Tomasz Malisiewicz

Hi Angela, `esvm_features` is called very very often! I had made the design decision to not pre-compute features and instead make billions of `esvm_features` function calls. When you are dealing...

1. Feel free to remove whatever variables/steps you don't like if you want to reduce memory usage. It makes sense that model.mask is all ones in your case. 2. I...

Hi Angela, 1.) The initialization is just a simple mechanism for creating a mean-zero vector which can be used to detect the exemplar in its originating image. I made this...

Thanks Amir for catching this! I might have already fixed this issue in my development branch as I've refactored a lot of things. I haven't pushed any changes into the...

Hey Amir, do you know how to do pull requests in github? The idea is that you can for my code, fix your own fork. Then if you think that...

notice the synthetic demo, some of the frames are completely off by at least one border row/col

The folders with .lock extensions are lockfiles which are written to let multiple processes communicate when you want to perform large scale training on a cluster. If you are running...

You should try downloading the PASCAL VOC dataset from the website. You can also try seeing what the following lines do... > > I=convert_to_I('http://people.csail.mit.edu/tomasz/VOCdevkit/VOC2007/JPEGImages/003835.jpg') > > imagesc(I)

This is more important that I previously thought...