Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

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

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

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

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.