An expert in computer vision who programmes computers to perceive the world in the same way that humans do, is to deliver a keynote speech during a visit to Qatar Computing Research Institute (QCRI), part of Hamad Bin Khalifa University (HBKU).
Dr Antonio Torralba, a professor of electrical engineering and computer science at the Massachusetts Institute of Technology (MIT) and a principal investigator at MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), will address the topic of ‘Learning to See’ at the Researchery on Monday, 25 March. Please see related link below.
In his talk, Dr Torralba will discuss recent advances in computer vision, a scientific field which deals with how computers can gain high-level understanding from digital images, videos, or audio and automate tasks that the human visual system can accomplish.
The MIT professor will demonstrate several applications for object recognition, computer graphics, and unsupervised learning from images and audio. Dr Torralba said that his research covers a wide range of topics in computer and human vision – including object and scene recognition in images, building systems that can see around the corner, studies on how deep neural networks work, and applications such as Pic2Recipe (a collaboration with QCRI) that predicts ingredients from a picture of food and suggest similar recipes.
I am also interested in other modalities such as audition and touch and how, together with vision, they can allow building systems to learn like humans do. A system able to perceive the world through multiple senses might be able to learn without requiring massive curated datasets.’
Dr. Torralba is the MIT director of the MIT-IBM Watson AI Lab and the inaugural director of The MIT Quest for Intelligence. He is the recipient of multiple awards, including a National Science Foundation CAREER Award. He is collaborating with QCRI scientists Ferda Ofli and Ingmar Weber on using machine learning to analyse social media images to better understand food habits in Qatar.
For more information about QCRI, visit qcri.org.qa.