no code implementations • 5 Nov 2017 • Saeed Ghodsi, Hoda Mohammadzade, Erfan Korki
The availability of low-cost range sensors and the development of relatively robust algorithms for the extraction of skeleton joint locations have inspired many researchers to develop human activity recognition methods using the 3-D data.
Human Activity Recognition Human-Object Interaction Detection
no code implementations • 23 Dec 2021 • Ensieh Khazaei, Hoda Mohammadzade
EEG signals in emotion recognition absorb special attention owing to their high temporal resolution and their information about what happens in the brain.
no code implementations • 15 Aug 2022 • Sara Khalili, Hoda Mohammadzade, Mohammad Mahdi Ahmadi
Experiments show that the proposed method can improve the classification accuracy by 36% for a non-deep model and 55% for a deep model in occlusion conditions.
no code implementations • 13 Apr 2023 • Niloufar Fakhfour, Mohammad ShahverdiKondori, Hoda Mohammadzade
We introduce an unsupervised method for alignment that uses global and local features of the frames.
no code implementations • 4 Oct 2023 • Atefeh Khoshkhahtinat, Hoda Mohammadzade
Epilepsy is a neurological disorder identified by sudden and recurrent seizures, which are believed to be accompanied by distinct changes in brain dynamics.
1 code implementation • 7 Feb 2018 • Hoda Mohammadzade, Amirhossein Sayyafan, Benyamin Ghojogh
The geometry alignment is performed pixel-wise, i. e., every pixel of the face is corresponded to a pixel of the reference face.
1 code implementation • 21 Aug 2017 • Mozhgan Mokari, Hoda Mohammadzade, Benyamin Ghojogh
This method introduces the definition of body states and then every action is modeled as a sequence of these states.
1 code implementation • 25 Sep 2018 • Benyamin Ghojogh, Saeed Sharifian, Hoda Mohammadzade
The experimental results on several well-known benchmarks show the outperforming performance of TBO algorithm in finding the global solution.
1 code implementation • 15 Feb 2018 • Benyamin Ghojogh, Hoda Mohammadzade, Mozhgan Mokari
The proposed regularized Mahalanobis distance metric is used in order to recognize both the involuntary and highly made-up actions at the same time.
1 code implementation • 7 Aug 2021 • Hassan Keshvarikhojasteh, Hoda Mohammadzade, Hamid Behroozi
In this paper, we propose a new network based on Gated Recurrent Unit (GRU) and two novel post-processing methods for TAL task.
1 code implementation • 17 Nov 2017 • Benyamin Ghojogh, Saeed Bagheri Shouraki, Hoda Mohammadzade, Ensieh Iranmehr
This paper proposes a fusion-based gender recognition method which uses facial images as input.
1 code implementation • 1 Mar 2021 • Mohammad Akyash, Hoda Mohammadzade, Hamid Behroozi
The main challenge in training deep neural networks is the lack of sufficient data to improve the model's generalization and avoid overfitting.
1 code implementation • 7 Mar 2023 • M. Mehrdad Morsali, Hoda Mohammadzade, Saeed Bagheri Shouraki
This paper presents a context-aware framework for feature selection and classification procedures to realize a fast and accurate audio event annotation and classification.
Ranked #2 on Environmental Sound Classification on UrbanSound8K (Accuracy metric)