Dr Harshala Gammulle
Faculty of Engineering,
School of Electrical Engineering & Robotics
Biography
Dr Harshala Gammulle was appointed Postdoctoral Research Fellow in SAIVT in February 2020. She earned her PhD in Computer Vision from QUT in December 2019, receiving the QUT Executive Dean’s Commendation for Outstanding Doctoral Thesis Award.Her expertise spans machine learning and computer vision, with a particular focus on spatio-temporal modelling for human behaviour understanding. She leads and contributes to interdisciplinary projects funded by Defence Science and Technology (DST), SmartSat Cooperative Research Centre (SmartSat CRC), the Queensland Department of Environment, Science and Innovation (QLD DESI), Surf Life Saving Queensland, and Rheinmetall Defence Australia. Some key initiatives include:
- Quantum–Classical Hybrid ML for Scalable, Reliable Biomedical Signal Analysis
Principal Investigator, QLD DESI - Beyond Fixed Length Context in Transformers – Augmenting Transformers with Neural Memories Chief Investigator, QLD DESI
- Robust Predictive AI for Natural Disaster Forecasting via Hyperspectral Band Registration
Chief Investigator, SmartSat CRC - Onboard Hyperspectral AI for Satellite Image Segmentation and Analysis
Key Researcher, SmartSat CRC - Autonomous Combat Warrior Visual Recognition System
Key Researcher, Rheinmetall Defence Australia - Explainable Human Behaviour Understanding for Effective Human–Machine Collaboration
Principal Investigator, QUT Early Career Research Idea Scheme - Auslan Assist Chief Investigator, QUT
Personal details
Positions
- Research Fellow
Faculty of Engineering,
School of Electrical Engineering & Robotics
Keywords
Computer Vision, Machine Learning, Deep Learning, Human-Machine Interaction, Human Behaviour Analysis, Medical Image Analysis
Research field
Artificial intelligence
Field of Research code, Australian and New Zealand Standard Research Classification (ANZSRC), 2020
Qualifications
- Doctor of Philosophy (Queensland University of Technology)
Teaching
EGB202 Microprocessors and Digital Systems - Lecturer and Co-coordinator (2026 Semester 1 - Present)
EGH444 Digital Signals and Image Processing - Lecturer (2023)
EGB103 Computing and Data for Engineers - Lecturer (2022- 2023)
EGH444 Digital Signals and Image Processing - Lecturer and Unit Coordinator (2022)
Publications
Research outputs by year
- Gammulle, H., Ahmedt-Aristizabal, D., Denman, S., Tychsen-Smith, L., Petersson, L. & Fookes, C. (2023). Continuous Human Action Recognition for Human-machine Interaction: A Review. ACM Computing Surveys, 55(13 s), Article 272. https://eprints.qut.edu.au/242813
- Fernando, T., Gammulle, H., Sridharan, S., Denman, S. & Fookes, C. (2025). Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 1941–1957. https://eprints.qut.edu.au/254548
- Alzubaidi, L., Jebur, S., Jaber, T., Mohammed, M., Alwzwazy, H., Saihood, A., Gammulle, H., Santamaria, J., Duan, Y., Fookes, C., Jurdak, R. & Gu, Y. (2025). ATD Learning: A secure, smart, and decentralised learning method for big data environments. Information Fusion, 118, Article 102953. https://eprints.qut.edu.au/254960
- Fernando, T., Fookes, C., Gammulle, H., Denman, S. & Sridharan, S. (2023). Toward On-Board Panoptic Segmentation of Multispectral Satellite Images. IEEE Transactions on Geoscience and Remote Sensing, 61, Article 5402312. https://eprints.qut.edu.au/239473
- Fernando, T., Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2022). Deep Learning for Medical Anomaly Detection: A Survey. ACM Computing Surveys, 54(7), Article 141. https://eprints.qut.edu.au/214059
- Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2021). TMMF: Temporal Multi-modal Fusion for Single-Stage Continuous Gesture Recognition. IEEE Transactions on Image Processing, 30, 7689–7701. https://eprints.qut.edu.au/214058
- Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2020). Fine-grained action segmentation using the semi-supervised action GAN. Pattern Recognition, 98, Article 107039. https://eprints.qut.edu.au/200897
- Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2020). Two-stream deep feature modelling for automated video endoscopy data analysis. Medical Image Computing and Computer Assisted Intervention - MICCAI 2020: 23rd International Conference, Proceedings, Part III, 742–751. https://eprints.qut.edu.au/203232
- Gammulle, P., Warnakulasuriya, T., Denman, S., Sridharan, S. & Fookes, C. (2019). Coupled generative adversarial network for continuous fine-grained action segmentation. Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 200–209. https://eprints.qut.edu.au/126905
- Gammulle, H., Denman, S., Sridharan, S. & Fookes, C. (2019). Predicting the future: A jointly learnt model for action anticipation. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV 2019), 5561–5570. https://eprints.qut.edu.au/200892
QUT ePrints
For more publications by Harshala, explore their research in QUT ePrints (our digital repository).
Filter publications:
A complete list of publications is available at: https://www.qut.edu.au/about/our-people/academic-profiles/pranali.gammule
Awards
- Type
- Nomination/Short Listed for an Award
- Reference year
- 2021
- Details
- Women in Technology (WiT). WiT Emerging Achiever Technology Award - Finalist
- Type
- University Prize including VC Award
- Reference year
- 2020
- Details
- Queensland University of Technology. QUT Executive Dean's Commendation for Outstanding Doctoral Thesis Award
- Type
- University Prize including VC Award
- Reference year
- 2015
- Details
- University Award for Academic Excellence, University of Peradeniya, Sri Lanka
Supervision
Looking for a postgraduate research supervisor?
I am currently accepting research students for Honours, Masters and PhD study.
You can browse existing student topics offered by QUT or propose your own topic.
Current supervisions
- Adversarial Defence in Classical and Quantum Autonomous Machine Learning Systems
PhD, Associate Supervisor
Other supervisors: Professor Clinton Fookes, Dr Tharindu Fernando Warnakulasuriya, Emeritus Professor Sridha Sridharan - Beyond Fixed Length Context in Transformers Augmenting Transformers with Neural Memories
PhD, Associate Supervisor
Other supervisors: Dr Tharindu Fernando Warnakulasuriya, Emeritus Professor Sridha Sridharan, Professor Clinton Fookes, Associate Professor Simon Denman - Deep Reinforcement Learning for HVAC system Intelligent Control
PhD, Principal Supervisor
Other supervisors: Distinguished Professor Lidia Morawska, Professor Clinton Fookes - Human Action Recognition for Real World Applications
PhD, Principal Supervisor
Other supervisors: Emeritus Professor Sridha Sridharan, Professor Clinton Fookes, Dr Tharindu Fernando Warnakulasuriya - Quantum-Classical Hybrid Machine Learning Algorithms for Disease Detection, Classification, and Monitoring Using Efficient, Scalable, Reliable, and Interpretable Biomedical Signal Analysis
PhD, Principal Supervisor
Other supervisors: Dr Tharindu Fernando Warnakulasuriya, Emeritus Professor Sridha Sridharan, Professor Clinton Fookes, Dr Kien Nguyen Thanh - Transformer Neural Networks on Fine-Grained Sports Data
PhD, Associate Supervisor
Other supervisors: Emeritus Professor Sridha Sridharan, Professor Clinton Fookes
Completed supervisions (Doctorate)
Completed supervisions (Masters by Research)
The supervisions listed above are only a selection.