no code implementations • 25 Feb 2024 • Vitalii Makogin, Duc Nguyen, Evgeny Spodarev
In practical applications, effectively segmenting cracks in large-scale computed tomography (CT) images holds significant importance for understanding the structural integrity of materials.
no code implementations • 21 Mar 2023 • Duc Nguyen, Anderson Ye Zhang
Unlike the existing methods which use $\{U_jU_1^\top\}_{j\geq 2}$, ours constructs an anchor matrix $M$ by aggregating useful information from all the block submatrices and estimates the latent permutations through $\{U_jM^\top\}_{j\geq 1}$.
no code implementations • 10 Mar 2023 • Duc Nguyen, Anderson Y. Zhang
Firstly, we obtain a refined entrywise error bound for the spectral algorithm, complementing the `average error' $\ell_2$ bound in their work.
no code implementations • 10 Feb 2023 • Duc Nguyen, Anderson Y. Zhang
We propose an initialization algorithm that can provide a provably accurate initial estimate and an EM algorithm that maximizes the true log-likelihood function efficiently.
no code implementations • 9 Oct 2022 • Duc Nguyen, Anderson Zhang
The Rasch model is one of the most fundamental models in \emph{item response theory} and has wide-ranging applications from education testing to recommendation systems.
1 code implementation • 12 Aug 2022 • Edison Mucllari, Vasily Zadorozhnyy, Cole Pospisil, Duc Nguyen, Qiang Ye
In recent years, using orthogonal matrices has been shown to be a promising approach in improving Recurrent Neural Networks (RNNs) with training, stability, and convergence, particularly, to control gradients.
no code implementations • 23 Jun 2022 • Duc Nguyen
The intersection of learning to rank and choice modeling is an active area of research with applications in e-commerce, information retrieval and the social sciences.
no code implementations • 1 Jun 2022 • Bao-Sinh Nguyen, Quang-Bach Tran, Tuan-Anh Nguyen Dang, Duc Nguyen, Hung Le
Measuring the confidence of AI models is critical for safely deploying AI in real-world industrial systems.
1 code implementation • 8 Jan 2021 • Abiy Tasissa, Duc Nguyen, James Murphy
A method for active learning of hyperspectral images (HSI) is proposed, which combines deep learning with diffusion processes on graphs.
no code implementations • 20 Sep 2020 • Duc Nguyen, Phuoc Nguyen, Kien Do, Santu Rana, Sunil Gupta, Truyen Tran
These include the capacity of the compact matrix LSTM to compress noisy data near perfectly, making the strategy of compressing-decompressing data ill-suited for anomaly detection under the noise.
no code implementations • 5 Nov 2019 • Duc Nguyen, Nhan Tran, Hung Le
Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition.
Optical Character Recognition Optical Character Recognition (OCR) +1
1 code implementation • 15 Mar 2019 • Ouassim Elhara, Konstantinos Varelas, Duc Nguyen, Tea Tusar, Dimo Brockhoff, Nikolaus Hansen, Anne Auger
The bbob-largescale test suite, containing 24 single-objective functions in continuous domain, extends the well-known single-objective noiseless bbob test suite, which has been used since 2009 in the BBOB workshop series, to large dimension.