Perceptual organization is the problem of identifying simplifying structure in raw visual data, for example, by grouping primitives that come from the same physical cause. A driving motivation behind perceptual organization research is to deliver compact representations that reduce the space of hypotheses for higher-level visual tasks. There is now also much interest in video processing, where the need for organization is even more acute due to the sheer size of video data. In neuroscience, there is evidence for many feedback connections influencing figure-ground discrimination and grouping processes, but, despite advances in deep learning, there has been relatively little work so far implementing such principles in computer vision. Driven by this observation, this year we steer the focus towards the use of feedback and recurrent visual processing in the organization of both static and dynamic imagery. 

We would like to bring together leading researchers on these topics, discuss the pros and cons of existing approaches, and debate on how the use of feedback and memory could help make a major leap over current feedforward visual architectures. 

We aim to provide a yearly summary of new progress in the field through a combination of keynote talks, workshop papers, and a panel discussion. Additionally, we also plan to have a session for invited student talks to give a chance for junior researchers to share their innovations. We will invite and encourage the participation from all related fields including computer vision, robotics, cognitive science, and HCI. This will provide an opportunity to share various perspectives for this exciting research agenda and encourage collaboration among multiple fields.