Seoul National University

Samsung Electronics Co., Ltd.

Samsung Electro-mechanics Co., Ltd.

Snur & Db Foundation

Byoung-Tak Zhang

Yu-Jung Heo

Sang-Woo Lee

Minsu Lee

Seongho Choi

Seong-Ho Choi

Seong-deok Lee

Seungchan Lee

Young-Jin Park

Sung-Su Kim

Kyu-sang Lee

Jung-bae Kim

Hyun-Jin Choi

Yeo-Jin Kim

Kyoung-whan Oh

Won-ki Park

Yun-Gyung Cheong

Jong-hwi Seo

Kibeom Kim

Young-Sang Choi

Ho-youl Lee

Yun-sun Nam

Seung-hak Choi

Young-il Jang

Taehyeong Kim

Kyung-Wha Park

Ha-nock Kwak

Min Whoo Lee

Seon Il Son

Kyoung-Woon On

Cheolho Han

You Won Jang

Ahjeong Seo

Yoonsung Kim

Wooyoung Kang

Byung-Chull Bae

Jaehyun Jun

Byung-ho Kang

Donghyun Kwak

Jang-min O

Min-Oh Heo

A target-oriented reinforcement learning method according to an embodiment includes: collecting data related to the target of reinforcement learning as target data in the process of performing the reinforcement learning; learning the collected target data as auxiliary learning for the reinforcement learning; and incorporating the results of the learning of the target data into the performance of the reinforcement learning.

Target-oriented reinforcement learning method and apparatus for performing the same

A method of constructing a transformer model for answering questions about a video story according to an embodiment includes: extracting feature vectors related to each character of a video from video data including vision data and subtitle data and question data for video questions and answers, and generating an input embedding using the feature vectors related to the character; and training a transformer model using the input embedding.

Method of constructing transformer model for answering questions about video story and computing apparatus for performing the same

There are proposed a method and system for information theory-based questioning for a goal-oriented dialog system. An information theory-based question provision system includes an approximate answer generation unit configured to generate an approximate answer by approximating the generation of an answer to a question by an answer module constituting a part of the goal-oriented dialog system; an intention inference unit configured to infer an intention value, which is the degree of proximity of the question to a goal, based on the answer of the answer module, and a question provision unit configured to provide a question to the answer module based on the intention value.

Method and system for information theory-based questioning for goal-oriented dialog system

A question answering method that is performed by a question answering apparatus includes: receiving a data set including video content and question-answer pairs; generating input time-series sequences from the video content of the input data set and also generating a question-answer time-series sequence from the question-answer pair of the input data set; calculating weights by associating the input time-series sequence with the question-answer time-series sequence and also calculating first result values by performing operations on the calculated weights and the input time-series sequences; calculating second result values by paying attention to portions of the input time-series sequences that are directly related to characters appearing in questions and answers; and calculating third result values by concatenating the time-series sequences, the first result values, the second result values, and Boolean flags and selecting a final answer based on the third result values.

Question answering apparatus and method

Disclosed herein are a visual story generation method and apparatus for generating a story from a plurality of images by using a deep learning network. The visual story generation method includes: extracting features from a plurality of respective images by using the first extraction unit of a deep learning network; generating the structure of a story based on the overall feature of the plurality of images by using the second extraction unit of the deep learning network; and generating the story by using outputs of the first and second extraction units.

Method and apparatus for generating story from plurality of images by using deep learning network

A query response method includes: dividing image frames, audio data and caption data included in video data of a data set on a per-shot basis based on the same single caption; extracting a shot feature vector by calculating the feature vectors of image frames, audio data and caption data included in each shot; extracting feature vectors of query data and a plurality of pieces of option data corresponding to the query data from each query-response pair included in the data set; calculating a video feature vector by inputting the shot feature vectors into a multilayer neural network, assigning an attention weight, calculated based on the feature vector of the query data, to output vectors of respective layers, and then summing the weighted output vectors; and selecting a final response from among the plurality of pieces of option data based on similarities between the video feature vector and option feature vectors.

