Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Efficient Facial Expression Recognition Framework Based on Edge Computing

Published in Journal of Supercomputing (SJR Q2), 2024

This paper presents a novel framework for facial expression recognition (FER) using edge computing to address the challenges of latency, memory usage, and privacy in DL-based FER models. It empirically evaluates various landmark detection models for robust, real-time FER on IoT devices, demonstrating significant improvements in efficiency and performance.

Recommended citation: Aikyn, N., Zhanegizov, A., Aidarov, T. et al. Efficient facial expression recognition framework based on edge computing. J Supercomput 80, 1935–1972 (2024). https://doi.org/10.1007/s11227-023-05548-x
Download Paper

Conference Papers

FedFSLAR: A Federated Learning Framework for Few-shot Action Recognition

Published in 2024 IEEE WACV Conference, 2024

This paper proposes FedFSLAR, a federated learning framework for few-shot action recognition that combines 3D-CNN-based spatiotemporal features with meta-learning. It addresses the challenges of data scarcity and bias in federated settings and validates the effectiveness of the framework under non-IID conditions, offering notable advances for FL and FSL in action recognition.

Recommended citation: N. A. Tu et al., "FedFSLAR: A Federated Learning Framework for Few-shot Action Recognition," 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), Waikoloa, HI, USA, 2024, pp. 270-279, doi: 10.1109/WACVW60836.2024.00035.
Download Paper

Few-shot Action Recognition with Video Transformer

Published in 2023 IEEE SITIS Conference, 2023

This paper introduces a few-shot action recognition framework integrating a Video Transformer with meta-learning via ProtoNet. Extensive experiments show superior performance over baselines, with effective transfer learning capabilities in cross-domain scenarios, offering a promising approach for few-shot learning in action recognition.

Recommended citation: N. Aikyn, A. Abu, T. Zhaksylyk and N. A. Tu, "Few-shot Action Recognition with Video Transformer," 2023 17th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Bangkok, Thailand, 2023, pp. 122-129, doi: 10.1109/SITIS61268.2023.00027.
Download Paper | Download Slides