Rajeev Kanth
Has grant
Principal Lecturer
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Recent Grants
Grant: Close
Virtual Learning Environment in Smart Mini-Factory (VLEFACT)
Open Date: 2021-11-01
Close Date: 2023-12-01
Grant: Close
University Collaboration Network for Drone Research (UCNDRONE)
Open Date: 2020-11-01
Close Date: 2023-01-01
Grant: Close
AIQUSEC – AI-based quantum-safe cybersecurity automation and orchestration for edge intelligence in future networks
Open Date:
Close Date:
Grant: Close
AUTOTIE-Automation and Artificial Intelligence Digitization Project
Open Date:
Close Date:
Articles (6)
Year:
2027
Year:
2026
Year:
2026
Year:
2025
Year:
2025
Many real-world applications rely on head pose estimation. The performance of head pose estimation has significantly improved with techniques like convolutional neural networks (CNN). However, CNN requires a large amount of data for training. This article presents a new framework for head pose estimation using computationally efficient first-order model-agnostic meta-learning (FO-MAML)-based method and compares the performance with existing MAML-based approaches. Experiments using one-shot, five-shot, and ten-shot settings are done using MAML and FO-MAML. A mean average error (MAEavg) of 7.72, 6.30, and 5.32 has been achieved in predicting head pose using MAML for one-, five-, and ten-shot settings, respectively. Similarly, MAEavg of 8.33, 6.84, and 6.23 has been achieved in predicting head pose using FO-MAML for one-, five-, and ten-shot settings, respectively. The computational complexity of an outer-loop update in MAML is found to be O(n2) whereas for FO-MAML it is O(n).
Year:
2023
Collaborators (3)
Jukka Heikkonen
Professor of Computer Science
University of Turku
Pasi Karjalainen
Professor
University of Eastern Finland
Harri Merisaari
Adjunct Professor
University of Turku
Make your next move.
Prepare your application
Review drafts before you send them.