Query response device and method

An equipment diagnosis system and method, which use abnormal data and normal data of equipment and accurately and effectively perform diagnosis on the equipment, are provided. The equipment diagnosis system includes a data acquisition unit to acquire time series data of equipment, a preprocessing unit convert the time series data into frequency data including a temporal component through a Fourier transform, a deep learning unit to perform deep learning through a convolution neural network (CNN) by using the frequency data, and a diagnosis unit to determine a state of the equipment to be a normal state or a breakdown state based on the deep learning.

Equipment diagnosis system and method based on deep learning

There are proposed an attention memory method and system for locating an object through visual dialogue. The attention memory system for identifying an object on an image includes: a control unit which generates a question for identifying a preset object on the image, derives an answer to the generated question, and identifies the preset object on the image based on the question and the answer; and memory which stores the image. The control unit generates the question by incorporating information about objects included in the image into the question, and updates the information about the objects based on the answer.

Attentive memory method and system for locating object through visual dialogue

The present invention relates to a wearable sensor-based automatic scheduling device and method. The wearable sensor-based automatic scheduling device includes: a typical schedule setting part that sets a typical schedule received from the user and specifying a specific event; an atypical schedule inferring part that infers an atypical schedule by analyzing the user's current location and the user's behavioral patterns occurring over a specific period of time in the past; and a schedule determining part that determines the schedule from this point on based on the typical schedule and the atypical schedule. Accordingly, the present invention may provide a technology that can predict the user's expected schedule in real time by taking into account both a typical schedule recorded in a scheduler and an atypical schedule mapped out based on daily behavioral patterns.

Wearable sensor-based automatic scheduling device and method

An apparatus for generating a probabilistic graphical model based on a time-space structure. The apparatus includes a first matrix generation unit configured to generate a first matrix having variables corresponding to stream data; a second matrix generation unit configured to classify the variables of the first matrix into either object variables that are objects of interest or input variables, acquire combination variables from multi-order combination of the input variables, and generate a second matrix using the acquired combination variables; and a model creation unit configured to create the probabilistic graphical model using the object variables of the first matrix and the combination variables of the second matrix.

Apparatus and method for generating probabilistic graphical model based on time-space structure

Provided are a photographing profile learning apparatus and method of a digital imaging device for recording a personal life history. The photographing profile learning method learns a user's photographing patterns by recommending at least one previous picture consistent with a user's photographing tendencies, using a recommendation function and a user profile based on a user feedback value and a compensation value, receiving user feedback regarding the recommended previous picture, and updating the user profile and the recommendation function according to the user feedback. Therefore, since photographing settings are performed according to a user's tendency and conditions, it is possible to maintain consistency between a currently photographed picture and previously photographed pictures and systematically produce a visual diary.

Apparatus and method for learning photographing profiles of digital imaging device for recording personal life history

A method and system for automatically extracting photography information is provided. The system for automatically extracting photography information includes an image input unit acquiring a preview image or a captured image as an input image, a photography information extraction unit extracting photography information of the input image, and a photography code generation unit generating a photography code indicating a user's photography pattern by using the extracted photography information.

Method and system for automatically extracting photography information

Provided are an apparatus and a method for coding genetic information. An aligning unit aligns sample genetic information, wild-type probe genetic information, and mutant-type probe genetic information, based on a mutation position. A code storage unit stores first orthogonal codes assigned to each of bases located at left and right base regions based on the mutation position and second orthogonal codes assigned to a base located at the mutation position. A coding unit creates first code strings and second code strings. The first code strings are created by assigning the first orthogonal codes, sequentially from left to right, to the bases that make the aligned genetic information and adding a flag that represents the presence or absence of a corresponding base on the genetic information to the assigned first orthogonal codes, and the second code strings are created by assigning the second orthogonal codes to the base located at the mutation position and adding a flag that represents the type of the sample genetic information to the assigned second orthogonal codes.

Apparatus and method for coding genetic information

Growing community of inventors

Seoul, South Korea

Byoung-Tak Zhang