Zobrazeno 1 - 10
of 139
pro vyhledávání: '"Phill Kyu Rhee"'
Publikováno v:
IEEE Access, Vol 6, Pp 61748-61760 (2018)
Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In most cases, image quality is noisy and biased, and
Externí odkaz:
https://doaj.org/article/2788a6091bdb49ff8d825377dbe75683
Publikováno v:
Symmetry, Vol 12, Iss 1, p 119 (2020)
People with disabilities (PWD) face a number of challenges such as obstacle avoidance or taking a minimum path to reach a destination while travelling or taking public transport, especially in airports or bus stations. In some cases, PWD, and specifi
Externí odkaz:
https://doaj.org/article/be85b47459734e02929cc11ff9454459
Publikováno v:
Symmetry, Vol 11, Iss 10, p 1271 (2019)
In this paper, we propose an open-set object detection framework based on a dynamic hierarchical structure with incremental learning capabilities for unseen object classes. We were motivated by the observation that deep features extracted from visual
Externí odkaz:
https://doaj.org/article/4cdce240c92b4fc48de5b1cb53030a32
Publikováno v:
Multimedia Tools and Applications. 79:6689-6708
We propose a robust object-detector ensemble by introducing a dynamic multi-layer multi-label (MLML)-tree–based adaptive deep learning framework. In many heterogeneous data distributions, deep attributes show latent hierarchical clustering properti
Publikováno v:
Cognitive Systems Research. 52:212-222
Facial expression recognition in a wild situation is a challenging problem in computer vision research due to different circumstances, such as pose dissimilarity, age, lighting conditions, occlusions, etc. Numerous methods, such as point tracking, pi
Publikováno v:
Cognitive Systems Research. 45:109-123
In this paper, we address the combination of the active learning (AL) and semi-supervised (SSL) learnings, called ASSL, to leverage the strong points of the both learning paradigms for improving the performance of object detection. Considering the pr
Autor:
Jin-Woo Kim, Phill Kyu Rhee
Publikováno v:
The Journal of the Institute of Internet Broadcasting and Communication. 17:165-171
Publikováno v:
Symmetry
Volume 11
Issue 10
Symmetry, Vol 11, Iss 10, p 1271 (2019)
Volume 11
Issue 10
Symmetry, Vol 11, Iss 10, p 1271 (2019)
In this paper, we propose an open-set object detection framework based on a dynamic hierarchical structure with incremental learning capabilities for unseen object classes. We were motivated by the observation that deep features extracted from visual
Publikováno v:
KSII Transactions on Internet and Information Systems. 13
Publikováno v:
Symmetry, Vol 12, Iss 1, p 119 (2020)
Symmetry
Volume 12
Issue 1
Symmetry
Volume 12
Issue 1
People with disabilities (PWD) face a number of challenges such as obstacle avoidance or taking a minimum path to reach a destination while travelling or taking public transport, especially in airports or bus stations. In some cases, PWD, and specifi