Semantic Segmentation with Second-Order Pooling
Joao Carreira, Rui Caseiro, Jorge Batista and Cristian Sminchisescu

Results on a random sample of images from the Pascal VOC 2011 Segmentation test set (48% VOC score, comp6).

You can now download source code to reproduce the results in the paper: code. This should work in a Linux 64 bits computer using MATLAB R2011b. For the VOC experiment it is recommendable to have 16 or preferrably 32 GB of RAM and at least 200GB of disk space.

Reference

[75] Semantic Segmentation with Second-Order Pooling
J. Carreira and R. Caseiro and J. Batista and C. Sminchisescu

European Conference on Computer Vision, 2012

Related References

[68] CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts
J. Carreira and C. Sminchisescu

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

Code