Overview
Background
Dr Alina Bialkowski is a computer vision & machine learning researcher developing interpretable machine learning models to increase the performance and transparency of Artificial Intelligence (AI) decision-making. Her research interests include quantifying and extracting actionable knowledge from data to solve real-world problems and giving human understanding to AI models through feature visualisation and attribution methods. She has applied these techniques to various multi-disciplinary applications such as medical imaging (including imaging strokes in the brain using the new sensing modality of electromagnetic imaging), modelling human attention in driving, intelligent transport systems (ITS), intelligent surveillance, and sports analytics.
Dr Bialkowski holds a PhD and BEng (Electrical Engineering) from the Queensland University of Technology, Australia. Her doctoral studies were in characterising group behaviours from visual and spatio-temporal data to enhance statistics and visualisation in sports analytics as well as intelligent surveillance systems. She spent a year at Disney Research Pittsburgh where she developed techniques to automatically analyse team sports, followed by 2.5 years as a postdoctoral researcher at the University College London, developing deep neural networks to better understand human perception and attention in driving, before joining UQ in late 2017.
The impact of her research is evidenced by the high number of citations to her work (>1600 citations and an h-index of 20 according to Google Scholar) and awards including a best paper prize in 2017 at WACV (a top computer vision conference). In addition to high impact journals and conferences, her work has resulted in 6 international patents filed with Disney Research, Toyota Motor Europe, University College London, and The University of Queensland.
Availability
- Dr Alina Bialkowski is:
- Available for supervision
- Media expert
Fields of research
Qualifications
- Bachelor (Honours), Queensland University of Technology
- Doctor of Philosophy, Queensland University of Technology
Research interests
-
Machine Learning
Developing interpretable or explainable models to increase trust and transparency of computer-based decisions.
-
Computer Vision
Developing models of visual information using image processing and feature representation learning approaches such as deep learning to perform predictions on data.
-
Sensors
Utilising sensors such as cameras and antennas/electromagnetic sensors to enable remote sensing and non-invasive imaging.
Works
Search Professor Alina Bialkowski’s works on UQ eSpace
2022
Conference Publication
Distilling representational similarity using Centered Kernel Alignment (CKA)
Saha, Aninda, Bialkowski, Alina and Khalifa, Sara (2022). Distilling representational similarity using Centered Kernel Alignment (CKA). British Machine Vision Conference, London, United Kingdom, 21-24 November 2022. British Machine Vision Association (BMVA).
2022
Conference Publication
Anomaly localisation from microwave signals using deep learning
Lai, Wei-Chung and Bialkowski, Alina (2022). Anomaly localisation from microwave signals using deep learning. 27th International Symposium on Antennas and Propagation (ISAP), Sydney, Australia, 31 October-3 November 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/isap53582.2022.9998673
2022
Conference Publication
Necessary but not sufficient: assurance mechanisms for enhancing trust in AI-enabled job screening
Lockey, Steve, Gillespie, Nicole, Curtis, Caitlin, Bingley, William, Worthy, Peter, Haslam, Alexander, Steffens, Niklas, Bialkowski, Alina, Ko, Ryan and Wiles, Janet (2022). Necessary but not sufficient: assurance mechanisms for enhancing trust in AI-enabled job screening. 82nd Annual Meeting of the Academy of Management, Seattle, WA United States, 5-9 August 2022. Briarcliff Manor, NY United States: Academy of Management. doi: 10.5465/ambpp.2022.10638abstract
2022
Conference Publication
Unified framework for effective knowledge distillation in single-stage object detectors
Saha, Aninda, Bialkowski, Alina and Khalifa, Sara (2022). Unified framework for effective knowledge distillation in single-stage object detectors. International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW, Australia, 30 November 2022 - 02 December 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/DICTA56598.2022.10034590
2022
Conference Publication
Feature similarity and its correlation with accuracy in knowledge distillation
Saha, Aninda, Bialkowski, Alina and Khalifa, Sara (2022). Feature similarity and its correlation with accuracy in knowledge distillation. International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW, Australia, 30 November 2022 - 02 December 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/DICTA56598.2022.10034621
2022
Conference Publication
Explainable deep learning for medical imaging models through class specific semantic dictionaries
Layton, Harrison, Shrapnel, Sally and Bialkowski, Alina (2022). Explainable deep learning for medical imaging models through class specific semantic dictionaries. International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW, Australia, 30 November 2022 - 02 December 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/DICTA56598.2022.10034639
2021
Other Outputs
Machine learning onboard satellites
SmartSat, Saha, Aninda , Sun, Yu , Bialkowski, Alina , Nguyen, Kien , Qin, A. Kai and Fookes, Clinton (2021). Machine learning onboard satellites. Adelaide, Australia: SmartSat Cooperative Research Centre.
