Can machines see the invisible? from Miriam Redi

Vision algorithms have achieved impressive performances in visual recognition. Nevertheless, an image is worth a thousand words, and not all these words refer to visible properties such as objects and scenes.

In this talk we will explore the subjective side of visual data, investigating how machine learning can detect intangible properties of images and videos, such as beauty, creativity, and more curious characteristics. We will see the impact of such detectors in the context of web and social media. And we will analyse the precious contribution of computer vision in understanding how people and cultures perceive visual properties, underlining the importance of feature interpretability for this task.

Bio: Miriam Redi is a Research Scientist at Yahoo Labs London. Her research focuses on content-based social multimedia analysis and computational advertising. In particular, she explores ways to automatically assess visual aesthetics and creativity, and exploit the power of computer vision in the context of web, social media, and culture understanding. Miriam got her Ph.D. at the Multimedia group in EURECOM, Sophia Antipolis. After obtaining her PhD, she was a Postdoc in the Social Media group at Yahoo Labs Barcelona. Since then, she maintains collaborations with main academic research groups from both the multimedia and the social media communities.