Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Jungchan Cho"'
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-12 (2023)
Abstract Polyp segmentation is challenging because the boundary between polyps and mucosa is ambiguous. Several models have considered the use of attention mechanisms to solve this problem. However, these models use only finite information obtained f
Externí odkaz:
https://doaj.org/article/ebdd4a0a11634713bc81a0b697ef9a25
Autor:
Jinah Kim, Jungchan Cho
Publikováno v:
IEEE Access, Vol 10, Pp 65315-65325 (2022)
Weakly supervised temporal action localization (WTAL) aims to localize temporal intervals of actions in an untrimmed video using only video-level action labels. Although the learning of the background is an important issue in WTAL, most previous stud
Externí odkaz:
https://doaj.org/article/ba225896e4a74418ac23e5039d33b818
Autor:
Geonu Lee, Jungchan Cho
Publikováno v:
IEEE Access, Vol 10, Pp 82656-82667 (2022)
An image location requiring focus to recognize a specific pedestrian attribute often depends on the state of the pedestrian within the image. In addition, various pedestrian attributes are closely related to each other. For example, the “Boots” a
Externí odkaz:
https://doaj.org/article/403a85c6723d401c99eba6c0ec079583
Publikováno v:
IEEE Access, Vol 9, Pp 34251-34263 (2021)
Human-object interaction (HOI) detection, which finds the relationships between humans and objects, is an important research area, but current HOI detection performance is unsatisfactory. One of the main problems is that CNN-based HOI detection algor
Externí odkaz:
https://doaj.org/article/d66a53405ab447ab8a0344d867df743b
Publikováno v:
IEEE Access, Vol 8, Pp 32502-32517 (2020)
The detection of abnormal postures, such as that of a reclining person, is a crucial part of visual surveillance. Further, even regular poses can appear rotated because of incongruity between the image and the angle of a pre-installed camera. However
Externí odkaz:
https://doaj.org/article/28cf850180a54fe1ad4b43fcbbe8b410
Publikováno v:
IEEE Access, Vol 8, Pp 216781-216792 (2020)
Detecting pill defection remains challenging, despite recent extensive studies, because of the lack of defective data. In this paper, we propose a pipeline composed of a pill detection module and an autoencoder-based defect detection module to detect
Externí odkaz:
https://doaj.org/article/30d786df20764463b1fc65a2c96b05e1
Publikováno v:
Sensors, Vol 22, Iss 17, p 6626 (2022)
Pedestrians are often obstructed by other objects or people in real-world vision sensors. These obstacles make pedestrian-attribute recognition (PAR) difficult; hence, occlusion processing for visual sensing is a key issue in PAR. To address this pro
Externí odkaz:
https://doaj.org/article/831e31bdccd14677a8816aab4363cd5b
Autor:
Jungchan Cho
Publikováno v:
Sensors, Vol 21, Iss 22, p 7539 (2021)
Universal domain adaptation (UDA) is a crucial research topic for efficient deep learning model training using data from various imaging sensors. However, its development is affected by unlabeled target data. Moreover, the nonexistence of prior knowl
Externí odkaz:
https://doaj.org/article/7a576453521840dfb764b12bf8684110
Autor:
Jungchan Cho, Hyoseok Hwang
Publikováno v:
Sensors, Vol 20, Iss 12, p 3491 (2020)
Emotion recognition plays an important role in the field of human–computer interaction (HCI). An electroencephalogram (EEG) is widely used to estimate human emotion owing to its convenience and mobility. Deep neural network (DNN) approaches using a
Externí odkaz:
https://doaj.org/article/338e55e142c94b0a8ce3dc60a0fcf387
Publikováno v:
Applied Sciences, Vol 10, Iss 4, p 1531 (2020)
Action recognition is an application that, ideally, requires real-time results. We focus on single-image-based action recognition instead of video-based because of improved speed and lower cost of computation. However, a single image contains limited
Externí odkaz:
https://doaj.org/article/1edcfe745d7e49649aefd26543e107b7