Abstract: A method and apparatus for face recognition robust to an alignment of the face comprising: estimating prior information of a facial shape from an input image cropped from an image including a face using the first deep neural network (DNN); extracting feature information of facial appearance from the input image by using a second DNN; training, by using a face image decoder based on the prior information and the feature information, the face recognition apparatus; and extracting, from a test image, facial shape-aware features in the inference step by using the trained second DNN.

Abstract: Provided are a tag, interrogator, and system for performing position measurement based on backscatter in a millimeter-wave band. In detail, provided is a tag including a planar Van Atta array antenna, a frequency-shift keying (FSK) modulator connected to the planar Van Atta array antenna, and at least one bias circuit connected to the FSK modulator, wherein the FSK modulator is configured to, based on an interrogation signal being received by the planar Van Atta array antenna, modulate the interrogation signal based on a control signal supplied through the at least one bias circuit, and output the modulated interrogation signal in a direction from which the interrogation signal is received, through the planar Van Atta array antenna.

Abstract: Provided is an apparatus for online action detection, the apparatus including a feature extraction unit configured to extract a chunk-level feature of a video chunk sequence of a streaming video, a filtering unit configured to perform filtering on the chunk-level feature, and an action classification unit configured to classify an action class using the filtered chunk-level feature.

Abstract: The present disclosure relates to a low-resolution face recognition device, which includes a high-resolution face image inputter; a low-resolution face image inputter; a high-resolution face feature extractor configured to extract a high-resolution face feature by using high-resolution and low-resolution face images; a face quality feature extractor configured to extract face quality features by using the high-resolution and low-resolution face images; a feature combiner configured to detect the high-resolution and low-resolution face features by concatenating the high-resolution face feature and the face quality feature; a feature adaptation network configured to extract a high-resolution face feature map and a low-resolution face feature map by using the detected high-resolution and low-resolution face features, respectively; and a consistency meter configured to determine a face ID by measuring consistency of a face feature map by using the extracted high-resolution and low-resolution face feature maps.

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: Provided is a communication device. The communication device includes an interrogator configured to output an interrogation signal in which unit chirp signals that vary from a first frequency to a second frequency are continuous, and backscatter tags configured to receive the interrogation signal and each provide a tag signal formed by frequency modulation on the interrogation signal, wherein the interrogator receives the tag signals and demodulates the tag signals.

Abstract: An electronic device according to an embodiment disclosed herein may include a memory including at least one instruction and a processor. By executing the at least one instruction, the processor may check feature information corresponding to a video and including at least one of an appearance-related feature value and a motion-related feature value from the video, calculate at least one of a starting score related to a starting point of an action instance, an ending score related to an ending point of an action instance, and a relatedness score between action instances on the basis of the feature information corresponding to the video, the action instances being included in the video, and generate an action proposal included in the video on the basis of the at least one score.

Abstract: A method and apparatus for face recognition robust to an alignment of the face comprising: estimating prior information of a facial shape from an input image cropped from an image including a face using the first deep neural network (DNN); extracting feature information of facial appearance from the input image by using a second DNN; training, by using a face image decoder based on the prior information and the feature information, the face recognition apparatus; and extracting, from a test image, facial shape-aware features in the inference step by using the trained second DNN.

Abstract: Provided is an apparatus for online action detection, the apparatus including a feature extraction unit configured to extract a chunk-level feature of a video chunk sequence of a streaming video, a filtering unit configured to perform filtering on the chunk-level feature, and an action classification unit configured to classify an action class using the filtered chunk-level feature.

Abstract: An electronic device according to an embodiment disclosed herein may include a memory including at least one instruction and a processor. By executing the at least one instruction, the processor may check feature information corresponding to a video and including at least one of an appearance-related feature value and a motion-related feature value from the video, calculate at least one of a starting score related to a starting point of an action instance, an ending score related to an ending point of an action instance, and a relatedness score between action instances on the basis of the feature information corresponding to the video, the action instances being included in the video, and generate an action proposal included in the video on the basis of the at least one score.