no code implementations • 13 Apr 2024 • Maedeh Jamali, Nader Karimi, Shadrokh Samavi, Shahram Shirani
By utilizing our model in this manner, quality improvements up to 2 dB and bitrate savings of up to 46% of the original target bitrate are possible.
no code implementations • 8 Dec 2023 • Zahra Nabizadeh Shahre-Babak, Nader Karimi, Krishna Rapaka, Tarek Amara, Shadrokh Samavi, Shahram Shirani
One solution is to predict each preset's transcoding time and select the preset that ensures the highest quality while adhering to live streaming time constraints.
no code implementations • 12 Jun 2023 • MohammadHossein Givkashi, Mohammadreza Naderi, Nader Karimi, Shahram Shirani, Shadrokh Samavi
In our approach, a mask is generated to show the desired size and location of the object.
no code implementations • 3 May 2023 • Yasaman Torabi, Shahram Shirani, James P. Reilly
In this study, a modified version of the affine non-negative matrix factorization (NMF) approach is proposed to blindly separate lung and heart sounds recorded by a digital stethoscope.
no code implementations • 12 Mar 2023 • Zahra Sobhaninia, Nasrin Abharian, Nader Karimi, Shahram Shirani, Shadrokh Samavi
Endoscopy is a valuable tool for the early diagnosis of colon cancer.
1 code implementation • 9 Jan 2023 • Mohammadreza Naderi, MohammadHossein Givkashi, Nader Karimi, Shahram Shirani, Shadrokh Samavi
None of the powerful existing models can fill out the missing parts of an image while considering the symmetry and homogeneity of the picture.
1 code implementation • 15 Nov 2022 • Mohammadreza Naderi, Nader Karimi, Ali Emami, Shahram Shirani, Shadrokh Samavi
Helping the cGAN learn the target distribution from noise input results in a better model generalization during the test time and allows the model to fit almost perfectly to the target domain distribution.
1 code implementation • 11 Sep 2022 • Mohammad Reza Naderi, Mohammad Hossein Givkashi, Nader Karimi, Shahram Shirani, Shadrokh Samavi
The PSO algorithm uses aesthetic quality assessment as its objective function to identify the best location and size for the objects to be placed in the background.
no code implementations • 9 Apr 2022 • S. M. Reza Soroushmehr, Shadrokh Samavi, Shahram Shirani
This search area is similar to that of the full search (FS) algorithm but smaller for most blocks of a frame.
no code implementations • 12 Sep 2021 • Mohammadreza Naderi, Zahra Nabizadeh, Nader Karimi, Shahram Shirani, Shadrokh Samavi
In this work, we propose a method called MSGDD-cGAN, which first stabilizes the performance of the cGANs using multi-connections gradients flow.
Conditional Image Generation Generative Adversarial Network +1
no code implementations • 24 May 2021 • Maedeh Jamali, Nader Karim, Pejman Khadivi, Shahram Shirani, Shadrokh Samavi
In this paper, we propose to use an end-to-end network for watermarking.
no code implementations • 1 Sep 2020 • Sajjad Abbasi, Mohsen Hajabdollahi, Pejman Khadivi, Nader Karimi, Roshanak Roshandel, Shahram Shirani, Shadrokh Samavi
Knowledge distillation addresses some of the shortcomings associated with transfer learning by generalizing a complex model to a lighter model.
no code implementations • 18 Apr 2020 • Hamed Sadeghi, Shahram Shirani, David W. Capson
A novel and fast semi-automatic method for segmentation, locating and counting blood cells in an image is proposed.
no code implementations • 27 Mar 2020 • Kamran Chitsaz, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi, Shahram Shirani
In this paper, a new method for CNN processing in the FFT domain is proposed, which is based on input splitting.
no code implementations • 9 Feb 2020 • Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi, Shahram Shirani
Knowledge distillation is recently proposed to transfer the knowledge of a model to another one and can be useful to cover the shortcomings of transfer learning.
no code implementations • 9 Feb 2020 • Emad Malekhosseini, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi, Shahram Shirani
For convolutional neural networks (CNNs) that have a large volume of input data, memory management becomes a major concern.
no code implementations • 9 Feb 2020 • Morteza Mousa-Pasandi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi, Shahram Shirani
In the proposed attenuation approach, weak filters are not abruptly removed, and there is a chance for these filters to return to the network.
no code implementations • 13 Oct 2017 • Eman Alibeigi, Shadrokh Samavi, Shahram Shirani, Zahra Rahmani
Most of the automatic verification systems are based on matching of fingerprint minutiae.
no code implementations • 8 Sep 2017 • Hamid R. Fazlali, Nader Karimi, S. M. Reza Soroushmehr, Shahram Shirani, Brahmajee. K. Nallamothu, Kevin R. Ward, Shadrokh Samavi, Kayvan Najarian
In this framework we use our catheter detection and tracking method which detects the catheter by finding its ridge in the first frame and traces in other frames by fitting a second order polynomial on it.
no code implementations • 6 Sep 2017 • Zohreh HosseinKhani, Mohsen Hajabdollahi, Nader Karimi, Reza Soroushmehr, Shahram Shirani, Kayvan Najarian, Shadrokh Samavi
In this paper a low complexity de-noising method is proposed that removes the noise by local analysis of the image blocks.
no code implementations • 19 Apr 2017 • Hamed Sadeghi, Shahrokh Valaee, Shahram Shirani
Then, it finds depth and angle-of-view of the query using the information provided by the OCR engine in order to refine the location estimate.
no code implementations • 30 Jun 2014 • Pedram Mohammadi, Abbas Ebrahimi-Moghadam, Shahram Shirani
Measuring the image quality is of fundamental importance for numerous image processing applications, where the goal of image quality assessment (IQA) methods is to automatically evaluate the quality of images in agreement with human quality judgments.