no code implementations • 13 Nov 2023 • Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi, Minija Tamosiunaite, Florentin Wörgötter
Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video.
no code implementations • 1 Oct 2023 • Fatemeh Ziaeetabar, Reza Safabakhsh, Saeedeh Momtazi, Minija Tamosiunaite, Florentin Wörgötter
To achieve this, we encode, first, the spatio-temporal inter dependencies between objects and actions with scene graphs and we combine this, in a second step, with a novel 3-level architecture creating a hierarchical attention mechanism using Graph Attention Networks (GATs).
no code implementations • 29 Sep 2023 • Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
To this end, we will introduce a framework for a rigorous study of harmonic and holomorphic hypothesis in learning theory terms and provide empirical evidence that continuous hypotheses does not perform as well as discontinuous hypotheses in some common machine learning tasks.
no code implementations • 25 Sep 2023 • Najmeh Mohammadbagheri, Fardin Ayar, Ahmad Nickabadi, Reza Safabakhsh
Semantic facial attribute editing using pre-trained Generative Adversarial Networks (GANs) has attracted a great deal of attention and effort from researchers in recent years.
no code implementations • 23 Jul 2023 • Mohammad Hadi Goldani, Reza Safabakhsh, Saeedeh Momtazi
This model includes a CapsNet with dynamic routing algorithm paralyzed with a size-based classifier for detecting short and long fake news statements.
1 code implementation • 26 May 2022 • Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
The reliability of a learning model is key to the successful deployment of machine learning in various industries.
1 code implementation • 7 Apr 2022 • Niloofar Ranjbar, Reza Safabakhsh
On the other hand, in some tasks such as medical, economic, and self-driving cars, users want the model to be interpretable to decide if they can trust these results or not.
no code implementations • 29 Sep 2021 • Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
This paper presents a model and a solution for the existence and transfer of adversarial examples in analytic hypotheses.
no code implementations • 22 Jul 2021 • Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
Also, we extend and unify some of the other proposals in the literature and provide alternative explanations on the observations made in those proposals.
1 code implementation • 3 Jul 2021 • Amirhossein Nouranizadeh, Mohammadjavad Matinkia, Mohammad Rahmati, Reza Safabakhsh
We evaluate our method, referred to as Maximum Entropy Weighted Independent Set Pooling (MEWISPool), on graph classification tasks and the combinatorial optimization problem of the maximum independent set.
Ranked #2 on Graph Classification on FRANKENSTEIN
1 code implementation • 8 Jan 2021 • Mehran Taghian, Ahmad Asadi, Reza Safabakhsh
The proposed model consists of an encoder which is a neural structure responsible for learning informative features from the input sequence, and a decoder which is a DRL model responsible for learning profitable strategies based on the features extracted by the encoder.
1 code implementation • 27 Oct 2020 • Mehran Taghian, Ahmad Asadi, Reza Safabakhsh
The effect of different input representations on the performance of the models is investigated and the performance of DRL-based models in different markets and asset situations is studied.
no code implementations • 3 Feb 2020 • Mohammad Hadi Goldani, Saeedeh Momtazi, Reza Safabakhsh
This paper aims to use capsule neural networks in the fake news detection task.
no code implementations • 26 Jun 2019 • Ahmad Asadi, Reza Safabakhsh
The existing approaches are based on neural encoder-decoder structures equipped with the attention mechanism.
no code implementations • 26 Nov 2017 • Ehsan Shojaedini, Mahshid Majd, Reza Safabakhsh
In this paper, a new paradigm is proposed based on genetic algorithm with an adaptive strategy.
no code implementations • 26 Aug 2017 • Ehsan Shojaedini, Reza Safabakhsh
We use the 3D feature information to estimate the scale of each feature.
no code implementations • 20 Nov 2015 • Ghazal Zand, Mojtaba Taherkhani, Reza Safabakhsh
Particle Filter algorithm (PF) suffers from some problems such as the loss of particle diversity, the need for large number of particles, and the costly selection of the importance density functions.