no code implementations • 27 Feb 2024 • Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun, Aref Miri Rekavandi, Hamid Laga, Farid Boussaid
To address these deficiencies, we introduce the Box-it-to-Bind-it (B2B) module - a novel, training-free approach for improving spatial control and semantic accuracy in text-to-image (T2I) diffusion models.
no code implementations • 16 Jan 2024 • Mohammad Khateri, Morteza Ghahremani, Alejandra Sierra, Jussi Tohka
The inability to acquire clean high-resolution (HR) electron microscopy (EM) images over a large brain tissue volume hampers many neuroscience studies.
1 code implementation • NeurIPS 2023 • Morteza Ghahremani, Christian Wachinger
The proposed method demonstrates broad applicability across different architectures such as multilayer perceptrons, convolutional neural networks, and vision transformers, enabling effective normalization of both low- and high-level features in multimodal neural networks.
no code implementations • 19 Sep 2023 • Mohammad Khateri, Morteza Ghahremani, Alejandra Sierra, Jussi Tohka
To overcome this limitation, we propose a novel deep-learning (DL)-based self-supervised super-resolution approach that computationally reconstructs isotropic 3DEM from the anisotropic acquisition.
1 code implementation • 29 Apr 2022 • Morteza Ghahremani, Mohammad Khateri, Alejandra Sierra, Jussi Tohka
The proposed ADL consists of two auto-encoders: a denoiser and a discriminator.
Ranked #1 on Color Image Denoising on CBSD68 sigma35
no code implementations • 17 Jan 2021 • Ardhendu Behera, Zachary Wharton, Morteza Ghahremani, Swagat Kumar, Nik Bessis
Affect is often expressed via non-verbal body language such as actions/gestures, which are vital indicators for human behaviors.
Facial Expression Recognition Facial Expression Recognition (FER) +2
1 code implementation • 1 Dec 2020 • Morteza Ghahremani, Yonghuai Liu, Bernard Tiddeman
In this paper, we show that robust and accurate keypoints exist in the specific scale-space domain.
1 code implementation • 21 Aug 2020 • Morteza Ghahremani, Bernard Tiddeman, Yonghuai Liu, Ardhendu Behera
Our method extracts the deep patterns inside a 3D object via creating a dynamic link to seek the most stable patterns and at once, throws away the unstable ones.