the program performs extracting at least one key frame from a video that is input in real time, determining a similarity between the key frame extracted from the input video and each of videos used as training data of prestored multiple recognition models, based on a pretrained similarity-matching network, and selecting a recognition model pretrained with a video having a maximal similarity to the key frame extracted from the input video, preprocessing the input video such that at least one of color and size of a video used as training data of an initial model is similar to that of the input video, and recognizing the preprocessed video based on the initial model.

Abstract: A machine learning apparatus according to an embodiment includes a feature extractor configured to extract features from an object region of an image, a label processor configured to create sentence label embeddings from a sentence label corresponding to the object region, a first training data creator to extract first sub-features from a plurality of first sub-regions created by partitioning the object region, add the sentence label embeddings to the extracted first sub-features, and add the first sub-features added with the sentence label embeddings to the features of the object region, a second training data creator to extract a plurality of second sub-regions along a bounding surface of the object region, create an attention matrix from the second sub-regions, and create a training data by applying the attention matrix to the features of the object region, and a trainer to train an object detection model using the training data.

Abstract: A method for predicting a value for unlabeled data according to an embodiment is executed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors. The method includes training a relation estimation model for predicting a label for labeled data based on a relation between respective predicted values of a plurality of pre-trained predictive models for the labeled data and a target model and obtaining a predicted value for unlabeled data based on the relation estimation model.

Abstract: An apparatus for deep fake image discrimination according to an embodiment includes an interface unit configured to receive image data and a classifier configured to determine whether the image data input through the interface unit is a deep fake image, and the classifier is trained to determine a deep fake image based on a synthetic image generated by swapping a portion of a real image with a fake image generated by self-replicating the real image.

Abstract: A compound of Chemical Formula 1, and an organic photoelectric device, an image sensor, and an electronic device including the same are disclosed: In Chemical Formula 1, each substituent is the same as described in the detailed description.

Abstract: Provided are an optimization system and method of a deep learning model. According to example embodiments, by optimizing the structure of the deep learning model appropriately for a target dataset without fixing the structure of the deep learning model, it is possible to generate a model structure capable of having high performance on the target dataset and also saving resources.

Abstract: An apparatus for classifying fake images according to an embodiment of the present disclosure includes an artifact remover configured to receive an input image to generate an artifact-removed image from which artifacts are removed, an artifact image generator configured to generate an artifact image by using a difference between the input image and the artifact removal image, and a determiner configured to determine whether the artifact image is a real image or a fake image by receiving the artifact image.

Abstract: An image processing apparatus includes a superpixel extractor configured to extract a plurality of superpixels from an input original image, a backbone network including N feature extracting layers (here, N is a natural number of two or more) which divide the input original image into grids including a plurality of regions and generate an output value including a feature value for each of the divided regions, and a superpixel pooling layer configured to generate a superpixel feature value corresponding to each of the plurality of superpixels using a first output value to an Nth output value output from each of the N feature extracting layers.

Abstract: A thrust supporting apparatus includes: a thrust runner configured to rotate integrally with a shaft; and a foil thrust bearing supporting an axial load of the shaft, the axial load being transmitted from the thrust runner. The foil thrust bearing includes a top foil facing a first surface of the thrust runner, and the thrust runner comprises first one or more grooves formed on the first surface.

Abstract: An IC communication device according to an embodiment of the present invention includes: a plurality of sensing ICs including a first sensing IC to an N-th sensing IC arranged to be adjacent (N is an integer equal to or greater than 2); and a controller connected to the first sensing IC, wherein when the controller in a sleep mode receives a wakeup signal and transmits the wakeup signal to the first sensing IC, the wakeup signal is transmitted in two directions to two sensing ICs, from the first sensing IC to the N-th sensing IC, arranged to be adjacent.

Abstract: An air foil bearing includes a bearing housing having a cylindrical shape that forms an accommodation space in a middle thereof for a rotating shaft, rotor, or journal; a first foil including a plurality of bump foils, which are arranged along an inner wall surface of the accommodation space of the bearing housing; and a second foil including a plurality of top foils, which are arranged in a circumferential direction along an inner circumference of the bearing housing to correspond to the plurality of bump foils and to support the rotating shaft, rotor, or journal. A portion of at least one of the plurality of top foils of the second foil is thicker than the other top foils of the plurality of top foils.

Abstract: A radial force support apparatus includes: a shaft coupled to an impeller and configured to rotate together with the impeller; and a foil radial bearing supporting the shaft. The foil radial bearing includes a top foil disposed on an inner circumferential surface of the foil radial bearing and facing at least a part of an outer circumferential surface of the shaft, and the shaft facing the top foil includes at least one groove provided on the outer circumferential surface of the shaft.

Abstract: A compound of Chemical Formula 1, and an organic photoelectric device, an image sensor, and an electronic device including the same are disclosed: In Chemical Formula 1, each substituent is the same as described in the detailed description.

Abstract: The fault diagnosis circuit includes a first line including a first resistor, having one end connected to the positive (+) terminal of a battery, and having the other end connected to a first input unit of an analog to digital converter (ADC); a second line including a second resistor, having one end connected to the positive (+) terminal of the battery, and having the other end connected to a first input unit of a comparator; and a third line including a third resistor, having one end connected to the negative (?) terminal of the battery, having a first other end connected to a second input unit of the ADC, and having a second other end connected to a second input unit of the comparator. A fault in a battery management system can be efficiently diagnosed using a smaller number of elements.