Education and Research

Education

• MSc in Data Science, Nazarbayev University, Kazakhstan
  Aug 2022 – Jun 2024
  GPA: 3.59 / 4.0
  Thesis: An Exploration of Video Transformers for Few-Shot Action Recognition

• BS in Computer Science, Nazarbayev University, Kazakhstan
  Aug 2018 – Jun 2022
  GPA: 3.71 / 4.0 (CS Courses GPA: 3.82 / 4.0)
  Honors: Diploma of Honor

Research Experience

Research Assistant

Nazarbayev University, Kazakhstan
July 2022 – Present
Focus: Deep Learning, Computer Vision, Few-Shot Learning, Federated Learning, Edge Computing, Vision Transformers, Vision-Language Models.

Key Projects

1. Vision-Language Models for Aerial Video Classification
   Adapted CLIP and other vision-language models to aerial video datasets, achieving state-of-the-art results in action detection for zero-shot, few-shot, and supervised settings.

2. Federated Few-Shot Action Recognition
   Integrated few-shot learning with federated learning frameworks, enhancing performance in federated settings using meta-learning techniques on transformer-based models.

3. Few-Shot Learning for Action Recognition with Video Transformers
   Developed a few-shot action recognition framework leveraging Transformer-based backbones, self-supervised pretraining, and optimized few-shot performance on custom datasets.

4. Transformer-Based Multi-Stream Human Action Recognition
   Built multi-stream models using RGB, optical flow, and skeletal data, achieving near-state-of-the-art results with transfer learning and keyframe sampling.

5. Facial Expression Recognition on Edge Systems
   Designed a FER framework optimized for edge devices, combining deep learning and edge computing to achieve real-time emotion recognition on resource-constrained devices.