no code implementations • 23 Jan 2024 • Ali Pourramezan Fard, Mohammad H. Mahoor, Muath Alsuhaibani, Hiroko H. Dodgec
Our proposed NLP framework consists of two Transformer-based modules, namely Sentence Embedding (SE) and Sentence Cross Attention (SCA).
1 code implementation • 2 Feb 2023 • Ali Pourramezan Fard, Mohammad H. Mahoor, Sarah Ariel Lamer, Timothy Sweeny
We analyze facial attribute entanglement in the latent space of GANs and apply the proposed transformation for editing the disentangled facial attributes.
1 code implementation • 29 Mar 2022 • Ali Pourramezan Fard, Mohammad H. Mahoor
Heatmap-based Regression (HBR) and Coordinate-based Regression (CBR) are among the two mainly used methods for face alignment.
Ranked #14 on Face Alignment on COFW
1 code implementation • IEEE Access 2022 • Ali Pourramezan Fard, Mohammad H. Mahoor
In addition, the Mean Discriminator component leads the network to make the mean embedded feature vectors of different classes to be less similar to each other. We use Xception network as the backbone of our model, and contrary to previous work, we propose an embedding feature space that contains k feature vectors.
Ranked #10 on Facial Expression Recognition (FER) on FER2013
Facial Expression Recognition Facial Expression Recognition (FER) +1
1 code implementation • 21 Nov 2021 • Jian Sun, Ali Pourramezan Fard, Mohammad H. Mahoor
To address the computational burdens of the Dynamic Routing mechanism, this paper proposes new Fully Connected (FC) layers by xnorizing the linear projection outside or inside the Dynamic Routing within the CapsFC layer.
Ranked #11 on Image Classification on MNIST (Accuracy metric)
1 code implementation • 13 Nov 2021 • Ali Pourramezan Fard, Mohammad H. Mahoor
We use two Teacher networks, a Tolerant-Teacher and a Tough-Teacher in conjunction with the Student network.
Ranked #17 on Face Alignment on COFW
1 code implementation • 27 Feb 2021 • Ali Pourramezan Fard, Hojjat Abdollahi, Mohammad Mahoor
We compare the performance of our proposed model called ASMNet with MobileNetV2 (which is about 2 times bigger than ASMNet) in both the face alignment and pose estimation tasks.
Ranked #1 on Head Pose Estimation on COFW