|Description (include details on usage, files and paper references)||The Polo instance segmentation dataset is a semantic segmentation task for Hough transform based segmentation masks. It consists of supervised segmentation for segmenting polo riders and humans into their own masks.
Zhang, H., Quan, L.: Partial similarity based nonparametric scene parsing in certain
environment. In: CVPR (2011)
S. Gould and Y. Zhang. Patchmatchgraph: building a graph of dense
patch correspondences for label transfer. In ECCV. 2012.
An Exemplar-based CRF for Multi-instance Object Segmentation. (pdf) (poster)
Xuming He, Stephen Gould, CVPR 2014
Multi-instance Object Segmentation with Exemplars
Xuming He, Stephen Gould, ICCV 2013