Dr Girmaw Abebe Tadesse is a Postdoctoral Researcher in Machine Learning for Healthcare at the Institute of Biomedical Engineering, University of Oxford. He primarily develops deep learning techniques to assist diagnosis of cardiovascular disease, cancer and infectious disease. He works in multiple projects with international collaborations including clinicians in China and Vietnam.
Girmaw completed his PhD at Queen Mary University of London under the Erasmus Mundus Joint Doctorate Program in Interactive and Cognitive Environments with UPC-BarcelonaTech. His PhD research focused on computer vision and machine learning algorithms for human activity recognition using wearable sensors.
Girmaw received his MSc degree in Telecommunications Engineering from Trento University, Italy in 2012, and the BSc degree in Electrical Engineering from Arba Minch University, Ethiopia in 2007. He has worked in various research groups across Europe, including the Technical Research Center for Dependency Care and Autonomous Living in Spain, KU Leuven in Belgium, and INESC-ID in Portugal.
- Multi-modal learning
- First-person vision
- Deep networks for temporal encoding in video and time-series data
- Automated Decision Support System for Patients at Risk of Myocardial Infarction (FAST Healthcare NetworksPlus Project)
- Predictive Monitoring of Acute Infectious Disease in Critically Ill Vietnamese Patients (Frontiers of Engineering)
- Epigenetic Enrichment of Circulating Tumour DNA to Enable Deep Profiling for Cancer Early Detection (Cancer Research UK)
- Robust multi-dimensional motion features for first-person vision activity recognition, G Abebe, A Cavallaro, X Parra, Computer Vision and Image Understanding 149, 229-248 18
- A long short-term memory convolutional neural network for first-person vision activity recognition, G Abebe, A Cavallaro, Proceedings of the IEEE International Conference on Computer Vision, 1339-1346 7
- Hierarchical modeling for first-person vision activity recognition, G Abebe, A Cavallaro Neurocomputing 267, 362-377 6
- Inertial-Vision: cross-domain knowledge transfer for wearable sensors G Abebe, A Cavallaro Proceedings of the IEEE International Conference on Computer Vision, 1392-1400 4
- Visual features for ego-centric activity recognition: A survey G Abebe Tadesse, A Cavallaro Proceedings of the 4th ACM Workshop on Wearable Systems and Applications, 48-53 1
- A first-person vision dataset of office activities G Abebe Tadesse, A Catala, A Cavallaro In Proc. of International Conference on Pattern Recognition (ICPR) Workshop on Multimodal Pattern Recognition of Social Signals in Human Computer Interaction (MPRSS), Beijing, China
- Monitoring of infectious disease patients using machine learning G Abebe Tadesse, T Zhu, L Thwaites, D Clifton Thirty-second Conference on Neural Information Processing Systems (NeurIPS) Workshop on Machine Learning for the Developing World (ML4D)
- 2018 Cross-domain transfer learning for cardiovascular diseases G Abebe Tadesse, T Zhu, Y Liu, M Tian, D Clifton Thirty-second Conference on Neural Information Processing Systems (NeurIPS …
- Cross-domain knowledge transfer for wearable sensors G Abebe Tadesse, T Zhu, A Cavallaro The second Black in AI event co-located with the thirty-second conference on …
- Improving patient care in low-resource settings using transfer learning G Abebe Tadesse, T Zhu, L Thwaites, D Clifton Thirty-second Conference on Neural Information Processing Systems (NeurIPS …
- Human Activity Recognition Using a Wearable Camera G Abebe Tadesse Queen Mary University of London
- Environment Classification and Acoustic Events Detection Using NMF and GMM Learning Algorithms for Monitoring Application, G Abebe Tadesse The Second International Conference on the Advancement of Science and …
- Automatic Audio-based Recognition of Activities of Daily Living G Abebe Tadesse, Trento university
- A first-person vision dataset of office activities G Abebe, A Catala, A Cavallaro
- Personalised Diagnostic Tools for Infectious Diseases GA Tadesse