2021
Journal Article
Case Report: preliminary images from an electromagnetic portable brain scanner for diagnosis and monitoring of acute stroke
Cook, David, Brown, Helen, Widanapathirana, Isuravi, Shah, Darshan, Walsham, James, Trakic, Adnan, Zhu, Guohun, Zamani, Ali, Guo, Lei, Brankovic, Aida, Al-Saffar, Ahmed, Stancombe, Anthony, Bialkowski, Alina, Nguyen, Phong, Bialkowski, Konstanty, Crozier, Stuart and Abbosh, Amin (2021). Case Report: preliminary images from an electromagnetic portable brain scanner for diagnosis and monitoring of acute stroke. Frontiers in Neurology, 12 765412, 765412. doi: 10.3389/fneur.2021.765412
2021
Other Outputs
Apparatus and process for medical imaging
Abbosh, Amin, Afasri, Arman, Zamani, Ali, Bialkowski, Alina, Zhu, Guohun, Nguyen, Thanh Phong, Guo, Lei and Wang, Yifan (2021). Apparatus and process for medical imaging. EP3846688A1.
2021
Conference Publication
Fusion of traffic sensors for enhanced road monitoring
Bialkowski, Alina, Bialkowski, Konstanty and Brankovic, Aida (2021). Fusion of traffic sensors for enhanced road monitoring. 17th ITS Asia Pacific Forum, Brisbane, Australia, 12-15 April 2021.
2021
Journal Article
Stroke classification in simulated electromagnetic imaging using graph approaches
Zhu, Guohun, Bialkowski, Alina, Guo, Lei, Mohammed, Beada'a and Abbosh, Amin (2021). Stroke classification in simulated electromagnetic imaging using graph approaches. IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology, 5 (1) 9095216, 46-53. doi: 10.1109/JERM.2020.2995329
2020
Journal Article
Closing the gap of simulation to reality in electromagnetic imaging of brain strokes via deep neural networks
Al-Saffar, Ahmed, Bialkowski, Alina, Baktashmotlagh, Mahsa, Trakic, Adnan, Guo, Lei and Abbosh, Amin (2020). Closing the gap of simulation to reality in electromagnetic imaging of brain strokes via deep neural networks. IEEE Transactions on Computational Imaging, 7 9274540, 13-21. doi: 10.1109/tci.2020.3041092
2017
Conference Publication
Predicting the perceptual demands of urban driving with video regression
Palmer, Luke, Bialkowski, Alina, Brostow, Gabriel J., Ambeck-Madsen, Jonas and Lavie, Nilli (2017). Predicting the perceptual demands of urban driving with video regression. 17th IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, California, 24-31 March 2017. NEW YORK: IEEE. doi: 10.1109/wacv.2017.52
2016
Journal Article
Discovering team structures in soccer from spatiotemporal data
Bialkowski, Alina, Lucey, Patrick, Carr, Peter, Matthews, Iain, Sridharan, Sridha and Fookes, Clinton (2016). Discovering team structures in soccer from spatiotemporal data. IEEE Transactions on Knowledge and Data Engineering, 28 (10) 7492601, 2596-2605. doi: 10.1109/tkde.2016.2581158
2015
Conference Publication
Quality vs quantity: improved shot prediction in soccer using strategic features from spatiotemporal data
Lucey, Patrick, Bialkowski, Alina, Monfort, Mathew, Carr, Peter and Matthews, Iain (2015). Quality vs quantity: improved shot prediction in soccer using strategic features from spatiotemporal data. MIT Sloan Sports Analytics Conference, Boston, MA United States, 27-28 February 2015. Boston, MA United States: MIT.
2014
Conference Publication
Win at home and draw away: automatic formation analysis highlighting the differences in home and away team behaviors
Bialkowski, Alina, Lucey, Patrick, Carr, Peter, Yue, Yisong and Matthews, Iain (2014). Win at home and draw away: automatic formation analysis highlighting the differences in home and away team behaviors. MIT Sloan Sports Analytics Conference, Boston, MA, United States, 28 February - 1 March 2014. Boston, MA, United States: MIT.
2014
Conference Publication
How to get an open shot: analyzing team movement in basketball using tracking data
Lucey, Patrick, Bialkowski, Alina, Carr, Peter, Yue, Yisong and Matthews, Iain (2014). How to get an open shot: analyzing team movement in basketball using tracking data. MIT Sloan Sports Analytics Conference, Boston, MA, United States, 28 February - 1 March 2014. Boston, MA, United States: MIT.
