Samsung Electronics Co., Ltd.

Korea Advanced Institute of Science and Technology

Insoo Kim

Jaejoon Han

Seungju Han

Jiwon Baek

Seong-Jin Park

Kyuhong Kim

Yusuf A Bhagat

Sean D Lai

Chang Kyu Choi

Zhouyue Pi

Hana Lee

Daquan Huang

Jungsuek Oh

Ju Hwan Song

Xu Zhu

Sung Ju Hwang

Johnny T Homer

Dohwan Lee

Ying Dong

Kikyung Kim

An image recognition method includes: receiving an input image of a first quality; extracting an input feature of a second quality of the input image from the input image by inputting the input image to an encoding model in an image recognizing model; and generating a recognition result for the input image based on the input feature.

Method and apparatus with image recognition

A processor-implemented radar data recognition method including generating a plurality of pieces of input data, with respectively different dimension configurations, based on radar data of an object; and outputting a recognition result of the object based on the generated plurality of pieces of input data using a recognition model.

Method and apparatus with radar data recognition

A method with access authority management includes: receiving an input image comprising a region of at least one portion of a body of a user; determining whether the user corresponds to multiple users or a single user using the region of the at least one portion of the body; performing a verification for the user based on a face region in the input image, in response to the determination that the user is the single user; determining whether the input image is a real image or a spoofed image based on whether the verification is successful; and allowing an access authority to a system to the user, in response to the determination that the input image is the real image.

Method and apparatus with access authority management

A processor-implemented neural network method includes: extracting, by a feature extractor of a neural network, a plurality of training feature vectors corresponding to a plurality of training class data of each of a plurality of classes including a first class and a second class; determining, by a feature sample generator of the neural network, an additional feature vector of the second class based on a mean vector and a variation vector of the plurality of training feature vectors of each of the first class and the second class; and training a class vector of the second class included in a classifier of the neural network based on the additional feature vector and the plurality of training feature vectors of the second class.

Method and apparatus with neural network meta-training and class vector training

A processor-implemented image processing method and apparatus are provided. The image processing method includes receiving an input image and rotation information associated with the input image, generating a feature vector of the input image based on pose information corresponding to the input image, generating an assistant feature vector which represents a target component according to a pose corresponding to the rotation information, based on the feature vector, the pose information, and the rotation information, and generating a target image which has the pose corresponding to the rotation information based on the feature vector and the assistant feature vector.

Image processing method and apparatus, and image processing training method

A processor-implemented facial image generating method includes: determining a first feature vector associated with a pose and a second feature vector associated with an identity by encoding an input image including a face; determining a flipped first feature vector by flipping the first feature vector with respect to an axis in a corresponding space; determining an assistant feature vector based on the flipped first feature vector and rotation information corresponding to the input image; determining a final feature vector based on the first feature vector and the assistant feature vector; and generating an output image including a rotated face by decoding the final feature vector and the second feature vector based on the rotation information.

Method and apparatus with facial image generating

A processor-implemented radar data recognition method includes: generating a plurality of pieces of input data, with respectively different dimension configurations, based on radar data of an object; and outputting a recognition result of the object based on the generated plurality of pieces of input data using a recognition model.

A data recognition method includes: extracting a feature map from input data based on a feature extraction layer of a data recognition model; pooling component vectors from the feature map based on a pooling layer of the data recognition model; and generating an embedding vector by recombining the component vectors based on a combination layer of the data recognition model.

Data recognition apparatus and method, and training apparatus and method

A speaker authentication method and apparatus may extract input speaker features corresponding to a plurality of frames of an input speech of an object, estimate discriminable speaker sections corresponding to the plurality of frames, and dynamically match the input speaker features to pre-enrolled enrolled speaker features based on the discriminable speaker section.

Method and apparatus with speaker authentication and/or training

A processor-implemented neural network method includes: determining, using a neural network, a feature vector based on a training image of a first class among a plurality of classes; determining, using the neural network, plural feature angles between the feature vector and class vectors of other classes among the plurality of classes; determining a margin based on a class angle between a first class vector of the first class and a second class vector of a second class, among the class vectors, and a feature angle between the feature vector and the first class vector; determining a loss value using a loss function including an angle with the margin applied to the feature angle and the plural feature angles; and training the neural network by updating, based on the loss value, either one or both of one or more parameters of the neural network and one or more of the class vectors.

Method and apparatus with authentication and neural network training

A method implemented by a device to measure a bodily parameter includes transmitting, by a transmit (Tx) antenna of an antenna pair, a first radar pulse to a receive (Rx) antenna of the antenna pair. The method also includes receiving, by the receive (Rx) antenna, the first radar pulse. The first radar pulse travels through a radar target between the Tx antenna and the Rx antenna. The method further includes transmitting, by the Tx antenna, a second radar pulse to the Rx antenna. In addition the method includes receiving, by the Rx antenna, the second radar pulse, wherein the second radar pulse travels through the radar target between the Tx antenna and the Rx antenna. The method also includes determining a bodily parameter within the radar target as a function of the transmission and the reception of the first radar pulse and the second radar pulse.

RF doppler bio-signal sensor for continuous heart rate variability and blood pressure monitoring

A method and apparatus correcting errors associated with timing offsets in radiofrequency coils. The method and apparatus include a memory element and a controller. The controller is configured to execute a set of instructions to receive data of a plurality of signals, the plurality of signals comprising at least one projection echo. The controller is also configured to identify a plurality of offsets of the plurality of signals based on the at least one projection echo. The controller is also configured to apply the plurality of offsets to a k-space of the plurality of signals.

Growing community of inventors

Seongnam-si, South Korea

Insoo Kim