F
Farzaneh Esmaili
Researcher at Tarbiat Modares University
Publications - 6
Citations - 9
Farzaneh Esmaili is an academic researcher from Tarbiat Modares University. The author has contributed to research in topics: Supervised learning & Computer science. The author has an hindex of 2, co-authored 4 publications receiving 8 citations.
Papers
More filters
Posted Content
Using Self-Supervised Co-Training to Improve Facial Representation.
TL;DR: In this article, a Hybrid Learning (HL) framework was proposed for standard Supervised Learning (SL), which used Self-Supervised co-training with SL in Multi-Task Learning (MTL) manner.
Posted Content
Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation
TL;DR: In this paper, the impact of ImageNet pre-training on fine-grained facial expression recognition (FER) was tested and it was shown from the results that training from scratch is better than ImageNet fine-tuning at stronger augmentation levels.
Posted Content
How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation?
TL;DR: In this article, modified versions of jigsaw puzzling and rotation are used as SSL pre-text tasks and the best architecture for Hybrid Multi-Task Learning (HMTL) is found.
Proceedings ArticleDOI
Predicting the Load Capacity of 4G Cellular Networks With Deep Learning
Hamid Azadegan,Farzaneh Esmaili +1 more
TL;DR: In this paper , the authors investigated the performance of the mobile phone network capacity of Mobile Telecommunication Company of Iran (MCI) using CQI prediction employing deep learning methods.
Posted Content
A Brief Review of Machine Learning Techniques for Protein Phosphorylation Sites Prediction.
TL;DR: In this paper, the authors comprehensively reviewed all reversible post-translational modification (PTM) data and showed that there are basically two main approaches for phosphorylation prediction by machine learning: end-to-end and conventional.