Zobrazeno 1 - 10
of 268
pro vyhledávání: '"Choi, Jongmoo"'
Publikováno v:
In International Review of Financial Analysis October 2024 95 Part A
Autor:
Akguc, Serkan, Choi, Jongmoo Jay
Publikováno v:
In Research in International Business and Finance January 2025 73 Part A
Autor:
Choi, Jongmoo Jay1 (AUTHOR) jjchoi@temple.edu, Li, Yuanzhi1 (AUTHOR), Shenkar, Oded2 (AUTHOR), Zhang, Jian3 (AUTHOR)
Publikováno v:
Journal of Accounting, Auditing & Finance. Jul2023, Vol. 38 Issue 3, p596-619. 24p. 1 Diagram, 9 Charts.
Autor:
Guo, Xiao, Choi, Jongmoo
Human motion prediction from motion capture data is a classical problem in the computer vision, and conventional methods take the holistic human body as input. These methods ignore the fact that, in various human activities, different body components
Externí odkaz:
http://arxiv.org/abs/1902.07367
This paper reports a visible and thermal drone monitoring system that integrates deep-learning-based detection and tracking modules. The biggest challenge in adopting deep learning methods for drone detection is the paucity of training drone images e
Externí odkaz:
http://arxiv.org/abs/1812.08333
Autor:
Wang, Ye, Choi, Jongmoo, Chen, Yueru, Li, Siyang, Huang, Qin, Zhang, Kaitai, Lee, Ming-Sui, Kuo, C. -C. Jay
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects. It becomes tremendously challenging when multiple objects occur and interact in a given video clip. In this pap
Externí odkaz:
http://arxiv.org/abs/1812.07712
One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation tr
Externí odkaz:
http://arxiv.org/abs/1812.05206
A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work. The biggest challenge in adopting deep learning methods for drone detection is the limited amount of training drone images. To addr
Externí odkaz:
http://arxiv.org/abs/1712.00863
We propose a novel 3D face recognition algorithm using a deep convolutional neural network (DCNN) and a 3D augmentation technique. The performance of 2D face recognition algorithms has significantly increased by leveraging the representational power
Externí odkaz:
http://arxiv.org/abs/1703.10714
Autor:
Hassner, Tal, Masi, Iacopo, Kim, Jungyeon, Choi, Jongmoo, Harel, Shai, Natarajan, Prem, Medioni, Gerard
We propose a novel approach to template based face recognition. Our dual goal is to both increase recognition accuracy and reduce the computational and storage costs of template matching. To do this, we leverage on an approach which was proven effect
Externí odkaz:
http://arxiv.org/abs/1607.01450