Hopkins155
홈페이지 · 논문 92편
The Hopkins 155 dataset consists of 156 video sequences of two or three motions. Each video sequence motion corresponds to a low-dimensional subspace. There are 39−550 data vectors drawn from two or three motions for each video sequence. Source: Symmetric low-rank representation for subspace clustering Image Source: http://www.vision.jhu.edu/data/hopkins155/
Videos