Dr Harshala Gammulle
Faculty of Engineering,
School of Electrical Engineering & Robotics
Biography
Dr Harshala Gammulle is a Research Fellow in the Signal Processing, Artificial Intelligence, and Vision Technologies (SAIVT) research program in the school of Electrical Engineering and Robotics at Queensland University of Technology (QUT). She obtained her BSc (Honours) from the University of Peradeniya, Sri Lanka, and her PhD from QUT, Australia. During her PhD, Harshala proposed machine learning techniques for understanding human behaviour in videos and received the QUT Executive Dean's Commendation for Outstanding Doctoral Thesis Award, for her thesis contributions. Her research to date has resulted in significant contributions to a diverse set of application domains including, security surveillance, sports, human-robot interaction and biomedical research. Since the completion of her PhD, Harshala is continuing her research activities in the Machine learning and Computer Vision domains collaborating with multiple research teams and industry partners.Highlights
- "Temporal Multi-Modal Fusion for Single-Stage Continuous Gesture Recognition", in Transactions on Image Processing (2021).
- Tools into Teammates
- "Fine-grained action segmentation using the semi-supervised action GAN." Pattern Recognition 98 (2020).
- "Predicting the Future: A Jointly Learnt Model for Action Anticipation." In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019.
- "Forecasting future action sequences with neural memory networks." In British Machine Vision Conference (BMVC) 2019.
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
EGH444 Digital Signals and Image Processing - Lecturer (2023)
EGB103 Computing and Data for Engineers - Lecturer (2022- Present)
EGH444 Digital Signals and Image Processing - Lecturer and Unit Coordinator (2022)
Publications
- 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. 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). 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. 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, P., Denman, S., Sridharan, S. & Fookes, C. (2019). Forecasting Future Action Sequences with Neural Memory Networks. Proceedings of the 30th British Machine Vision Conference 2019, BMVC 201, 1–12. https://eprints.qut.edu.au/200899
- Gammulle, P., Denman, S., Sridharan, S. & Fookes, C. (2019). Multi-level sequence GAN for group activity recognition. Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, Revised Selected Papers, 331–346. https://eprints.qut.edu.au/126865
- 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
- Gammulle, P., Denman, S., Sridharan, S. & Fookes, C. (2017). Two stream LSTM: A deep fusion framework for human action recognition. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV 2017), 177–186. https://eprints.qut.edu.au/118097
QUT ePrints
For more publications by Harshala, explore their research in QUT ePrints (our digital repository).
Awards
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2020
- Details
- QUT Executive Dean's Commendation for Outstanding Doctoral Thesis Award
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2015
- Details
- University Award for Academic Excellence, University of Peradeniya, Sri Lanka
- Type
- Other
- Reference year
- 2021
- Details
- WiT Emerging Achiever Technology Award - Finalist
Supervision
Current supervisions
- PhD, Associate Supervisor
Other supervisors: Distinguished Professor Lidia Morawska, Professor Clinton Fookes, Dr Rohan Jayaratne - Transformer Neural Networks on Fine-Grained Sports Data
PhD, Associate Supervisor
Other supervisors: Professor Sridha Sridharan, Professor Clinton Fookes - PhD, Associate Supervisor
Other supervisors: Professor Sridha Sridharan, Professor Clinton Fookes, Dr Tharindu Fernando Warnakulasuriya - MPhil, Associate Supervisor
Other supervisors: Professor YuanTong Gu, Dr Laith Alzubaidi
The supervisions listed above are only a selection.