Author(s): Karimi A; Poullis C;

This paper addresses few-shot semantic segmentation and proposes a novel transductive end-to-end method that overcomes three key problems affecting performance. First, we present a novel ensemble of visual features learned from pretrained classification and ...

Article GUID: 38369571

Author(s): Chen Q; Poullis C;

No abstract

Article GUID: 36517657

Author(s): Chen Q; Poullis C;

Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour, gradient and smoot ...

Article GUID: 36385172