Samsung Electronics Co., Ltd.

Sungkyunkwan University

Hyundai Motor Company

Dongwook Lee

Hyeonjin Shin

Minsu Seol

Sangwon Kim

Seongjun Park

Byung In Yoo

Changyong Son

Seohyung Lee

Changbeom Park

Sunil Kim

Yunseong Lee

Jaechul Park

Changbum Lee

Jaeho Lee

Jaejoon Han

Jinseong Heo

Sanghyun Jo

Jinwoo Son

Eunkyu Lee

Kiyoung Lee

Dongho Kim

Chang Kyu Choi

Seungwon Lee

Duhyun Lee

Changseok Lee

Keunwook Shin

Dong Chul Park

Jaewoo Lee

Seunggeol Nam

Seongjun Jeong

Alum Jung

Jiman Kwon

Jaehyeon Park

Sangil Jung

Daehyun Cho

Changsik Song

Seungwook Kim

Wonju Lee

Jaehyoung Yoo

Hakryoul Kim

Hyejin Cho

Juhyen Lee

Geonhee Back

Hyunjae Song

Changho Lee

Taewoo Kim

Hyunjeong Lee

Byungkyu Lee

Hyunseok Yu

Sang Il Lee

Ju Hwan Song

Byoungkug Kim

Youngjun Choi

Kangho Lee

Jongman Park

Jahoo Koo

Changin Choi

Seonghyeon Kim

Gangminh Lee

Jeongtaek Lee

Hongjung Son

Youngjoo Jung

JaeWoo Lee

Kyoungyoup Park

Jooyong Sin

Jiseop Song

Kapje Sung

Daeul Park

Jonghoon Yoon

Jihan Yun

Jaemin Ko

Dongcheol Jeong

Dae Huyn Ji

A method of generating a hyperlapse video includes: comparing a first reference point of a first image and a corresponding second reference point of a second image; based on the comparing, displaying a first user interface for matching the first reference point and second reference point; and determining whether to perform automatic shooting for the hyperlapse video based on whether the first reference point and the second reference point match.

Method and apparatus with hyperlapse video generation

A method with self-attention includes: obtaining a three-dimensional (3D) feature map; generating 3D query data and 3D key data by performing a convolution operation based on the 3D feature map; generating two-dimensional (2D) vertical data based on a vertical projection of the 3D query data and the 3D key data; generating 2D horizontal data based on a horizontal projection of the 3D query data and the 3D key data; determining an intermediate attention result through a multiplication based on the 2D vertical data and the 2D horizontal data; and determining a final attention result through a multiplication based on the intermediate attention result and the 3D feature map.

Method and apparatus with self-attention-based image recognition

A processor-implemented method with target object tracking includes: setting a search area for a target object included in an input image based on a position of a first target box in a template image; selecting a network path from a plurality of network paths of a neural network model according to a resizing ratio of a size of another image that is input to the neural network model to a size of the search area; and tracking the target object by estimating a position of a second target box corresponding to the target object in the input image according to the selected network path.

Method and apparatus with target object tracking

A processor-implemented method with object tracking includes: performing, using a first template, forward object tracking on first image frames in a first sequence group; determining a template candidate of a second template for second image frames in a second sequence group; performing backward object tracking on the first image frames using the template candidate; determining a confidence of the template candidate using a result of comparing a first tracking result determined by the forward object tracking performed on the first image frames and a second tracking result determined by the backward object tracking performed on the first image frames; determining the second template based on the confidence of the template candidate; and performing forward object tracking on the second image frames using the second template.

Method and apparatus with object tracking

According to an aspect of the inventive concept, an electronic device includes a transmitter including a plurality of antennas, and a communication processor for calculating a total exposure ratio (TER) value of each of the plurality of antennas, wherein the communication processor includes an antenna index buffer for storing a used antenna index, which is an index of one or more used antennas from among the plurality of antennas used in each window, a used power buffer for storing used power of an antenna corresponding to the used antenna index, and a controller configured to calculate the TER value based on the used antenna index, the used power, and an influence matrix.

