no code implementations • 26 Aug 2023 • Seyedeh Fatemeh Razavi, Mohammad Mahdi Mehmanchi, Reshad Hosseini, Mostafa Tavassolipour
This study investigates the effect of manifold learning using normalizing flows on out-of-distribution detection.
1 code implementation • 6 Mar 2023 • Mohammad Mahdi Afrasiabi, Reshad Hosseini, Aliazam Abbasfar
Super-resolution is the process of obtaining a high-resolution image from one or more low-resolution images.
no code implementations • 11 Dec 2022 • Peyman Baghershahi, Reshad Hosseini, Hadi Moradi
Many Graph Neural Networks (GNNs) are proposed for Knowledge Graph Embedding (KGE).
1 code implementation • 11 Dec 2022 • Mohammad Pasande, Reshad Hosseini, Babak Nadjar Araabi
Gaussian Mixture Models (GMMs) are one of the most potent parametric density models used extensively in many applications.
1 code implementation • 7 Aug 2022 • Mohammad Hossein Nasseri, Mohammadreza Babaee, Hadi Moradi, Reshad Hosseini
In this paper, a method for measuring camera motion and removing its effect is presented that efficiently reduces the camera motion effect on tracking.
no code implementations • 7 Jun 2022 • Seyedeh Fatemeh Razavi, Mohammad Mahdi Mehmanchi, Reshad Hosseini, Mostafa Tavassolipour
We propose a single-step method for joint manifold learning and density estimation by disentangling the transformed space obtained by normalizing flows to manifold and off-manifold parts.
no code implementations • 2 Jun 2022 • Ali Karimi, Zahra Mousavi Kouzehkanan, Reshad Hosseini, Hadi Asheri
OSM has consistently shown better classification accuracies over cross-entropy and hinge losses for small to large neural networks.
1 code implementation • 20 Dec 2021 • Peyman Baghershahi, Reshad Hosseini, Hadi Moradi
Notably, we yield our promising results with a significant reduction of 66. 9% in the dimensionality of embeddings compared to the five best recent state-of-the-art competitors on average.
Ranked #16 on
Link Prediction
on FB15k-237
1 code implementation • 1 Nov 2021 • Romina Oji, Seyedeh Fatemeh Razavi, Sajjad Abdi Dehsorkh, Alireza Hariri, Hadi Asheri, Reshad Hosseini
Comparison with other available Persian textual normalization tools indicates the superiority of the proposed method in speech processing.
no code implementations • 29 Aug 2021 • Seyed-Mahdi Nasiri, Reshad Hosseini, Hadi Moradi
A viewing graph is a set of unknown camera poses, as the vertices, and the observed relative motions, as the edges.
1 code implementation • 25 Aug 2021 • Reza Godaz, Benyamin Ghojogh, Reshad Hosseini, Reza Monsefi, Fakhri Karray, Mark Crowley
Riemannian LBFGS (RLBFGS) is an extension of this method to Riemannian manifolds.
no code implementations • 9 Jul 2021 • Seyed-Mahdi Nasiri, Reshad Hosseini, Hadi Moradi
Therefore, in contrast to the common practice, we argue that the simple mid-point method should be used in structure-from-motion applications where there is uncertainty in camera parameters.
1 code implementation • 21 Apr 2021 • Reza Godaz, Reza Monsefi, Faezeh Toutounian, Reshad Hosseini
In this paper, we tackle two important problems in low-rank learning, which are partial singular value decomposition and numerical rank estimation of huge matrices.
Matrix Factorization / Decomposition
Riemannian optimization
no code implementations • 11 Mar 2021 • Aida Khozaei, Hadi Moradi, Reshad Hosseini
In this study, we propose a framework for the classification of partially separable data types that are not classifiable using typical methods.
1 code implementation • 6 Mar 2021 • Mohammad Hossein Nasseri, Hadi Moradi, Reshad Hosseini, Mohammadreza Babaee
In contrast, there are algorithms that only use motion cues to increase speed, especially for online applications.
no code implementations • 13 Dec 2020 • Milad Ghorbani, Reshad Hosseini, Seyed Pooya Shariatpanahi, Majid Nili Ahmadabadi
We propose a free-energy minimization framework for selecting the subspaces and integrate the policy of the state-space into the subspaces.
1 code implementation • 27 Oct 2020 • Zahra Mousavi Kouzehkanan, Reshad Hosseini, Babak Nadjar Araabi
Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold.
no code implementations • 5 Aug 2020 • Seyedeh Fatemeh Razavi, Reshad Hosseini, Tina Behzad
The class of recurrent mixture density networks is an important class of probabilistic models used extensively in sequence modeling and sequence-to-sequence mapping applications.
no code implementations • 28 Feb 2019 • Taraneh Younesian, Saeed Masoudnia, Reshad Hosseini, Babak N. Araabi
We benefit from transfer learning using a pre-trained CNN for feature learning.
no code implementations • 7 Dec 2018 • Pourya Habib Zadeh, Reshad Hosseini, Suvrit Sra
On the other hand, deep-RBF networks assign high confidence only to the regions containing enough feature points, but they have been discounted due to the widely-held belief that they have the vanishing gradient problem.
no code implementations • 22 Oct 2017 • Maryam Hashemzadeh, Reshad Hosseini, Majid Nili Ahmadabadi
Generalization and faster learning in a subspace are due to many-to-one mapping of experiences from the full-space to each state in the subspace.
1 code implementation • 10 Jun 2017 • Reshad Hosseini, Suvrit Sra
This motivates us to take a closer look at the problem geometry, and derive a better formulation that is much more amenable to Riemannian optimization.
1 code implementation • 18 Jul 2016 • Pourya Habib Zadeh, Reshad Hosseini, Suvrit Sra
We revisit the task of learning a Euclidean metric from data.
no code implementations • NeurIPS 2015 • Reshad Hosseini, Suvrit Sra
We take a new look at parameter estimation for Gaussian Mixture Model (GMMs).
1 code implementation • 22 Jul 2015 • Reshad Hosseini, Mohamadreza Mash'al
Mixture models are powerful statistical models used in many applications ranging from density estimation to clustering and classification.
no code implementations • 25 Jun 2015 • Reshad Hosseini, Suvrit Sra
We take a new look at parameter estimation for Gaussian Mixture Models (GMMs).
no code implementations • 17 Oct 2014 • Reshad Hosseini, Suvrit Sra, Lucas Theis, Matthias Bethge
We study modeling and inference with the Elliptical Gamma Distribution (EGD).
no code implementations • NeurIPS 2013 • Suvrit Sra, Reshad Hosseini
We exploit the remarkable structure of the convex cone of positive definite matrices which allows one to uncover hidden geodesic convexity of objective functions that are nonconvex in the ordinary Euclidean sense.