公开(公告)号：US20240378695A1

公开(公告)日：2024-11-14

申请号：US18032825

申请日：2022-11-04

Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

Inventor： SA IM SHIN ,  Bo Eun KIM ,  Han Mu PARK ,  Chung Il KIM

IPC: G06T5/50 ,  G06T5/77 ,  G06T11/60

Abstract: The present invention relates to an image inpainting apparatus and an image inpainting method, the image inpainting apparatus including: a background inpainting part configured to generate a background-inpainted image by carrying out inpainting on a background with respect to an input image in which a region to be inpainted is set up; an object inpainting part configured to generate an object image by carrying out inpainting on an object; and an image overlapping part configured to generate an output image by causing the background-inpainted image and the object image, which are generated, to overlap each other.

公开(公告)号：US20240193797A1

公开(公告)日：2024-06-13

申请号：US18531940

申请日：2023-12-07

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun KIM ,  Jung Ho KIM ,  Sa Im SHIN

IPC: G06T7/262 ,  G06F17/16

CPC classification number: G06T7/262 ,  G06F17/16

Abstract: There are provided a method and a system for generating human motions, which generate motions of an empty frame by using motions in a given frame. A human motion generation method according to an embodiment includes: a first step of transforming, by a system, a domain of pose information of a frame; a second step of generating, by the system, motion features of an empty frame in the transformed domain; and a third step of inversely transforming, by the system, the generated motion features into a time domain. Accordingly, the method and system may effectively generate motions by obtaining a basis vector to be used for transforming a domain of motion trajectory information by training a deep learning-based transform model, transforming a motion trajectory through the basis vector, and inputting the transformed motion trajectory to a motion generation model.

公开(公告)号：US20190286931A1

公开(公告)日：2019-09-19

申请号：US16043338

申请日：2018-07-24

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun KIM ,  Choong Sang CHO ,  Hye Dong JUNG ,  Young Han LEE

IPC: G06K9/46 ,  G06F17/24 ,  G06F17/27 ,  G06N5/04 ,  G06N3/08 ,  G06T7/00

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

公开(公告)号：US20240096071A1

公开(公告)日：2024-03-21

申请号：US18368600

申请日：2023-09-15

Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

Inventor： Sa Im SHIN ,  Jung Ho KIM ,  Bo Eun KIM

IPC: G06V10/774 ,  G06T7/246 ,  G06V10/20 ,  G06V10/82 ,  G06V10/94 ,  G06V20/40 ,  G06V40/20

CPC classification number: G06V10/7747 ,  G06T7/251 ,  G06V10/255 ,  G06V10/82 ,  G06V10/95 ,  G06V20/46 ,  G06V40/23 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: There is provided a video processing method performed by a computing device, the method including the steps of: collecting video from an external device; generating preprocessed data by extracting two-dimensional or three-dimensional skeleton information from the video; pre-training a first artificial intelligence model including N transformer blocks from the preprocessed data by applying an attention from a body of an object to a plurality of joints, an attention from each of the plurality of joints to the body, and an attention between persons; and learning, when parameters determined as a result of the pre-training of the first artificial intelligence model are transferred, a method of recognizing an action from the video received from the external device, using a second artificial intelligence model including the N transformer blocks on the basis of the parameters, wherein N is a natural number equal to or larger than 2.

公开(公告)号：US20210117723A1

公开(公告)日：2021-04-22

申请号：US17016654

申请日：2020-09-10

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun KIM ,  Hye Dong JUNG

IPC: G06K9/62 ,  G06F40/10

Abstract: A method and a system for automatically generating multiple captions of an image are provided. A method for training an auto image caption generation model according to an embodiment of the present disclosure includes: generating a caption attention map by using an image; converting the generated caption attention map into a latent variable by projecting the caption attention map onto a latent space; deriving a guide map by using the latent variable; and training to generate captions of an image by using the guide map and the image. Accordingly, a plurality of captions describing various characteristics of an image and including various expressions can be automatically generated.