no code implementations • 12 Oct 2023 • Shervin Halat, Mohammad Rahmati, Ehsan Nazerfard
Thus, here, we have considered dense prediction tasks on security inspection x-ray images to evaluate our proposed model Segmentation Localization (SegLoc).
no code implementations • 4 Oct 2023 • Hamid Mohammadi, Ehsan Nazerfard, Tahereh Firoozi
The empirical results show the proposed MoE architecture's superiority over CNN-based models by achieving 92. 4% accuracy on the RWF dataset.
no code implementations • 4 Feb 2022 • Hamid Mohammadi, Ehsan Nazerfard
The proposed model achieved state-of-the-art accuracy of 90. 4% and 98. 7% on RWF and Hockey datasets, respectively.
Ranked #2 on Activity Recognition on RWF-2000 (using extra training data)
no code implementations • 29 Mar 2019 • Elnaz Soleimania, Ehsan Nazerfard
This paper presents a novel method of adversarial knowledge transfer named SA-GAN stands for Subject Adaptor GAN which utilizes Generative Adversarial Network framework to perform cross-subject transfer learning in the domain of wearable sensor-based Human Activity Recognition.
Generative Adversarial Network Human Activity Recognition +2
no code implementations • 12 Mar 2019 • Parviz Asghari, Elnaz Soelimani, Ehsan Nazerfard
After detecting the activity pane, the predicted label will be corrected utilizing statistical features such as time of day at which the activity happened and the duration of the activity.