2014
Conference Publication
Large-scale analysis of soccer matches using spatiotemporal tracking data
Bialkowski, Alina, Lucey, Patrick, Carr, Peter, Yue, Yisong, Sridharan, Sridha and Matthews, Iain (2014). Large-scale analysis of soccer matches using spatiotemporal tracking data. 2014 IEEE International Conference on Data Mining, Shenzhen, China, 14-17 December 2014. Red Hook, NY, United States: Curran Associates. doi: 10.1109/icdm.2014.133
2014
Conference Publication
Identifying team style in soccer using formations learned from spatiotemporal tracking data
Bialkowski, Alina, Lucey, Patrick, Carr, Peter, Yue, Yisong, Sridharan, Sridha and Matthews, Iain (2014). Identifying team style in soccer using formations learned from spatiotemporal tracking data. 2014 IEEE International Conference on Data Mining, Shenzhen, China, 14-17 December 2014. Red Hook, NY, United States: Curran Associates. doi: 10.1109/icdmw.2014.167
2014
Book Chapter
Representing team behaviours from noisy data using player role
Bialkowski, Alina, Lucey, Patrick, Carr, Peter, Sridharan, Sridha and Matthews, Iain (2014). Representing team behaviours from noisy data using player role. Computer Vision in Sports. (pp. 247-269) Cham, Switzerland: Springer . doi: 10.1007/978-3-319-09396-3_12
Supervision
Availability
- Dr Alina Bialkowski is:
- Available for supervision
Before you email them, read our advice on how to contact a supervisor.
Available projects
-
AgriTwins Project 5: Implementation of Digital Twin Technology for Environmental Monitoring and Sustainable Land Use Management in Bega Valley
PhD Project 5: Implementation of Digital Twin Technology for Environmental Monitoring and Sustainable Land Use Management in Bega valley
With Bega Group & Regional Circularity Co-operative
Description:
This project aims to apply digital twin technology to map and monitor land use in the production region of Bega Valley focusing on greenhouse gas (GHG) monitoring and enhancing environmental sustainability. This could include, but not exclusively, monitoring of natural capital (carbon and biodiversity), soil moisture, river flows, sequestration, etc.
Utilising data from satellite imagery, drones, sensors, weather stations and any other remote sensing techniques, the digital/quantum twin will integrate all forms of available data with land topography parameters, soil health data, and microclimate data to provide a dynamic and comprehensive representation of the region.
This approach will enable better decision-making and environmental stewardship, enhancing both productivity and sustainability in the Bega Valley.
Objectives:
- Develop a high-resolution digital twin of the region for land use classification.
- Monitor and analyse land topography, resource utilisation, and environmental impacts.
- Optimise land management practices to enhance sustainability and productivity.
- Facilitate with environmental regulations, to support stakeholder collaboration and informed decision-making.
Deliverables:
- Comprehensive digital/quantum twin model of the region, incorporating detailed land use classifications.
- Real-time environmental monitoring dashboard providing up-to-date insights into resource utilisation and environmental impacts.
- Optimisation and decision support tools to aid in sustainable land management practices.
- Reports documenting alignment with environmental and regulatory standards.
- Training and engagement materials to educate stakeholders and promote active participation in sustainable practices.
If interested please email me at alina.bialkowski@uq.edu.au with the subject containing AgriTwins
Supervision history
Current supervision
-
Doctor Philosophy
Using deep learning to improve emergency response in natural hazard management
Principal Advisor
-
Doctor Philosophy
Robust Deep Learning Models for Microwave Imaging
Principal Advisor
Other advisors: Dr Lei Guo
-
Master Philosophy
Experience Saturation: Quantifying Demotivation and Disengagement
Associate Advisor
Other advisors: Professor Julie Henry, Dr Nell Baghaei
-
Master Philosophy
Non-Invasive Abundance Monitoring of Captive Mala (Lagorchestes hirsutus) Using Proximal Remote Sensing
Associate Advisor
Other advisors: Associate Professor Diana Fisher, Dr Lorna Hernandez Santin
-
Master Philosophy
Explainable decision support for skin cancer detection using machine learning
Associate Advisor
Other advisors: Professor Tim Miller
-
-
Doctor Philosophy
Electromagnetic Solver Using Physics-Guided Deep Neural Network
Associate Advisor
Other advisors: Dr Lei Guo, Professor Amin Abbosh
-
Doctor Philosophy
Minimally Invasive Blood Analysis Using Data-Driven Electromagnetic Techniques
Associate Advisor
Other advisors: Associate Professor Konstanty Bialkowski, Dr Lei Guo, Professor Amin Abbosh
Completed supervision
-
2024
Doctor Philosophy
Knowledge Distillation for Enhancing Lightweight Computer Vision Models
Principal Advisor
-
2025
Doctor Philosophy
Universal Deep Learning for Reliable Electromagnetic Imaging and Detection in Inhomogeneous Media
Associate Advisor
Other advisors: Dr Lei Guo, Professor Amin Abbosh
-
2021
Doctor Philosophy
Characterization and Detection of Skin Malignancies Using Microwave Techniques
Associate Advisor
Other advisors: Professor Amin Abbosh
Media
Enquiries
Contact Dr Alina Bialkowski directly for media enquiries about:
- Artificial Intelligence
- Machine Learning
Need help?
For help with finding experts, story ideas and media enquiries, contact our Media team: