Samsung Display Co., Ltd.

Hyundai Motor Company

Kia Corporation

Seoul National University

Inha University Research and Business Foundation

Kang Il Lee

Young Chan Kim

Byung Cheol Song

Jun Ho Choi

Gunhee Kim

Min Gyeong Jo

Wonsuk Yang

Youngjae Yu

Heeseung Yun

A method of providing an interface for visual question answering includes receiving 360-degree video data, acquiring a plurality of images corresponding to a plurality of fields of view (FOV) based on the 360-degree video data, identifying a plurality of objects included in the plurality of images and storing metadata regarding the plurality of objects, converting plane coordinates of each of the plurality of objects into spherical coordinates, classifying the plurality of objects into a plurality of lists, selecting a first object having a highest correct answer probability, comparing the spherical coordinates of the first object having the highest correct answer probability with the spherical coordinates of each of the remaining first objects, and removing a first object satisfying a preset condition among the remaining first objects from the plurality of images, and generating an interface for visual question answering.

Method and system of providing interface for visual question answering

Systems and methods for detecting eye information are described. According to one embodiment, a detecting device includes a determination unit, a generation unit, and a detection unit. The determination unit is configured to determine whether a user wears glasses from an input image by using a first neural network including a plurality of filters. The generation unit is configured to generate a face image in which the glasses are removed from the input image by using a learned generator when a glasses-wearing signal is received from the determination unit. The detection unit is configured to generate an eye image by receiving the input image from the determination unit or receiving the face image from the generation unit and detect a pupil from the eye image using a second neural network including a plurality of filters.

Detecting device

Growing community of inventors

Incheon, South Korea

Kang Il Lee