Dr Dimity Miller
Faculty of Engineering,
School of Electrical Engineering & Robotics
Personal details
Positions
- Lecturer
Faculty of Engineering,
School of Electrical Engineering & Robotics
Research field
Computer vision and multimedia computation, Machine learning, Control engineering, mechatronics and robotics
Field of Research code, Australian and New Zealand Standard Research Classification (ANZSRC), 2020
Qualifications
- Doctoral Degree (Queensland University of Technology)
- Bachelor of Engineering (Mechatronics, Robotics) (Queensland University of Technology)
Publications
- Miller, D., Sünderhauf, N., Milford, M. & Dayoub, F. (2021). Class Anchor Clustering: A Loss for Distance-based Open Set Recognition. Proceedings of the 2021 Winter Conference on Applications of Computer Vision (WACV '21), 3569–3577. https://eprints.qut.edu.au/207543
- Hall, D., Dayoub, F., Skinner, J., Zhang, H., Miller, D., Corke, P., Carneiro, G., Angelova, A. & Sünderhauf, N. (2020). Probabilistic object detection: Definition and evaluation. Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 1020–1029. https://eprints.qut.edu.au/201949
- Miller, D., Suenderhauf, N., Zhang, H., Hall, D. & Dayoub, F. (2019). Benchmarking sampling-based probabilistic object detectors. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 42–45. https://eprints.qut.edu.au/137187/
- Miller, D., Dayoub, F., Milford, M. & Suenderhauf, N. (2019). Evaluating merging strategies for sampling-based uncertainty techniques in object detection. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), 2348–2354. https://eprints.qut.edu.au/127819
- Miller, D., Nicholson, L., Dayoub, F. & Suenderhauf, N. (2018). Dropout sampling for robust object detection in open-set conditions. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), 3243–3249. https://eprints.qut.edu.au/122856
QUT ePrints
For more publications by Dimity, explore their research in QUT ePrints (our digital repository).