Zobrazeno 1 - 10
of 3 618
pro vyhledávání: '"Nguyen Trong, The"'
The accurate alignment of 3D woodblock geometrical models with 2D orthographic projection images presents a significant challenge in the digital preservation of Vietnamese cultural heritage. This paper proposes a unified image processing algorithm to
Externí odkaz:
http://arxiv.org/abs/2411.05524
Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning
Externí odkaz:
http://arxiv.org/abs/2407.06045
Video scene graph generation (VidSGG) has emerged as a transformative approach to capturing and interpreting the intricate relationships among objects and their temporal dynamics in video sequences. In this paper, we introduce the new AeroEye dataset
Externí odkaz:
http://arxiv.org/abs/2406.01029
Autor:
Huynh, Thanh Trung, Nguyen, Trong Bang, Nguyen, Phi Le, Nguyen, Thanh Tam, Weidlich, Matthias, Nguyen, Quoc Viet Hung, Aberer, Karl
Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data poisoning
Externí odkaz:
http://arxiv.org/abs/2405.18040
The entropy error function has been widely used in neural networks. Nevertheless, the network training based on this error function generally leads to a slow convergence rate, and can easily be trapped in a local minimum or even with the incorrect sa
Externí odkaz:
http://arxiv.org/abs/2405.18552
Autor:
Trieu, Doan-An, Nguyen, Trong-Thanh D., Nguyen, Thanh-Duy D., Tran, Thanh, Le, Van-Hoang, Phan, Ngoc-Loan
Precise control of the electron phase accumulated during its sub-cycle motion within intense laser fields is essential in strong-field physics, yet remains mostly indirect and complicated so far. In this Letter, we develop a novel approach to control
Externí odkaz:
http://arxiv.org/abs/2405.11753
The rapid advancement of large language models (LLMs) necessitates the development of new benchmarks to accurately assess their capabilities. To address this need for Vietnamese, this work aims to introduce ViLLM-Eval, the comprehensive evaluation su
Externí odkaz:
http://arxiv.org/abs/2404.11086
Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexi
Externí odkaz:
http://arxiv.org/abs/2403.18605
Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, however, struggle with a diver
Externí odkaz:
http://arxiv.org/abs/2312.03050
Autor:
Nghia-Nguyen, Trong, Thanh Cuong, Le, Khatir, Samir, Hoang, Le Minh, Chaiyaput, Salisa, Abdel Wahab, Magd
Publikováno v:
Engineering Computations, 2024, Vol. 41, Issue 8/9, pp. 2054-2073.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/EC-10-2023-0749
