Schedule
8.30-8.35am |
Opening Remarks |
8.35-9.20am |
Talk: Feature Learning in Computer Vision Sara Hooker, Google AI |
9.20-10.00am |
Spotlight Talks 3 and 5 minute talks by Indaba attendees |
10.00-10.25am |
Panel: Frontiers of Computer Vision Naila Murray, Naver Labs Richard Klein, University of Witwatersrand Daniela Massiceti, University of Oxford Moderator: Sara Hooker, Google AI |
10.25-10.30am |
Closing Remarks |
Spotlight Talks
Panel: Frontiers of Computer Vision
Naila Murray, Senior Scientist & Team Lead, Naver Labs Europe
Naila is a senior scientist and lead the Computer Vision (CV) group. Her research interests include fine-grained visual categorization and search, visual attention and image aesthetics analysis. Currently, her research focuses on image search and video action recognition.
Richard Klein, Lecturer, University of Witwatersrand
Richard completed his PhD in Computer Vision at the University of the Witwatersrand in 2017. Prior to that he completed his MSc and BSc (Hons) in Computer Vision from the same university. He is currently a lecturer in the School of Computer Science and Applied Mathematics at Wits. He is the junior focus area coordinator in the NRF Centre of Excellence in Mathematics and Statistical Sciences - Machine Intelligence and Learning from Experience. His work focuses on the use of computer vision to understand human behaviour, particularly in an educational setting.
Daniela Massiceti, PhD Student, University of Oxford
Daniela is a doctoral student in the Torr Vision Group at the University of Oxford under the supervision of Professor Philip Torr and Dr Stephen Hicks. Prior to this, she completed a M.Sc Neuroscience, and before that a B.Sc Electrical and Computer Engineering at the University of Cape Town. She is interested in multi-modal representations of the world and how these can be used to interface AI systems with humans. In her PhD, she is exploring the combinations of vision and language in the context of models for visual-based dialogue. Her motivation for grounding these dialogue models in real-world visual scenarios is toward building AI-based assistants to help blind/visually-impaired people.
Daniela is a doctoral student in the Torr Vision Group at the University of Oxford under the supervision of Professor Philip Torr and Dr Stephen Hicks. Prior to this, she completed a M.Sc Neuroscience, and before that a B.Sc Electrical and Computer Engineering at the University of Cape Town. She is interested in multi-modal representations of the world and how these can be used to interface AI systems with humans. In her PhD, she is exploring the combinations of vision and language in the context of models for visual-based dialogue. Her motivation for grounding these dialogue models in real-world visual scenarios is toward building AI-based assistants to help blind/visually-impaired people.
Moderator: Sara Hooker, Google AI
Sara Hooker is a researcher at Google Brain doing deep learning research on reliable explanations of model predictions for black-box models. Her main research interests gravitate towards interpretability, model compression and security. In 2014, she founded Delta Analytics, a non-profit dedicated to bringing technical capacity to help non-profits across the world use machine learning for good. She grew up in Africa, in Mozambique, Lesotho, Swaziland, South Africa, and Kenya. Her family now lives in Monrovia, Liberia.
Call for Spotlight Talks
We invite all confirmed Deep Learning Indaba attendees to apply to present their research in computer vision as a spotlight talk at the Frontiers of Computer Vision session. You will need to give us a short summary of your talk and upload a draft of your slides. Successful applicants will each give a 5 minute oral presentation (with slides) followed by 1 minute of questions from the audience. As a speaker, you will have the opportunity to have your work profiled and engage with fellow researchers.