Ali Sahfiei

I recently completed my Bachelor’s degree in Computer Science at Sharif University of Technology Top University in Iran. My research interests lie in Trustworthy AI and Computer Vision, particularly at its intersection with Natural Language Processing. I am also interested in self-supervised learning and scenarios with limited annotated data, aiming to develop models that generalize well under low-resource conditions.

During my undergraduate studies, I conducted research on diffusion models for text-to-image generation and vision-language Models. Prior to university, I was awarded a Bronze Medal in the National Mathematics Olympiad.

selected publications

NAACL Findings

Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description

Mahshid Dehghani, Amirahmad Shafiee^*, Ali Shafiei^*, and 6 more authors

2024

Abs arXiv

Existing 3D facial emotion modeling have been constrained by limited emotion classes and insufficient datasets. This paper introduces "Emo3D", an extensive "Text-Image-Expression dataset" spanning a wide spectrum of human emotions, each paired with images and 3D blendshapes. Leveraging Large Language Models (LLMs), we generate a diverse array of textual descriptions, facilitating the capture of a broad spectrum of emotional expressions. Using this unique dataset, we conduct a comprehensive evaluation of language-based models’ fine-tuning and vision-language models like Contranstive Language Image Pretraining (CLIP) for 3D facial expression synthesis. We also introduce a new evaluation metric for this task to more directly measure the conveyed emotion. Our new evaluation metric, Emo3D, demonstrates its superiority over Mean Squared Error (MSE) metrics in assessing visual-text alignment and semantic richness in 3D facial expressions associated with human emotions. "Emo3D" has great applications in animation design, virtual reality, and emotional human-computer interaction.