Summary
Viktoriia Sharmanska is passionate about designing intelligent systems that can learn concepts from visual data using machine learning models. Visual data are images or videos coming from either existing available databases, or directly from the Web. She got her MSc in Applied Mathematics from the Taras Shevchenko National University of Kyiv, Ukraine, and her PhD in Computer Vision and Machine Learning from the Institute of Science and Technology Austria. Her PhD thesis was focused on attribute-based object recognition and the models based on learning using privileged information. From June 2015, she was a visiting research fellow at the University of Sussex, UK working on cross-modal and cross-dataset learning with privileged information.
Since October 2017, she joined Imperial College London as a research fellow leading the project in 'Deep Understanding of Human Behaviour from Video Data: Action plus Emotion Approach'. Her research interests include deep learning methods for understanding human behaviour from facial and bodily cues, algorithmic fairness, designing machine learning models that can overcome human and dataset collection biases.
Selected Publications
Journal Articles
Doukas MC, Koujan MR, Sharmanska V, et al., 2021, Head2Head++: deep facial attributes re-targeting, Ieee Transactions on Biometrics, Behavior, and Identity Science, Vol:3, ISSN:2637-6407, Pages:31-43
Truong AH, Sharmanska V, Limback-Stanic C, et al., 2020, Optimisation of deep learning methods for visualisation of tumour heterogeneity and brain tumour grading through digital pathology, Neuro-oncology Advances, Vol:2, ISSN:2632-2498
Conference
Quadrianto N, Sharmanska V, Thomas O, 2020, Discovering fair representations in the data domain, 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Pages:8219-8228, ISSN:2575-7075
Demir I, Bazazian D, Romero A, et al., 2018, WiCV 2018: The Fourth Women In Computer Vision Workshop, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Pages:1941-1943, ISSN:2160-7508
Quadrianto N, Sharmanska V, 2017, Recycling privileged learning and distribution matching for fairness, Advances in Neural Information Processing Systems (NIPS), Neural Information Processing Systems Foundation, Inc.
Sharmanska V, Hernandez-Lobato D, Hernandez-Lobato JM, et al., 2016, Ambiguity helps: classification with disagreements in crowdsourced annotations, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Pages:2194-2202, ISSN:1063-6919
Sharmanska V, Quadrianto N, 2016, Learning from the mistakes of others: matching errors in cross-dataset learning, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Pages:3967-3975, ISSN:1063-6919
Pentina A, Sharmanska V, Lampert CH, 2015, Curriculum learning of multiple tasks, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, Pages:5492-5500, ISSN:1063-6919
Sharmanska V, Quadrianto N, Lampert CH, 2014, Learning to rank using privileged information, IEEE International Conference on Computer Vision (ICCV), IEEE, Pages:825-832, ISSN:1550-5499