Context Image Segmentation is a complicated problem that often cannot be performed in a fully automatic manner. We use this dataset as a way for testing and exploring methods to make such semi-automatic segmentation work better Content 151 images with full segmentations and paint strokes (compiled by: http://www.robots.ox.ac.uk/~vgg/data/iseg/) Acknowledgements Visual Graphics Group at Oxford for Compiling the data GrabCut Dataset from Microsoft PASCAL Dataset Alpha Matting Dataset Inspiration - How well do different techniques work at expanding the initial labels to a full segmentation? - Which techniques are quick enough to run in real time (the paint strokes are normally given and the user waits for feedback, they can't be precomputed) - Are any of these techniques easy to implement in the JavaScript so they could be browser-based?