Deep holistic image understanding
Image understanding involves not only object recognition, but also object delineation. This shape recovery task is challenging because of two reasons. First, the necessity of learning a good representation of the visual inputs. Second, the need to account for contextual information across the image, such as edges and appearance consistency. Deep convolutional neural networks are successful at the former, but have limited capacity to delineate visual objects. I will present a framework that extends the capabilities of deep learning techniques to tackle this scenario, obtaining cutting edge results in semantic segmentation (i.e. detecting and delineating objects), and depth estimation.
Bernardino is a post-doc in Torr Vision Group at University of Oxford. He received his PhD degree from University College London in 2014, supervised by Prof. Massimiliano Pontil and Dr. Nadia Berthouze. He has published in top-tier machine learning conferences such as NIPS, ICML and AISTATS, receiving several awards such as the Best Paper Runner-up Prize at ICML 2013, and the Best Paper Award at ACII 2013. During his PhD he interned at Microsoft Research, Redmond. His research focuses on multitask and transfer learning methods applied to computer vision tasks such as object recognition and segmentation, and emotion recognition.