Electronic device and operating method of electronic device

Provided is a method and apparatus with neural network operation. The method includes generating a first intermediate operation result by performing a first-order partial operation of a neural network layer on a first input line of a first area of a frame, generating a second intermediate operation result by performing another first-order partial operation of the neural network layer on a second input line of the first area, and generating an objective operation result of the neural network layer with respect to the first area based on a second-order partial operation performed on the first intermediate operation result and the second intermediate operation result.

Method and apparatus with neural network operation

A method and apparatus for object tracking are provided, where the object tracking method includes determining box information of candidate boxes in a current image frame and similarity scores of the candidate boxes based on including a search region of the current image frame with a template image corresponding to a target object, adjusting the similarity scores of the candidate boxes using a distractor map including distractor information of a previous image frame, determining a target box corresponding to the target object and a distractor box corresponding to a distractor of the target object from the candidate boxes based on the adjusted similarity scores, and updating the distractor map based on distractor information of the current image frame according to the distractor box.

A method of controlling a memory and an electronic device performing the method are provided. The electronic device includes a memory configured to store instructions executable by the processor; and at least one processor configured to execute the instructions to: determine a use state of the electronic device corresponding to an available area of the memory, determine a temperature of the electronic device, determine a memory parameter based on the use state and the temperature, and convert a used area of the memory into the available area based on the memory parameter.

Electronic device performing method of controlling memory based on temperature and available area of the memory

Provided is an apparatus and method for improving the entry speed of a large-memory consuming application in an electric device which detect an execution of an application, check if the application is a large-memory consuming application which uses a large amount of memory, and if the application is the large-memory consuming application, execute pre-process thread reclaim, select a process corresponding to a reclaiming target among processes currently resident in the memory, reclaim part of the memory being used by the selected process without terminating the selected process, and thereby improve the entry speed of a large-memory consuming application.

Apparatus and method for enhancing launch speed of large-memory consuming app

Provided are a functionalized polycyclic aromatic hydrocarbon compound and a light-emitting device including the same. The functionalized polycyclic aromatic hydrocarbon compound is structurally stable, and exhibits high light-emission characteristics since aggregation caused by π-π stacking is inhibited, and thus may have high efficiency and long lifespan characteristics.

Functionalized polycyclic aromatic hydrocarbon compound and light-emitting device including the same

A method and apparatus for processing an image based on partial images. The method includes extracting a feature of a current partial processing region of an input image frame by inputting pixel data of the current partial processing region into a convolutional neural network (CNN), updating a hidden state of a recurrent neural network (RNN) for a context between the current partial processing region and at least one previous partial processing region by inputting the extracted feature into the RNN, and generating an image processing result for the input image frame based on the updated hidden state.

Method and apparatus for processing image based on partial images

Disclosed is a method and apparatus for adaptive tracking of a target object. The method includes method of tracking an object, the method including estimating a dynamic characteristic of an object in an input image based on frames of the input image, determining a size of a crop region for a current frame of the input image based on the dynamic characteristic of the object, generating a cropped image by cropping the current frame based on the size of the crop region, and generating a result of tracking the object for the current frame using the cropped image.

Method and apparatus with adaptive object tracking

A system includes: an image sensor configured to acquire an image; an image processor configured to generate a quantized image based on the acquired image using a trained quantization filter; and an output interface configured to output the quantized image.

Method and apparatus with quantized image generation

An electronic device comprises: a memory management module; a processor operatively connected to the memory management module; and a memory controlled by the memory management module and operatively connected to the processor. The memory is configured to store instructions which, when executed, cause the processor to: execute at least one process, identify a rate at which the at least one process is terminated, based on a preconfigured first cycle, determine a number of times the identified rate exceeds a first threshold value, and based on a determination that the number of times the identified rate exceeds the first threshold value is greater than a second threshold value, reboot the electronic device.

Memory management method and electronic device

A processor-implemented neural network method includes: obtaining a first weight kernel of a weight model and pruning information of the first weight kernel; determining, based on the pruning information, a processing range of an input feature map for each weight element vector of the first weight kernel; performing a convolution operation between the input feature map and the first weight kernel based on the determined processing range; and generating an output feature map of a neural network layer based on an operation result of the convolution operation.

Method and apparatus with neural network operation processing

Growing community of inventors

Suwon-si, South Korea

Dongwook Lee